Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "VM:
   - z3fold fixes and enhancements by Henry Burns and Vitaly Wool

   - more accurate reclaimed slab caches calculations by Yafang Shao

   - fix MAP_UNINITIALIZED UAPI symbol to not depend on config, by
     Christoph Hellwig

   - !CONFIG_MMU fixes by Christoph Hellwig

   - new novmcoredd parameter to omit device dumps from vmcore, by
     Kairui Song

   - new test_meminit module for testing heap and pagealloc
     initialization, by Alexander Potapenko

   - ioremap improvements for huge mappings, by Anshuman Khandual

   - generalize kprobe page fault handling, by Anshuman Khandual

   - device-dax hotplug fixes and improvements, by Pavel Tatashin

   - enable synchronous DAX fault on powerpc, by Aneesh Kumar K.V

   - add pte_devmap() support for arm64, by Robin Murphy

   - unify locked_vm accounting with a helper, by Daniel Jordan

   - several misc fixes

  core/lib:
   - new typeof_member() macro including some users, by Alexey Dobriyan

   - make BIT() and GENMASK() available in asm, by Masahiro Yamada

   - changed LIST_POISON2 on x86_64 to 0xdead000000000122 for better
     code generation, by Alexey Dobriyan

   - rbtree code size optimizations, by Michel Lespinasse

   - convert struct pid count to refcount_t, by Joel Fernandes

  get_maintainer.pl:
   - add --no-moderated switch to skip moderated ML's, by Joe Perches

  misc:
   - ptrace PTRACE_GET_SYSCALL_INFO interface

   - coda updates

   - gdb scripts, various"

[ Using merge message suggestion from Vlastimil Babka, with some editing - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (100 commits)
  fs/select.c: use struct_size() in kmalloc()
  mm: add account_locked_vm utility function
  arm64: mm: implement pte_devmap support
  mm: introduce ARCH_HAS_PTE_DEVMAP
  mm: clean up is_device_*_page() definitions
  mm/mmap: move common defines to mman-common.h
  mm: move MAP_SYNC to asm-generic/mman-common.h
  device-dax: "Hotremove" persistent memory that is used like normal RAM
  mm/hotplug: make remove_memory() interface usable
  device-dax: fix memory and resource leak if hotplug fails
  include/linux/lz4.h: fix spelling and copy-paste errors in documentation
  ipc/mqueue.c: only perform resource calculation if user valid
  include/asm-generic/bug.h: fix "cut here" for WARN_ON for __WARN_TAINT architectures
  scripts/gdb: add helpers to find and list devices
  scripts/gdb: add lx-genpd-summary command
  drivers/pps/pps.c: clear offset flags in PPS_SETPARAMS ioctl
  kernel/pid.c: convert struct pid count to refcount_t
  drivers/rapidio/devices/rio_mport_cdev.c: NUL terminate some strings
  select: shift restore_saved_sigmask_unless() into poll_select_copy_remaining()
  select: change do_poll() to return -ERESTARTNOHAND rather than -EINTR
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -2877,6 +2877,17 @@
 			/sys/module/printk/parameters/console_suspend) to
 			turn on/off it dynamically.
 
+	novmcoredd	[KNL,KDUMP]
+			Disable device dump. Device dump allows drivers to
+			append dump data to vmcore so you can collect driver
+			specified debug info.  Drivers can append the data
+			without any limit and this data is stored in memory,
+			so this may cause significant memory stress.  Disabling
+			device dump can help save memory but the driver debug
+			data will be no longer available.  This parameter
+			is only available when CONFIG_PROC_VMCORE_DEVICE_DUMP
+			is set.
+
 	noaliencache	[MM, NUMA, SLAB] Disables the allocation of alien
 			caches in the slab allocator.  Saves per-node memory,
 			but will impact performance.

Documentation/devicetree/bindings/usb/s3c2410-usb.txt

@@ -4,7 +4,7 @@ OHCI
 
 Required properties:
  - compatible: should be "samsung,s3c2410-ohci" for USB host controller
- - reg: address and lenght of the controller memory mapped region
+ - reg: address and length of the controller memory mapped region
  - interrupts: interrupt number for the USB OHCI controller
  - clocks: Should reference the bus and host clocks
  - clock-names: Should contain two strings

Documentation/filesystems/coda.txt

@@ -481,7 +481,10 @@ kernel support.
 
 
 
-
+  struct coda_timespec {
+          int64_t         tv_sec;         /* seconds */
+          long            tv_nsec;        /* nanoseconds */
+  };
 
   struct coda_vattr {
           enum coda_vtype va_type;        /* vnode type (for create) */
@@ -493,9 +496,9 @@ kernel support.
           long            va_fileid;      /* file id */
           u_quad_t        va_size;        /* file size in bytes */
           long            va_blocksize;   /* blocksize preferred for i/o */
-          struct timespec va_atime;       /* time of last access */
+          struct coda_timespec va_atime;  /* time of last access */
-          struct timespec va_mtime;       /* time of last modification */
+          struct coda_timespec va_mtime;  /* time of last modification */
-          struct timespec va_ctime;       /* time file changed */
+          struct coda_timespec va_ctime;  /* time file changed */
           u_long          va_gen;         /* generation number of file */
           u_long          va_flags;       /* flags defined for file */
           dev_t           va_rdev;        /* device special file represents */

arch/alpha/include/asm/io.h

@@ -93,11 +93,6 @@ static inline void * phys_to_virt(unsigned long address)
 
 #define page_to_phys(page)	page_to_pa(page)
 
-static inline dma_addr_t __deprecated isa_page_to_bus(struct page *page)
-{
-	return page_to_phys(page);
-}
-
 /* Maximum PIO space address supported?  */
 #define IO_SPACE_LIMIT 0xffff
 

arch/arc/include/asm/pgtable.h

@@ -32,7 +32,7 @@
 #ifndef _ASM_ARC_PGTABLE_H
 #define _ASM_ARC_PGTABLE_H
 
-#include <linux/const.h>
+#include <linux/bits.h>
 #define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <asm/page.h>
@@ -215,11 +215,11 @@
 #define BITS_FOR_PTE	(PGDIR_SHIFT - PAGE_SHIFT)
 #define BITS_FOR_PGD	(32 - PGDIR_SHIFT)
 
-#define PGDIR_SIZE	_BITUL(PGDIR_SHIFT)	/* vaddr span, not PDG sz */
+#define PGDIR_SIZE	BIT(PGDIR_SHIFT)	/* vaddr span, not PDG sz */
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-#define	PTRS_PER_PTE	_BITUL(BITS_FOR_PTE)
+#define	PTRS_PER_PTE	BIT(BITS_FOR_PTE)
-#define	PTRS_PER_PGD	_BITUL(BITS_FOR_PGD)
+#define	PTRS_PER_PGD	BIT(BITS_FOR_PGD)
 
 /*
  * Number of entries a user land program use.

arch/arc/plat-eznps/include/plat/ctop.h

@@ -10,6 +10,7 @@
 #error "Incorrect ctop.h include"
 #endif
 
+#include <linux/bits.h>
 #include <linux/types.h>
 #include <soc/nps/common.h>
 
@@ -51,19 +52,19 @@
 #define CTOP_INST_AXOR_DI_R2_R2_R3		0x4A664C06
 
 /* Do not use D$ for address in 2G-3G */
-#define HW_COMPLY_KRN_NOT_D_CACHED		_BITUL(28)
+#define HW_COMPLY_KRN_NOT_D_CACHED		BIT(28)
 
 #define NPS_MSU_EN_CFG				0x80
 #define NPS_CRG_BLKID				0x480
-#define NPS_CRG_SYNC_BIT			_BITUL(0)
+#define NPS_CRG_SYNC_BIT			BIT(0)
 #define NPS_GIM_BLKID				0x5C0
 
 /* GIM registers and fields*/
-#define NPS_GIM_UART_LINE			_BITUL(7)
+#define NPS_GIM_UART_LINE			BIT(7)
-#define NPS_GIM_DBG_LAN_EAST_TX_DONE_LINE	_BITUL(10)
+#define NPS_GIM_DBG_LAN_EAST_TX_DONE_LINE	BIT(10)
-#define NPS_GIM_DBG_LAN_EAST_RX_RDY_LINE	_BITUL(11)
+#define NPS_GIM_DBG_LAN_EAST_RX_RDY_LINE	BIT(11)
-#define NPS_GIM_DBG_LAN_WEST_TX_DONE_LINE	_BITUL(25)
+#define NPS_GIM_DBG_LAN_WEST_TX_DONE_LINE	BIT(25)
-#define NPS_GIM_DBG_LAN_WEST_RX_RDY_LINE	_BITUL(26)
+#define NPS_GIM_DBG_LAN_WEST_RX_RDY_LINE	BIT(26)
 
 #ifndef __ASSEMBLY__
 /* Functional registers definition */

arch/arm/include/asm/io.h

@@ -30,7 +30,6 @@
  * ISA I/O bus memory addresses are 1:1 with the physical address.
  */
 #define isa_virt_to_bus virt_to_phys
-#define isa_page_to_bus page_to_phys
 #define isa_bus_to_virt phys_to_virt
 
 /*

arch/arm/mm/fault.c

@@ -27,28 +27,6 @@
 
 #ifdef CONFIG_MMU
 
-#ifdef CONFIG_KPROBES
-static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
-{
-	int ret = 0;
-
-	if (!user_mode(regs)) {
-		/* kprobe_running() needs smp_processor_id() */
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, fsr))
-			ret = 1;
-		preempt_enable();
-	}
-
-	return ret;
-}
-#else
-static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
-{
-	return 0;
-}
-#endif
-
 /*
  * This is useful to dump out the page tables associated with
  * 'addr' in mm 'mm'.
@@ -265,7 +243,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	vm_fault_t fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-	if (notify_page_fault(regs, fsr))
+	if (kprobe_page_fault(regs, fsr))
 		return 0;
 
 	tsk = current;

arch/arm64/Kconfig

@@ -24,6 +24,7 @@ config ARM64
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
+	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_DIRECT_MAP

arch/arm64/include/asm/pgtable-prot.h

@@ -16,6 +16,7 @@
 #define PTE_WRITE		(PTE_DBM)		 /* same as DBM (51) */
 #define PTE_DIRTY		(_AT(pteval_t, 1) << 55)
 #define PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
+#define PTE_DEVMAP		(_AT(pteval_t, 1) << 57)
 #define PTE_PROT_NONE		(_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */
 
 #ifndef __ASSEMBLY__

arch/arm64/include/asm/pgtable.h

@@ -79,6 +79,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
+#define pte_devmap(pte)		(!!(pte_val(pte) & PTE_DEVMAP))
 
 #define pte_cont_addr_end(addr, end)						\
 ({	unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK;	\
@@ -206,6 +207,11 @@ static inline pmd_t pmd_mkcont(pmd_t pmd)
 	return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
 }
 
+static inline pte_t pte_mkdevmap(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_DEVMAP));
+}
+
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	WRITE_ONCE(*ptep, pte);
@@ -388,6 +394,11 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define pmd_devmap(pmd)		pte_devmap(pmd_pte(pmd))
+#endif
+#define pmd_mkdevmap(pmd)	pte_pmd(pte_mkdevmap(pmd_pte(pmd)))
+
 #define __pmd_to_phys(pmd)	__pte_to_phys(pmd_pte(pmd))
 #define __phys_to_pmd_val(phys)	__phys_to_pte_val(phys)
 #define pmd_pfn(pmd)		((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT)
@@ -673,6 +684,16 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
 {
 	return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
 }
+
+static inline int pud_devmap(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pgd_devmap(pgd_t pgd)
+{
+	return 0;
+}
 #endif
 
 /*

arch/arm64/include/asm/sysreg.h

@@ -9,7 +9,7 @@
 #ifndef __ASM_SYSREG_H
 #define __ASM_SYSREG_H
 
-#include <linux/const.h>
+#include <linux/bits.h>
 #include <linux/stringify.h>
 
 /*
@@ -478,31 +478,31 @@
 #define SYS_CNTV_CVAL_EL02		sys_reg(3, 5, 14, 3, 2)
 
 /* Common SCTLR_ELx flags. */
-#define SCTLR_ELx_DSSBS	(_BITUL(44))
+#define SCTLR_ELx_DSSBS	(BIT(44))
-#define SCTLR_ELx_ENIA	(_BITUL(31))
+#define SCTLR_ELx_ENIA	(BIT(31))
-#define SCTLR_ELx_ENIB	(_BITUL(30))
+#define SCTLR_ELx_ENIB	(BIT(30))
-#define SCTLR_ELx_ENDA	(_BITUL(27))
+#define SCTLR_ELx_ENDA	(BIT(27))
-#define SCTLR_ELx_EE    (_BITUL(25))
+#define SCTLR_ELx_EE    (BIT(25))
-#define SCTLR_ELx_IESB	(_BITUL(21))
+#define SCTLR_ELx_IESB	(BIT(21))
-#define SCTLR_ELx_WXN	(_BITUL(19))
+#define SCTLR_ELx_WXN	(BIT(19))
-#define SCTLR_ELx_ENDB	(_BITUL(13))
+#define SCTLR_ELx_ENDB	(BIT(13))
-#define SCTLR_ELx_I	(_BITUL(12))
+#define SCTLR_ELx_I	(BIT(12))
-#define SCTLR_ELx_SA	(_BITUL(3))
+#define SCTLR_ELx_SA	(BIT(3))
-#define SCTLR_ELx_C	(_BITUL(2))
+#define SCTLR_ELx_C	(BIT(2))
-#define SCTLR_ELx_A	(_BITUL(1))
+#define SCTLR_ELx_A	(BIT(1))
-#define SCTLR_ELx_M	(_BITUL(0))
+#define SCTLR_ELx_M	(BIT(0))
 
 #define SCTLR_ELx_FLAGS	(SCTLR_ELx_M  | SCTLR_ELx_A | SCTLR_ELx_C | \
 			 SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_IESB)
 
 /* SCTLR_EL2 specific flags. */
-#define SCTLR_EL2_RES1	((_BITUL(4))  | (_BITUL(5))  | (_BITUL(11)) | (_BITUL(16)) | \
+#define SCTLR_EL2_RES1	((BIT(4))  | (BIT(5))  | (BIT(11)) | (BIT(16)) | \
-			 (_BITUL(18)) | (_BITUL(22)) | (_BITUL(23)) | (_BITUL(28)) | \
+			 (BIT(18)) | (BIT(22)) | (BIT(23)) | (BIT(28)) | \
-			 (_BITUL(29)))
+			 (BIT(29)))
-#define SCTLR_EL2_RES0	((_BITUL(6))  | (_BITUL(7))  | (_BITUL(8))  | (_BITUL(9))  | \
+#define SCTLR_EL2_RES0	((BIT(6))  | (BIT(7))  | (BIT(8))  | (BIT(9))  | \
-			 (_BITUL(10)) | (_BITUL(13)) | (_BITUL(14)) | (_BITUL(15)) | \
+			 (BIT(10)) | (BIT(13)) | (BIT(14)) | (BIT(15)) | \
-			 (_BITUL(17)) | (_BITUL(20)) | (_BITUL(24)) | (_BITUL(26)) | \
+			 (BIT(17)) | (BIT(20)) | (BIT(24)) | (BIT(26)) | \
-			 (_BITUL(27)) | (_BITUL(30)) | (_BITUL(31)) | \
+			 (BIT(27)) | (BIT(30)) | (BIT(31)) | \
 			 (0xffffefffUL << 32))
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
@@ -524,23 +524,23 @@
 #endif
 
 /* SCTLR_EL1 specific flags. */
-#define SCTLR_EL1_UCI		(_BITUL(26))
+#define SCTLR_EL1_UCI		(BIT(26))
-#define SCTLR_EL1_E0E		(_BITUL(24))
+#define SCTLR_EL1_E0E		(BIT(24))
-#define SCTLR_EL1_SPAN		(_BITUL(23))
+#define SCTLR_EL1_SPAN		(BIT(23))
-#define SCTLR_EL1_NTWE		(_BITUL(18))
+#define SCTLR_EL1_NTWE		(BIT(18))
-#define SCTLR_EL1_NTWI		(_BITUL(16))
+#define SCTLR_EL1_NTWI		(BIT(16))
-#define SCTLR_EL1_UCT		(_BITUL(15))
+#define SCTLR_EL1_UCT		(BIT(15))
-#define SCTLR_EL1_DZE		(_BITUL(14))
+#define SCTLR_EL1_DZE		(BIT(14))
-#define SCTLR_EL1_UMA		(_BITUL(9))
+#define SCTLR_EL1_UMA		(BIT(9))
-#define SCTLR_EL1_SED		(_BITUL(8))
+#define SCTLR_EL1_SED		(BIT(8))
-#define SCTLR_EL1_ITD		(_BITUL(7))
+#define SCTLR_EL1_ITD		(BIT(7))
-#define SCTLR_EL1_CP15BEN	(_BITUL(5))
+#define SCTLR_EL1_CP15BEN	(BIT(5))
-#define SCTLR_EL1_SA0		(_BITUL(4))
+#define SCTLR_EL1_SA0		(BIT(4))
 
-#define SCTLR_EL1_RES1	((_BITUL(11)) | (_BITUL(20)) | (_BITUL(22)) | (_BITUL(28)) | \
+#define SCTLR_EL1_RES1	((BIT(11)) | (BIT(20)) | (BIT(22)) | (BIT(28)) | \
-			 (_BITUL(29)))
+			 (BIT(29)))
-#define SCTLR_EL1_RES0  ((_BITUL(6))  | (_BITUL(10)) | (_BITUL(13)) | (_BITUL(17)) | \
+#define SCTLR_EL1_RES0  ((BIT(6))  | (BIT(10)) | (BIT(13)) | (BIT(17)) | \
-			 (_BITUL(27)) | (_BITUL(30)) | (_BITUL(31)) | \
+			 (BIT(27)) | (BIT(30)) | (BIT(31)) | \
 			 (0xffffefffUL << 32))
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
@@ -756,13 +756,13 @@
 #define ZCR_ELx_LEN_SIZE	9
 #define ZCR_ELx_LEN_MASK	0x1ff
 
-#define CPACR_EL1_ZEN_EL1EN	(_BITUL(16)) /* enable EL1 access */
+#define CPACR_EL1_ZEN_EL1EN	(BIT(16)) /* enable EL1 access */
-#define CPACR_EL1_ZEN_EL0EN	(_BITUL(17)) /* enable EL0 access, if EL1EN set */
+#define CPACR_EL1_ZEN_EL0EN	(BIT(17)) /* enable EL0 access, if EL1EN set */
 #define CPACR_EL1_ZEN		(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
 
 
 /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
-#define SYS_MPIDR_SAFE_VAL	(_BITUL(31))
+#define SYS_MPIDR_SAFE_VAL	(BIT(31))
 
 #ifdef __ASSEMBLY__
 

arch/arm64/mm/fault.c

@@ -59,28 +59,6 @@ static inline const struct fault_info *esr_to_debug_fault_info(unsigned int esr)
 	return debug_fault_info + DBG_ESR_EVT(esr);
 }
 
-#ifdef CONFIG_KPROBES
-static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
-{
-	int ret = 0;
-
-	/* kprobe_running() needs smp_processor_id() */
-	if (!user_mode(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, esr))
-			ret = 1;
-		preempt_enable();
-	}
-
-	return ret;
-}
-#else
-static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
-{
-	return 0;
-}
-#endif
-
 static void data_abort_decode(unsigned int esr)
 {
 	pr_alert("Data abort info:\n");
@@ -434,7 +412,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	unsigned long vm_flags = VM_READ | VM_WRITE;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-	if (notify_page_fault(regs, esr))
+	if (kprobe_page_fault(regs, esr))
 		return 0;
 
 	/*

arch/arm64/mm/mmu.c

@@ -942,6 +942,11 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
 	return dt_virt;
 }
 
+int __init arch_ioremap_p4d_supported(void)
+{
+	return 0;
+}
+
 int __init arch_ioremap_pud_supported(void)
 {
 	/*

arch/hexagon/include/asm/syscall.h

@@ -9,6 +9,8 @@
 #define _ASM_HEXAGON_SYSCALL_H
 
 #include <uapi/linux/audit.h>
+#include <linux/err.h>
+#include <asm/ptrace.h>
 
 typedef long (*syscall_fn)(unsigned long, unsigned long,
 	unsigned long, unsigned long,
@@ -31,6 +33,18 @@ static inline void syscall_get_arguments(struct task_struct *task,
 	memcpy(args, &(&regs->r00)[0], 6 * sizeof(args[0]));
 }
 
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	return IS_ERR_VALUE(regs->r00) ? regs->r00 : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->r00;
+}
+
 static inline int syscall_get_arch(struct task_struct *task)
 {
 	return AUDIT_ARCH_HEXAGON;

arch/ia64/mm/fault.c

@@ -21,28 +21,6 @@
 
 extern int die(char *, struct pt_regs *, long);
 
-#ifdef CONFIG_KPROBES
-static inline int notify_page_fault(struct pt_regs *regs, int trap)
-{
-	int ret = 0;
-
-	if (!user_mode(regs)) {
-		/* kprobe_running() needs smp_processor_id() */
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, trap))
-			ret = 1;
-		preempt_enable();
-	}
-
-	return ret;
-}
-#else
-static inline int notify_page_fault(struct pt_regs *regs, int trap)
-{
-	return 0;
-}
-#endif
-
 /*
  * Return TRUE if ADDRESS points at a page in the kernel's mapped segment
  * (inside region 5, on ia64) and that page is present.
@@ -116,7 +94,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	/*
 	 * This is to handle the kprobes on user space access instructions
 	 */
-	if (notify_page_fault(regs, TRAP_BRKPT))
+	if (kprobe_page_fault(regs, TRAP_BRKPT))
 		return;
 
 	if (user_mode(regs))

arch/mips/include/asm/io.h

@@ -149,8 +149,6 @@ static inline void *isa_bus_to_virt(unsigned long address)
 	return phys_to_virt(address);
 }
 
-#define isa_page_to_bus page_to_phys
-
 /*
  * However PCI ones are not necessarily 1:1 and therefore these interfaces
  * are forbidden in portable PCI drivers.

arch/mips/include/asm/kprobes.h

@@ -41,6 +41,7 @@ do {									\
 #define kretprobe_blacklist_size 0
 
 void arch_remove_kprobe(struct kprobe *p);
+int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {

arch/mips/include/asm/syscall.h

@@ -89,6 +89,12 @@ static inline unsigned long mips_get_syscall_arg(unsigned long *arg,
 	unreachable();
 }
 
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	return regs->regs[7] ? -regs->regs[2] : 0;
+}
+
 static inline long syscall_get_return_value(struct task_struct *task,
 					    struct pt_regs *regs)
 {

arch/mips/kernel/kprobes.c

@@ -398,7 +398,7 @@ out:
 	return 1;
 }
 
-static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();

arch/nds32/include/asm/syscall.h

@@ -26,7 +26,8 @@ struct pt_regs;
  *
  * It's only valid to call this when @task is known to be blocked.
  */
-int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
+static inline int
+syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
 	return regs->syscallno;
 }
@@ -47,7 +48,8 @@ int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
  * system call instruction.  This may not be the same as what the
  * register state looked like at system call entry tracing.
  */
-void syscall_rollback(struct task_struct *task, struct pt_regs *regs)
+static inline void
+syscall_rollback(struct task_struct *task, struct pt_regs *regs)
 {
 	regs->uregs[0] = regs->orig_r0;
 }
@@ -62,7 +64,8 @@ void syscall_rollback(struct task_struct *task, struct pt_regs *regs)
  * It's only valid to call this when @task is stopped for tracing on exit
  * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
-long syscall_get_error(struct task_struct *task, struct pt_regs *regs)
+static inline long
+syscall_get_error(struct task_struct *task, struct pt_regs *regs)
 {
 	unsigned long error = regs->uregs[0];
 	return IS_ERR_VALUE(error) ? error : 0;
@@ -79,7 +82,8 @@ long syscall_get_error(struct task_struct *task, struct pt_regs *regs)
  * It's only valid to call this when @task is stopped for tracing on exit
  * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
-long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs)
+static inline long
+syscall_get_return_value(struct task_struct *task, struct pt_regs *regs)
 {
 	return regs->uregs[0];
 }
@@ -99,8 +103,9 @@ long syscall_get_return_value(struct task_struct *task, struct pt_regs *regs)
  * It's only valid to call this when @task is stopped for tracing on exit
  * from a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
-void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
+static inline void
-			      int error, long val)
+syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
+			 int error, long val)
 {
 	regs->uregs[0] = (long)error ? error : val;
 }
@@ -118,8 +123,9 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
  * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
 #define SYSCALL_MAX_ARGS 6
-void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
+static inline void
-			   unsigned long *args)
+syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
+		      unsigned long *args)
 {
 	args[0] = regs->orig_r0;
 	args++;
@@ -138,8 +144,9 @@ void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
  * It's only valid to call this when @task is stopped for tracing on
  * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
  */
-void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
+static inline void
-			   const unsigned long *args)
+syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
+		      const unsigned long *args)
 {
 	regs->orig_r0 = args[0];
 	args++;

arch/parisc/include/asm/syscall.h

@@ -29,6 +29,13 @@ static inline void syscall_get_arguments(struct task_struct *tsk,
 	args[0] = regs->gr[26];
 }
 
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	unsigned long error = regs->gr[28];
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
 static inline long syscall_get_return_value(struct task_struct *task,
 						struct pt_regs *regs)
 {

arch/powerpc/Kconfig

@@ -129,6 +129,7 @@ config PPC
 	select ARCH_HAS_MMIOWB			if PPC64
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API                if PPC64
+	select ARCH_HAS_PTE_DEVMAP		if PPC_BOOK3S_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC64
@@ -136,7 +137,6 @@ config PPC
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if PPC64
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_HAS_ZONE_DEVICE		if PPC_BOOK3S_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_KEEP_MEMBLOCK
 	select ARCH_MIGHT_HAVE_PC_PARPORT

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -90,7 +90,6 @@
 #define _PAGE_SOFT_DIRTY	_RPAGE_SW3 /* software: software dirty tracking */
 #define _PAGE_SPECIAL		_RPAGE_SW2 /* software: special page */
 #define _PAGE_DEVMAP		_RPAGE_SW1 /* software: ZONE_DEVICE page */
-#define __HAVE_ARCH_PTE_DEVMAP
 
 /*
  * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE

arch/powerpc/include/asm/syscall.h

@@ -35,6 +35,16 @@ static inline void syscall_rollback(struct task_struct *task,
 	regs->gpr[3] = regs->orig_gpr3;
 }
 
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	/*
+	 * If the system call failed,
+	 * regs->gpr[3] contains a positive ERRORCODE.
+	 */
+	return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0;
+}
+
 static inline long syscall_get_return_value(struct task_struct *task,
 					    struct pt_regs *regs)
 {

arch/powerpc/include/uapi/asm/mman.h

@@ -21,15 +21,11 @@
 #define MAP_DENYWRITE	0x0800		/* ETXTBSY */
 #define MAP_EXECUTABLE	0x1000		/* mark it as an executable */
 
+
 #define MCL_CURRENT     0x2000          /* lock all currently mapped pages */
 #define MCL_FUTURE      0x4000          /* lock all additions to address space */
 #define MCL_ONFAULT	0x8000		/* lock all pages that are faulted in */
 
-#define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
-#define MAP_NONBLOCK	0x10000		/* do not block on IO */
-#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
-#define MAP_HUGETLB	0x40000		/* create a huge page mapping */
-
 /* Override any generic PKEY permission defines */
 #define PKEY_DISABLE_EXECUTE   0x4
 #undef PKEY_ACCESS_MASK

arch/powerpc/kvm/book3s_64_vio.c

@@ -19,6 +19,7 @@
 #include <linux/anon_inodes.h>
 #include <linux/iommu.h>
 #include <linux/file.h>
+#include <linux/mm.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -45,43 +46,6 @@ static unsigned long kvmppc_stt_pages(unsigned long tce_pages)
 	return tce_pages + ALIGN(stt_bytes, PAGE_SIZE) / PAGE_SIZE;
 }
 
-static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
-{
-	long ret = 0;
-
-	if (!current || !current->mm)
-		return ret; /* process exited */
-
-	down_write(&current->mm->mmap_sem);
-
-	if (inc) {
-		unsigned long locked, lock_limit;
-
-		locked = current->mm->locked_vm + stt_pages;
-		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			ret = -ENOMEM;
-		else
-			current->mm->locked_vm += stt_pages;
-	} else {
-		if (WARN_ON_ONCE(stt_pages > current->mm->locked_vm))
-			stt_pages = current->mm->locked_vm;
-
-		current->mm->locked_vm -= stt_pages;
-	}
-
-	pr_debug("[%d] RLIMIT_MEMLOCK KVM %c%ld %ld/%ld%s\n", current->pid,
-			inc ? '+' : '-',
-			stt_pages << PAGE_SHIFT,
-			current->mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK),
-			ret ? " - exceeded" : "");
-
-	up_write(&current->mm->mmap_sem);
-
-	return ret;
-}
-
 static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
 {
 	struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
@@ -291,7 +255,7 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 
 	kvm_put_kvm(stt->kvm);
 
-	kvmppc_account_memlimit(
+	account_locked_vm(current->mm,
 		kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false);
 	call_rcu(&stt->rcu, release_spapr_tce_table);
 
@@ -316,7 +280,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 		return -EINVAL;
 
 	npages = kvmppc_tce_pages(size);
-	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
+	ret = account_locked_vm(current->mm, kvmppc_stt_pages(npages), true);
 	if (ret)
 		return ret;
 
@@ -362,7 +326,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 
 	kfree(stt);
  fail_acct:
-	kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
+	account_locked_vm(current->mm, kvmppc_stt_pages(npages), false);
 	return ret;
 }
 

arch/powerpc/mm/book3s64/iommu_api.c

@@ -14,6 +14,7 @@
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <linux/sizes.h>
+#include <linux/mm.h>
 #include <asm/mmu_context.h>
 #include <asm/pte-walk.h>
 #include <linux/mm_inline.h>
@@ -46,40 +47,6 @@ struct mm_iommu_table_group_mem_t {
 	u64 dev_hpa;		/* Device memory base address */
 };
 
-static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
-		unsigned long npages, bool incr)
-{
-	long ret = 0, locked, lock_limit;
-
-	if (!npages)
-		return 0;
-
-	down_write(&mm->mmap_sem);
-
-	if (incr) {
-		locked = mm->locked_vm + npages;
-		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			ret = -ENOMEM;
-		else
-			mm->locked_vm += npages;
-	} else {
-		if (WARN_ON_ONCE(npages > mm->locked_vm))
-			npages = mm->locked_vm;
-		mm->locked_vm -= npages;
-	}
-
-	pr_debug("[%d] RLIMIT_MEMLOCK HASH64 %c%ld %ld/%ld\n",
-			current ? current->pid : 0,
-			incr ? '+' : '-',
-			npages << PAGE_SHIFT,
-			mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK));
-	up_write(&mm->mmap_sem);
-
-	return ret;
-}
-
 bool mm_iommu_preregistered(struct mm_struct *mm)
 {
 	return !list_empty(&mm->context.iommu_group_mem_list);
@@ -96,7 +63,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	unsigned long entry, chunk;
 
 	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
-		ret = mm_iommu_adjust_locked_vm(mm, entries, true);
+		ret = account_locked_vm(mm, entries, true);
 		if (ret)
 			return ret;
 
@@ -211,7 +178,7 @@ free_exit:
 	kfree(mem);
 
 unlock_exit:
-	mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+	account_locked_vm(mm, locked_entries, false);
 
 	return ret;
 }
@@ -311,7 +278,7 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 unlock_exit:
 	mutex_unlock(&mem_list_mutex);
 
-	mm_iommu_adjust_locked_vm(mm, unlock_entries, false);
+	account_locked_vm(mm, unlock_entries, false);
 
 	return ret;
 }

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -1237,3 +1237,8 @@ int radix__ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size,
 		return 0;
 	}
 }
+
+int __init arch_ioremap_p4d_supported(void)
+{
+	return 0;
+}

arch/powerpc/mm/fault.c

@@ -42,26 +42,6 @@
 #include <asm/debug.h>
 #include <asm/kup.h>
 
-static inline bool notify_page_fault(struct pt_regs *regs)
-{
-	bool ret = false;
-
-#ifdef CONFIG_KPROBES
-	/* kprobe_running() needs smp_processor_id() */
-	if (!user_mode(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, 11))
-			ret = true;
-		preempt_enable();
-	}
-#endif /* CONFIG_KPROBES */
-
-	if (unlikely(debugger_fault_handler(regs)))
-		ret = true;
-
-	return ret;
-}
-
 /*
  * Check whether the instruction inst is a store using
  * an update addressing form which will update r1.
@@ -461,8 +441,9 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
 	int is_write = page_fault_is_write(error_code);
 	vm_fault_t fault, major = 0;
 	bool must_retry = false;
+	bool kprobe_fault = kprobe_page_fault(regs, 11);
 
-	if (notify_page_fault(regs))
+	if (unlikely(debugger_fault_handler(regs) || kprobe_fault))
 		return 0;
 
 	if (unlikely(page_fault_is_bad(error_code))) {

arch/s390/include/asm/ctl_reg.h

@@ -8,27 +8,27 @@
 #ifndef __ASM_CTL_REG_H
 #define __ASM_CTL_REG_H
 
-#include <linux/const.h>
+#include <linux/bits.h>
 
-#define CR0_CLOCK_COMPARATOR_SIGN	_BITUL(63 - 10)
+#define CR0_CLOCK_COMPARATOR_SIGN	BIT(63 - 10)
-#define CR0_EMERGENCY_SIGNAL_SUBMASK	_BITUL(63 - 49)
+#define CR0_EMERGENCY_SIGNAL_SUBMASK	BIT(63 - 49)
-#define CR0_EXTERNAL_CALL_SUBMASK	_BITUL(63 - 50)
+#define CR0_EXTERNAL_CALL_SUBMASK	BIT(63 - 50)
-#define CR0_CLOCK_COMPARATOR_SUBMASK	_BITUL(63 - 52)
+#define CR0_CLOCK_COMPARATOR_SUBMASK	BIT(63 - 52)
-#define CR0_CPU_TIMER_SUBMASK		_BITUL(63 - 53)
+#define CR0_CPU_TIMER_SUBMASK		BIT(63 - 53)
-#define CR0_SERVICE_SIGNAL_SUBMASK	_BITUL(63 - 54)
+#define CR0_SERVICE_SIGNAL_SUBMASK	BIT(63 - 54)
-#define CR0_UNUSED_56			_BITUL(63 - 56)
+#define CR0_UNUSED_56			BIT(63 - 56)
-#define CR0_INTERRUPT_KEY_SUBMASK	_BITUL(63 - 57)
+#define CR0_INTERRUPT_KEY_SUBMASK	BIT(63 - 57)
-#define CR0_MEASUREMENT_ALERT_SUBMASK	_BITUL(63 - 58)
+#define CR0_MEASUREMENT_ALERT_SUBMASK	BIT(63 - 58)
 
-#define CR2_GUARDED_STORAGE		_BITUL(63 - 59)
+#define CR2_GUARDED_STORAGE		BIT(63 - 59)
 
-#define CR14_UNUSED_32			_BITUL(63 - 32)
+#define CR14_UNUSED_32			BIT(63 - 32)
-#define CR14_UNUSED_33			_BITUL(63 - 33)
+#define CR14_UNUSED_33			BIT(63 - 33)
-#define CR14_CHANNEL_REPORT_SUBMASK	_BITUL(63 - 35)
+#define CR14_CHANNEL_REPORT_SUBMASK	BIT(63 - 35)
-#define CR14_RECOVERY_SUBMASK		_BITUL(63 - 36)
+#define CR14_RECOVERY_SUBMASK		BIT(63 - 36)
-#define CR14_DEGRADATION_SUBMASK	_BITUL(63 - 37)
+#define CR14_DEGRADATION_SUBMASK	BIT(63 - 37)
-#define CR14_EXTERNAL_DAMAGE_SUBMASK	_BITUL(63 - 38)
+#define CR14_EXTERNAL_DAMAGE_SUBMASK	BIT(63 - 38)
-#define CR14_WARNING_SUBMASK		_BITUL(63 - 39)
+#define CR14_WARNING_SUBMASK		BIT(63 - 39)
 
 #ifndef __ASSEMBLY__
 

arch/s390/include/asm/nmi.h

@@ -12,7 +12,7 @@
 #ifndef _ASM_S390_NMI_H
 #define _ASM_S390_NMI_H
 
-#include <linux/const.h>
+#include <linux/bits.h>
 #include <linux/types.h>
 
 #define MCIC_SUBCLASS_MASK	(1ULL<<63 | 1ULL<<62 | 1ULL<<61 | \
@@ -20,15 +20,15 @@
 				1ULL<<55 | 1ULL<<54 | 1ULL<<53 | \
 				1ULL<<52 | 1ULL<<47 | 1ULL<<46 | \
 				1ULL<<45 | 1ULL<<44)
-#define MCCK_CODE_SYSTEM_DAMAGE		_BITUL(63)
+#define MCCK_CODE_SYSTEM_DAMAGE		BIT(63)
-#define MCCK_CODE_EXT_DAMAGE		_BITUL(63 - 5)
+#define MCCK_CODE_EXT_DAMAGE		BIT(63 - 5)
-#define MCCK_CODE_CP			_BITUL(63 - 9)
+#define MCCK_CODE_CP			BIT(63 - 9)
-#define MCCK_CODE_CPU_TIMER_VALID	_BITUL(63 - 46)
+#define MCCK_CODE_CPU_TIMER_VALID	BIT(63 - 46)
-#define MCCK_CODE_PSW_MWP_VALID		_BITUL(63 - 20)
+#define MCCK_CODE_PSW_MWP_VALID		BIT(63 - 20)
-#define MCCK_CODE_PSW_IA_VALID		_BITUL(63 - 23)
+#define MCCK_CODE_PSW_IA_VALID		BIT(63 - 23)
-#define MCCK_CODE_CR_VALID		_BITUL(63 - 29)
+#define MCCK_CODE_CR_VALID		BIT(63 - 29)
-#define MCCK_CODE_GS_VALID		_BITUL(63 - 36)
+#define MCCK_CODE_GS_VALID		BIT(63 - 36)
-#define MCCK_CODE_FC_VALID		_BITUL(63 - 43)
+#define MCCK_CODE_FC_VALID		BIT(63 - 43)
 
 #ifndef __ASSEMBLY__
 

arch/s390/include/asm/processor.h

@@ -12,7 +12,7 @@
 #ifndef __ASM_S390_PROCESSOR_H
 #define __ASM_S390_PROCESSOR_H
 
-#include <linux/const.h>
+#include <linux/bits.h>
 
 #define CIF_MCCK_PENDING	0	/* machine check handling is pending */
 #define CIF_ASCE_PRIMARY	1	/* primary asce needs fixup / uaccess */
@@ -24,15 +24,15 @@
 #define CIF_MCCK_GUEST		7	/* machine check happening in guest */
 #define CIF_DEDICATED_CPU	8	/* this CPU is dedicated */
 
-#define _CIF_MCCK_PENDING	_BITUL(CIF_MCCK_PENDING)
+#define _CIF_MCCK_PENDING	BIT(CIF_MCCK_PENDING)
-#define _CIF_ASCE_PRIMARY	_BITUL(CIF_ASCE_PRIMARY)
+#define _CIF_ASCE_PRIMARY	BIT(CIF_ASCE_PRIMARY)
-#define _CIF_ASCE_SECONDARY	_BITUL(CIF_ASCE_SECONDARY)
+#define _CIF_ASCE_SECONDARY	BIT(CIF_ASCE_SECONDARY)
-#define _CIF_NOHZ_DELAY		_BITUL(CIF_NOHZ_DELAY)
+#define _CIF_NOHZ_DELAY		BIT(CIF_NOHZ_DELAY)
-#define _CIF_FPU		_BITUL(CIF_FPU)
+#define _CIF_FPU		BIT(CIF_FPU)
-#define _CIF_IGNORE_IRQ		_BITUL(CIF_IGNORE_IRQ)
+#define _CIF_IGNORE_IRQ		BIT(CIF_IGNORE_IRQ)
-#define _CIF_ENABLED_WAIT	_BITUL(CIF_ENABLED_WAIT)
+#define _CIF_ENABLED_WAIT	BIT(CIF_ENABLED_WAIT)
-#define _CIF_MCCK_GUEST		_BITUL(CIF_MCCK_GUEST)
+#define _CIF_MCCK_GUEST		BIT(CIF_MCCK_GUEST)
-#define _CIF_DEDICATED_CPU	_BITUL(CIF_DEDICATED_CPU)
+#define _CIF_DEDICATED_CPU	BIT(CIF_DEDICATED_CPU)
 
 #ifndef __ASSEMBLY__
 

arch/s390/include/asm/ptrace.h

@@ -7,7 +7,7 @@
 #ifndef _S390_PTRACE_H
 #define _S390_PTRACE_H
 
-#include <linux/const.h>
+#include <linux/bits.h>
 #include <uapi/asm/ptrace.h>
 
 #define PIF_SYSCALL		0	/* inside a system call */
@@ -15,10 +15,10 @@
 #define PIF_SYSCALL_RESTART	2	/* restart the current system call */
 #define PIF_GUEST_FAULT		3	/* indicates program check in sie64a */
 
-#define _PIF_SYSCALL		_BITUL(PIF_SYSCALL)
+#define _PIF_SYSCALL		BIT(PIF_SYSCALL)
-#define _PIF_PER_TRAP		_BITUL(PIF_PER_TRAP)
+#define _PIF_PER_TRAP		BIT(PIF_PER_TRAP)
-#define _PIF_SYSCALL_RESTART	_BITUL(PIF_SYSCALL_RESTART)
+#define _PIF_SYSCALL_RESTART	BIT(PIF_SYSCALL_RESTART)
-#define _PIF_GUEST_FAULT	_BITUL(PIF_GUEST_FAULT)
+#define _PIF_GUEST_FAULT	BIT(PIF_GUEST_FAULT)
 
 #ifndef __ASSEMBLY__
 

arch/s390/include/asm/setup.h

@@ -6,7 +6,7 @@
 #ifndef _ASM_S390_SETUP_H
 #define _ASM_S390_SETUP_H
 
-#include <linux/const.h>
+#include <linux/bits.h>
 #include <uapi/asm/setup.h>
 
 #define EP_OFFSET		0x10008
@@ -21,25 +21,25 @@
  * Machine features detected in early.c
  */
 
-#define MACHINE_FLAG_VM		_BITUL(0)
+#define MACHINE_FLAG_VM		BIT(0)
-#define MACHINE_FLAG_KVM	_BITUL(1)
+#define MACHINE_FLAG_KVM	BIT(1)
-#define MACHINE_FLAG_LPAR	_BITUL(2)
+#define MACHINE_FLAG_LPAR	BIT(2)
-#define MACHINE_FLAG_DIAG9C	_BITUL(3)
+#define MACHINE_FLAG_DIAG9C	BIT(3)
-#define MACHINE_FLAG_ESOP	_BITUL(4)
+#define MACHINE_FLAG_ESOP	BIT(4)
-#define MACHINE_FLAG_IDTE	_BITUL(5)
+#define MACHINE_FLAG_IDTE	BIT(5)
-#define MACHINE_FLAG_DIAG44	_BITUL(6)
+#define MACHINE_FLAG_DIAG44	BIT(6)
-#define MACHINE_FLAG_EDAT1	_BITUL(7)
+#define MACHINE_FLAG_EDAT1	BIT(7)
-#define MACHINE_FLAG_EDAT2	_BITUL(8)
+#define MACHINE_FLAG_EDAT2	BIT(8)
-#define MACHINE_FLAG_TOPOLOGY	_BITUL(10)
+#define MACHINE_FLAG_TOPOLOGY	BIT(10)
-#define MACHINE_FLAG_TE		_BITUL(11)
+#define MACHINE_FLAG_TE		BIT(11)
-#define MACHINE_FLAG_TLB_LC	_BITUL(12)
+#define MACHINE_FLAG_TLB_LC	BIT(12)
-#define MACHINE_FLAG_VX		_BITUL(13)
+#define MACHINE_FLAG_VX		BIT(13)
-#define MACHINE_FLAG_TLB_GUEST	_BITUL(14)
+#define MACHINE_FLAG_TLB_GUEST	BIT(14)
-#define MACHINE_FLAG_NX		_BITUL(15)
+#define MACHINE_FLAG_NX		BIT(15)
-#define MACHINE_FLAG_GS		_BITUL(16)
+#define MACHINE_FLAG_GS		BIT(16)
-#define MACHINE_FLAG_SCC	_BITUL(17)
+#define MACHINE_FLAG_SCC	BIT(17)
 
-#define LPP_MAGIC		_BITUL(31)
+#define LPP_MAGIC		BIT(31)
 #define LPP_PID_MASK		_AC(0xffffffff, UL)
 
 /* Offsets to entry points in kernel/head.S  */

arch/s390/include/asm/thread_info.h

@@ -8,7 +8,7 @@
 #ifndef _ASM_THREAD_INFO_H
 #define _ASM_THREAD_INFO_H
 
-#include <linux/const.h>
+#include <linux/bits.h>
 
 /*
  * General size of kernel stacks
@@ -82,21 +82,21 @@ void arch_setup_new_exec(void);
 #define TIF_SECCOMP		26	/* secure computing */
 #define TIF_SYSCALL_TRACEPOINT	27	/* syscall tracepoint instrumentation */
 
-#define _TIF_NOTIFY_RESUME	_BITUL(TIF_NOTIFY_RESUME)
+#define _TIF_NOTIFY_RESUME	BIT(TIF_NOTIFY_RESUME)
-#define _TIF_SIGPENDING		_BITUL(TIF_SIGPENDING)
+#define _TIF_SIGPENDING		BIT(TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED	_BITUL(TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED	BIT(TIF_NEED_RESCHED)
-#define _TIF_UPROBE		_BITUL(TIF_UPROBE)
+#define _TIF_UPROBE		BIT(TIF_UPROBE)
-#define _TIF_GUARDED_STORAGE	_BITUL(TIF_GUARDED_STORAGE)
+#define _TIF_GUARDED_STORAGE	BIT(TIF_GUARDED_STORAGE)
-#define _TIF_PATCH_PENDING	_BITUL(TIF_PATCH_PENDING)
+#define _TIF_PATCH_PENDING	BIT(TIF_PATCH_PENDING)
-#define _TIF_ISOLATE_BP		_BITUL(TIF_ISOLATE_BP)
+#define _TIF_ISOLATE_BP		BIT(TIF_ISOLATE_BP)
-#define _TIF_ISOLATE_BP_GUEST	_BITUL(TIF_ISOLATE_BP_GUEST)
+#define _TIF_ISOLATE_BP_GUEST	BIT(TIF_ISOLATE_BP_GUEST)
 
-#define _TIF_31BIT		_BITUL(TIF_31BIT)
+#define _TIF_31BIT		BIT(TIF_31BIT)
-#define _TIF_SINGLE_STEP	_BITUL(TIF_SINGLE_STEP)
+#define _TIF_SINGLE_STEP	BIT(TIF_SINGLE_STEP)
 
-#define _TIF_SYSCALL_TRACE	_BITUL(TIF_SYSCALL_TRACE)
+#define _TIF_SYSCALL_TRACE	BIT(TIF_SYSCALL_TRACE)
-#define _TIF_SYSCALL_AUDIT	_BITUL(TIF_SYSCALL_AUDIT)
+#define _TIF_SYSCALL_AUDIT	BIT(TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP		_BITUL(TIF_SECCOMP)
+#define _TIF_SECCOMP		BIT(TIF_SECCOMP)
-#define _TIF_SYSCALL_TRACEPOINT	_BITUL(TIF_SYSCALL_TRACEPOINT)
+#define _TIF_SYSCALL_TRACEPOINT	BIT(TIF_SYSCALL_TRACEPOINT)
 
 #endif /* _ASM_THREAD_INFO_H */

arch/s390/mm/fault.c

@@ -67,20 +67,6 @@ static int __init fault_init(void)
 }
 early_initcall(fault_init);
 
-static inline int notify_page_fault(struct pt_regs *regs)
-{
-	int ret = 0;
-
-	/* kprobe_running() needs smp_processor_id() */
-	if (kprobes_built_in() && !user_mode(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, 14))
-			ret = 1;
-		preempt_enable();
-	}
-	return ret;
-}
-
 /*
  * Find out which address space caused the exception.
  */
@@ -412,7 +398,7 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 	 */
 	clear_pt_regs_flag(regs, PIF_PER_TRAP);
 
-	if (notify_page_fault(regs))
+	if (kprobe_page_fault(regs, 14))
 		return 0;
 
 	mm = tsk->mm;

arch/sh/mm/fault.c

@@ -24,20 +24,6 @@
 #include <asm/tlbflush.h>
 #include <asm/traps.h>
 
-static inline int notify_page_fault(struct pt_regs *regs, int trap)
-{
-	int ret = 0;
-
-	if (kprobes_built_in() && !user_mode(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, trap))
-			ret = 1;
-		preempt_enable();
-	}
-
-	return ret;
-}
-
 static void
 force_sig_info_fault(int si_signo, int si_code, unsigned long address)
 {
@@ -412,14 +398,14 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 	if (unlikely(fault_in_kernel_space(address))) {
 		if (vmalloc_fault(address) >= 0)
 			return;
-		if (notify_page_fault(regs, vec))
+		if (kprobe_page_fault(regs, vec))
 			return;
 
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
 
-	if (unlikely(notify_page_fault(regs, vec)))
+	if (unlikely(kprobe_page_fault(regs, vec)))
 		return;
 
 	/* Only enable interrupts if they were on before the fault */

arch/sparc/include/uapi/asm/mman.h

@@ -22,10 +22,4 @@
 #define MCL_FUTURE      0x4000          /* lock all additions to address space */
 #define MCL_ONFAULT	0x8000		/* lock all pages that are faulted in */
 
-#define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
-#define MAP_NONBLOCK	0x10000		/* do not block on IO */
-#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
-#define MAP_HUGETLB	0x40000		/* create a huge page mapping */
-
-
 #endif /* _UAPI__SPARC_MMAN_H__ */

arch/sparc/mm/fault_64.c

@@ -38,20 +38,6 @@
 
 int show_unhandled_signals = 1;
 
-static inline __kprobes int notify_page_fault(struct pt_regs *regs)
-{
-	int ret = 0;
-
-	/* kprobe_running() needs smp_processor_id() */
-	if (kprobes_built_in() && !user_mode(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, 0))
-			ret = 1;
-		preempt_enable();
-	}
-	return ret;
-}
-
 static void __kprobes unhandled_fault(unsigned long address,
 				      struct task_struct *tsk,
 				      struct pt_regs *regs)
@@ -285,7 +271,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 
 	fault_code = get_thread_fault_code();
 
-	if (notify_page_fault(regs))
+	if (kprobe_page_fault(regs, 0))
 		goto exit_exception;
 
 	si_code = SEGV_MAPERR;

arch/x86/Kconfig

@@ -70,6 +70,7 @@ config X86
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PMEM_API		if X86_64
+	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
@@ -80,7 +81,6 @@ config X86
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_HAS_ZONE_DEVICE		if X86_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT

arch/x86/include/asm/io.h

@@ -165,7 +165,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
 {
 	return (unsigned int)virt_to_phys(address);
 }
-#define isa_page_to_bus(page)	((unsigned int)page_to_phys(page))
 #define isa_bus_to_virt		phys_to_virt
 
 /*

arch/x86/include/asm/pgtable.h

@@ -271,7 +271,7 @@ static inline int has_transparent_hugepage(void)
 	return boot_cpu_has(X86_FEATURE_PSE);
 }
 
-#ifdef __HAVE_ARCH_PTE_DEVMAP
+#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
 static inline int pmd_devmap(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_DEVMAP);
@@ -732,7 +732,7 @@ static inline int pte_present(pte_t a)
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
-#ifdef __HAVE_ARCH_PTE_DEVMAP
+#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
 static inline int pte_devmap(pte_t a)
 {
 	return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP;

arch/x86/include/asm/pgtable_types.h

@@ -103,7 +103,6 @@
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #define _PAGE_DEVMAP	(_AT(u64, 1) << _PAGE_BIT_DEVMAP)
-#define __HAVE_ARCH_PTE_DEVMAP
 #else
 #define _PAGE_NX	(_AT(pteval_t, 0))
 #define _PAGE_DEVMAP	(_AT(pteval_t, 0))

arch/x86/mm/fault.c

@@ -46,23 +46,6 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
 	return 0;
 }
 
-static nokprobe_inline int kprobes_fault(struct pt_regs *regs)
-{
-	if (!kprobes_built_in())
-		return 0;
-	if (user_mode(regs))
-		return 0;
-	/*
-	 * To be potentially processing a kprobe fault and to be allowed to call
-	 * kprobe_running(), we have to be non-preemptible.
-	 */
-	if (preemptible())
-		return 0;
-	if (!kprobe_running())
-		return 0;
-	return kprobe_fault_handler(regs, X86_TRAP_PF);
-}
-
 /*
  * Prefetch quirks:
  *
@@ -1282,7 +1265,7 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
 		return;
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (kprobes_fault(regs))
+	if (kprobe_page_fault(regs, X86_TRAP_PF))
 		return;
 
 	/*
@@ -1313,7 +1296,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	mm = tsk->mm;
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (unlikely(kprobes_fault(regs)))
+	if (unlikely(kprobe_page_fault(regs, X86_TRAP_PF)))
 		return;
 
 	/*

arch/x86/mm/ioremap.c

@@ -459,6 +459,11 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
+int __init arch_ioremap_p4d_supported(void)
+{
+	return 0;
+}
+
 int __init arch_ioremap_pud_supported(void)
 {
 #ifdef CONFIG_X86_64

arch/xtensa/include/uapi/asm/mman.h

@@ -56,12 +56,8 @@
 #define MAP_STACK	0x40000		/* give out an address that is best suited for process/thread stacks */
 #define MAP_HUGETLB	0x80000		/* create a huge page mapping */
 #define MAP_FIXED_NOREPLACE 0x100000	/* MAP_FIXED which doesn't unmap underlying mapping */
-#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED
+#define MAP_UNINITIALIZED 0x4000000	/* For anonymous mmap, memory could be
-# define MAP_UNINITIALIZED 0x4000000	/* For anonymous mmap, memory could be
 					 * uninitialized */
-#else
-# define MAP_UNINITIALIZED 0x0		/* Don't support this flag */
-#endif
 
 /*
  * Flags for msync

drivers/dax/dax-private.h

@@ -43,6 +43,7 @@ struct dax_region {
  * @target_node: effective numa node if dev_dax memory range is onlined
  * @dev - device core
  * @pgmap - pgmap for memmap setup / lifetime (driver owned)
+ * @dax_mem_res: physical address range of hotadded DAX memory
  */
 struct dev_dax {
 	struct dax_region *region;
@@ -50,6 +51,7 @@ struct dev_dax {
 	int target_node;
 	struct device dev;
 	struct dev_pagemap pgmap;
+	struct resource *dax_kmem_res;
 };
 
 static inline struct dev_dax *to_dev_dax(struct device *dev)

drivers/dax/kmem.c

@@ -66,23 +66,59 @@ int dev_dax_kmem_probe(struct device *dev)
 	new_res->name = dev_name(dev);
 
 	rc = add_memory(numa_node, new_res->start, resource_size(new_res));
-	if (rc)
+	if (rc) {
+		release_resource(new_res);
+		kfree(new_res);
 		return rc;
+	}
+	dev_dax->dax_kmem_res = new_res;
 
 	return 0;
 }
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static int dev_dax_kmem_remove(struct device *dev)
+{
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+	struct resource *res = dev_dax->dax_kmem_res;
+	resource_size_t kmem_start = res->start;
+	resource_size_t kmem_size = resource_size(res);
+	int rc;
+
+	/*
+	 * We have one shot for removing memory, if some memory blocks were not
+	 * offline prior to calling this function remove_memory() will fail, and
+	 * there is no way to hotremove this memory until reboot because device
+	 * unbind will succeed even if we return failure.
+	 */
+	rc = remove_memory(dev_dax->target_node, kmem_start, kmem_size);
+	if (rc) {
+		dev_err(dev,
+			"DAX region %pR cannot be hotremoved until the next reboot\n",
+			res);
+		return rc;
+	}
+
+	/* Release and free dax resources */
+	release_resource(res);
+	kfree(res);
+	dev_dax->dax_kmem_res = NULL;
+
+	return 0;
+}
+#else
 static int dev_dax_kmem_remove(struct device *dev)
 {
 	/*
-	 * Purposely leak the request_mem_region() for the device-dax
+	 * Without hotremove purposely leak the request_mem_region() for the
-	 * range and return '0' to ->remove() attempts. The removal of
+	 * device-dax range and return '0' to ->remove() attempts. The removal
-	 * the device from the driver always succeeds, but the region
+	 * of the device from the driver always succeeds, but the region is
-	 * is permanently pinned as reserved by the unreleased
+	 * permanently pinned as reserved by the unreleased
 	 * request_mem_region().
 	 */
 	return 0;
 }
+#endif /* CONFIG_MEMORY_HOTREMOVE */
 
 static struct dax_device_driver device_dax_kmem_driver = {
 	.drv = {

drivers/fpga/dfl-afu-dma-region.c

@@ -12,6 +12,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/sched/signal.h>
 #include <linux/uaccess.h>
+#include <linux/mm.h>
 
 #include "dfl-afu.h"
 
@@ -31,52 +32,6 @@ void afu_dma_region_init(struct dfl_feature_platform_data *pdata)
 	afu->dma_regions = RB_ROOT;
 }
 
-/**
- * afu_dma_adjust_locked_vm - adjust locked memory
- * @dev: port device
- * @npages: number of pages
- * @incr: increase or decrease locked memory
- *
- * Increase or decrease the locked memory size with npages input.
- *
- * Return 0 on success.
- * Return -ENOMEM if locked memory size is over the limit and no CAP_IPC_LOCK.
- */
-static int afu_dma_adjust_locked_vm(struct device *dev, long npages, bool incr)
-{
-	unsigned long locked, lock_limit;
-	int ret = 0;
-
-	/* the task is exiting. */
-	if (!current->mm)
-		return 0;
-
-	down_write(&current->mm->mmap_sem);
-
-	if (incr) {
-		locked = current->mm->locked_vm + npages;
-		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
-		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-			ret = -ENOMEM;
-		else
-			current->mm->locked_vm += npages;
-	} else {
-		if (WARN_ON_ONCE(npages > current->mm->locked_vm))
-			npages = current->mm->locked_vm;
-		current->mm->locked_vm -= npages;
-	}
-
-	dev_dbg(dev, "[%d] RLIMIT_MEMLOCK %c%ld %ld/%ld%s\n", current->pid,
-		incr ? '+' : '-', npages << PAGE_SHIFT,
-		current->mm->locked_vm << PAGE_SHIFT, rlimit(RLIMIT_MEMLOCK),
-		ret ? "- exceeded" : "");
-
-	up_write(&current->mm->mmap_sem);
-
-	return ret;
-}
-
 /**
  * afu_dma_pin_pages - pin pages of given dma memory region
  * @pdata: feature device platform data
@@ -92,7 +47,7 @@ static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata,
 	struct device *dev = &pdata->dev->dev;
 	int ret, pinned;
 
-	ret = afu_dma_adjust_locked_vm(dev, npages, true);
+	ret = account_locked_vm(current->mm, npages, true);
 	if (ret)
 		return ret;
 
@@ -121,7 +76,7 @@ put_pages:
 free_pages:
 	kfree(region->pages);
 unlock_vm:
-	afu_dma_adjust_locked_vm(dev, npages, false);
+	account_locked_vm(current->mm, npages, false);
 	return ret;
 }
 
@@ -141,7 +96,7 @@ static void afu_dma_unpin_pages(struct dfl_feature_platform_data *pdata,
 
 	put_all_pages(region->pages, npages);
 	kfree(region->pages);
-	afu_dma_adjust_locked_vm(dev, npages, false);
+	account_locked_vm(current->mm, npages, false);
 
 	dev_dbg(dev, "%ld pages unpinned\n", npages);
 }

drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c

@@ -53,7 +53,7 @@ int mt76x02u_skb_dma_info(struct sk_buff *skb, int port, u32 flags)
 	pad = round_up(skb->len, 4) + 4 - skb->len;
 
 	/* First packet of a A-MSDU burst keeps track of the whole burst
-	 * length, need to update lenght of it and the last packet.
+	 * length, need to update length of it and the last packet.
 	 */
 	skb_walk_frags(skb, iter) {
 		last = iter;

drivers/pps/pps.c

@@ -152,6 +152,14 @@ static long pps_cdev_ioctl(struct file *file,
 			pps->params.mode |= PPS_CANWAIT;
 		pps->params.api_version = PPS_API_VERS;
 
+		/*
+		 * Clear unused fields of pps_kparams to avoid leaking
+		 * uninitialized data of the PPS_SETPARAMS caller via
+		 * PPS_GETPARAMS
+		 */
+		pps->params.assert_off_tu.flags = 0;
+		pps->params.clear_off_tu.flags = 0;
+
 		spin_unlock_irq(&pps->lock);
 
 		break;

drivers/rapidio/devices/rio_mport_cdev.c

@@ -1686,6 +1686,7 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv,
 
 	if (copy_from_user(&dev_info, arg, sizeof(dev_info)))
 		return -EFAULT;
+	dev_info.name[sizeof(dev_info.name) - 1] = '\0';
 
 	rmcd_debug(RDEV, "name:%s ct:0x%x did:0x%x hc:0x%x", dev_info.name,
 		   dev_info.comptag, dev_info.destid, dev_info.hopcount);
@@ -1817,6 +1818,7 @@ static int rio_mport_del_riodev(struct mport_cdev_priv *priv, void __user *arg)
 
 	if (copy_from_user(&dev_info, arg, sizeof(dev_info)))
 		return -EFAULT;
+	dev_info.name[sizeof(dev_info.name) - 1] = '\0';
 
 	mport = priv->md->mport;
 

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -19,6 +19,7 @@
 #include <linux/vmalloc.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
+#include <linux/mm.h>
 
 #include <asm/iommu.h>
 #include <asm/tce.h>
@@ -31,51 +32,6 @@
 static void tce_iommu_detach_group(void *iommu_data,
 		struct iommu_group *iommu_group);
 
-static long try_increment_locked_vm(struct mm_struct *mm, long npages)
-{
-	long ret = 0, locked, lock_limit;
-
-	if (WARN_ON_ONCE(!mm))
-		return -EPERM;
-
-	if (!npages)
-		return 0;
-
-	down_write(&mm->mmap_sem);
-	locked = mm->locked_vm + npages;
-	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-	if (locked > lock_limit && !capable(CAP_IPC_LOCK))
-		ret = -ENOMEM;
-	else
-		mm->locked_vm += npages;
-
-	pr_debug("[%d] RLIMIT_MEMLOCK +%ld %ld/%ld%s\n", current->pid,
-			npages << PAGE_SHIFT,
-			mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK),
-			ret ? " - exceeded" : "");
-
-	up_write(&mm->mmap_sem);
-
-	return ret;
-}
-
-static void decrement_locked_vm(struct mm_struct *mm, long npages)
-{
-	if (!mm || !npages)
-		return;
-
-	down_write(&mm->mmap_sem);
-	if (WARN_ON_ONCE(npages > mm->locked_vm))
-		npages = mm->locked_vm;
-	mm->locked_vm -= npages;
-	pr_debug("[%d] RLIMIT_MEMLOCK -%ld %ld/%ld\n", current->pid,
-			npages << PAGE_SHIFT,
-			mm->locked_vm << PAGE_SHIFT,
-			rlimit(RLIMIT_MEMLOCK));
-	up_write(&mm->mmap_sem);
-}
-
 /*
  * VFIO IOMMU fd for SPAPR_TCE IOMMU implementation
  *
@@ -333,7 +289,7 @@ static int tce_iommu_enable(struct tce_container *container)
 		return ret;
 
 	locked = table_group->tce32_size >> PAGE_SHIFT;
-	ret = try_increment_locked_vm(container->mm, locked);
+	ret = account_locked_vm(container->mm, locked, true);
 	if (ret)
 		return ret;
 
@@ -352,7 +308,7 @@ static void tce_iommu_disable(struct tce_container *container)
 	container->enabled = false;
 
 	BUG_ON(!container->mm);
-	decrement_locked_vm(container->mm, container->locked_pages);
+	account_locked_vm(container->mm, container->locked_pages, false);
 }
 
 static void *tce_iommu_open(unsigned long arg)
@@ -656,7 +612,7 @@ static long tce_iommu_create_table(struct tce_container *container,
 	if (!table_size)
 		return -EINVAL;
 
-	ret = try_increment_locked_vm(container->mm, table_size >> PAGE_SHIFT);
+	ret = account_locked_vm(container->mm, table_size >> PAGE_SHIFT, true);
 	if (ret)
 		return ret;
 
@@ -675,7 +631,7 @@ static void tce_iommu_free_table(struct tce_container *container,
 	unsigned long pages = tbl->it_allocated_size >> PAGE_SHIFT;
 
 	iommu_tce_table_put(tbl);
-	decrement_locked_vm(container->mm, pages);
+	account_locked_vm(container->mm, pages, false);
 }
 
 static long tce_iommu_create_window(struct tce_container *container,

drivers/vfio/vfio_iommu_type1.c

@@ -272,21 +272,8 @@ static int vfio_lock_acct(struct vfio_dma *dma, long npage, bool async)
 
 	ret = down_write_killable(&mm->mmap_sem);
 	if (!ret) {
-		if (npage > 0) {
+		ret = __account_locked_vm(mm, abs(npage), npage > 0, dma->task,
-			if (!dma->lock_cap) {
+					  dma->lock_cap);
-				unsigned long limit;
-
-				limit = task_rlimit(dma->task,
-						RLIMIT_MEMLOCK) >> PAGE_SHIFT;
-
-				if (mm->locked_vm + npage > limit)
-					ret = -ENOMEM;
-			}
-		}
-
-		if (!ret)
-			mm->locked_vm += npage;
-
 		up_write(&mm->mmap_sem);
 	}
 

fs/aio.c

@@ -2094,7 +2094,6 @@ SYSCALL_DEFINE6(io_pgetevents,
 		const struct __aio_sigset __user *, usig)
 {
 	struct __aio_sigset	ksig = { NULL, };
-	sigset_t		ksigmask, sigsaved;
 	struct timespec64	ts;
 	bool interrupted;
 	int ret;
@@ -2105,14 +2104,14 @@ SYSCALL_DEFINE6(io_pgetevents,
 	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
 		return -EFAULT;
 
-	ret = set_user_sigmask(ksig.sigmask, &ksigmask, &sigsaved, ksig.sigsetsize);
+	ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
 
 	interrupted = signal_pending(current);
-	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	restore_saved_sigmask_unless(interrupted);
 	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 
@@ -2130,7 +2129,6 @@ SYSCALL_DEFINE6(io_pgetevents_time32,
 		const struct __aio_sigset __user *, usig)
 {
 	struct __aio_sigset	ksig = { NULL, };
-	sigset_t		ksigmask, sigsaved;
 	struct timespec64	ts;
 	bool interrupted;
 	int ret;
@@ -2142,14 +2140,14 @@ SYSCALL_DEFINE6(io_pgetevents_time32,
 		return -EFAULT;
 
 
-	ret = set_user_sigmask(ksig.sigmask, &ksigmask, &sigsaved, ksig.sigsetsize);
+	ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
 
 	interrupted = signal_pending(current);
-	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	restore_saved_sigmask_unless(interrupted);
 	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 
@@ -2198,7 +2196,6 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
 		const struct __compat_aio_sigset __user *, usig)
 {
 	struct __compat_aio_sigset ksig = { NULL, };
-	sigset_t ksigmask, sigsaved;
 	struct timespec64 t;
 	bool interrupted;
 	int ret;
@@ -2209,14 +2206,14 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
 	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
 		return -EFAULT;
 
-	ret = set_compat_user_sigmask(ksig.sigmask, &ksigmask, &sigsaved, ksig.sigsetsize);
+	ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
 
 	interrupted = signal_pending(current);
-	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	restore_saved_sigmask_unless(interrupted);
 	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 
@@ -2234,7 +2231,6 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64,
 		const struct __compat_aio_sigset __user *, usig)
 {
 	struct __compat_aio_sigset ksig = { NULL, };
-	sigset_t ksigmask, sigsaved;
 	struct timespec64 t;
 	bool interrupted;
 	int ret;
@@ -2245,14 +2241,14 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64,
 	if (usig && copy_from_user(&ksig, usig, sizeof(ksig)))
 		return -EFAULT;
 
-	ret = set_compat_user_sigmask(ksig.sigmask, &ksigmask, &sigsaved, ksig.sigsetsize);
+	ret = set_compat_user_sigmask(ksig.sigmask, ksig.sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
 
 	interrupted = signal_pending(current);
-	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	restore_saved_sigmask_unless(interrupted);
 	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 

fs/binfmt_elf.c

@@ -1127,7 +1127,6 @@ out_free_interp:
 			  load_addr, interp_load_addr);
 	if (retval < 0)
 		goto out;
-	/* N.B. passed_fileno might not be initialized? */
 	current->mm->end_code = end_code;
 	current->mm->start_code = start_code;
 	current->mm->start_data = start_data;

fs/binfmt_flat.c

@@ -431,7 +431,6 @@ static int load_flat_file(struct linux_binprm *bprm,
 	unsigned long len, memp, memp_size, extra, rlim;
 	__be32 __user *reloc;
 	u32 __user *rp;
-	struct inode *inode;
 	int i, rev, relocs;
 	loff_t fpos;
 	unsigned long start_code, end_code;
@@ -439,7 +438,6 @@ static int load_flat_file(struct linux_binprm *bprm,
 	int ret;
 
 	hdr = ((struct flat_hdr *) bprm->buf);		/* exec-header */
-	inode = file_inode(bprm->file);
 
 	text_len  = ntohl(hdr->data_start);
 	data_len  = ntohl(hdr->data_end) - ntohl(hdr->data_start);

fs/coda/Makefile

@@ -6,7 +6,8 @@
 obj-$(CONFIG_CODA_FS) += coda.o
 
 coda-objs := psdev.o cache.o cnode.o inode.o dir.o file.o upcall.o \
-	     coda_linux.o symlink.o pioctl.o sysctl.o 
+	     coda_linux.o symlink.o pioctl.o
+coda-$(CONFIG_SYSCTL) += sysctl.o
 
 # If you want debugging output, please uncomment the following line.
 

fs/coda/cache.c

@@ -21,7 +21,7 @@
 #include <linux/spinlock.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
+#include "coda_psdev.h"
 #include "coda_linux.h"
 #include "coda_cache.h"
 

fs/coda/cnode.c

@@ -8,8 +8,8 @@
 #include <linux/time.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
 #include <linux/pagemap.h>
+#include "coda_psdev.h"
 #include "coda_linux.h"
 
 static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2)
@@ -137,11 +137,6 @@ struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb)
 	struct inode *inode;
 	unsigned long hash = coda_f2i(fid);
 
-	if ( !sb ) {
-		pr_warn("%s: no sb!\n", __func__);
-		return NULL;
-	}
-
 	inode = ilookup5(sb, hash, coda_test_inode, fid);
 	if ( !inode )
 		return NULL;
@@ -153,6 +148,16 @@ struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb)
 	return inode;
 }
 
+struct coda_file_info *coda_ftoc(struct file *file)
+{
+	struct coda_file_info *cfi = file->private_data;
+
+	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
+
+	return cfi;
+
+}
+
 /* the CONTROL inode is made without asking attributes from Venus */
 struct inode *coda_cnode_makectl(struct super_block *sb)
 {

fs/coda/coda_fs_i.h

@@ -40,10 +40,9 @@ struct coda_file_info {
 	int		   cfi_magic;	  /* magic number */
 	struct file	  *cfi_container; /* container file for this cnode */
 	unsigned int	   cfi_mapcount;  /* nr of times this file is mapped */
+	bool		   cfi_access_intent; /* is access intent supported */
 };
 
-#define CODA_FTOC(file) ((struct coda_file_info *)((file)->private_data))
-
 /* flags */
 #define C_VATTR       0x1   /* Validity of vattr in inode */
 #define C_FLUSH       0x2   /* used after a flush */
@@ -54,6 +53,7 @@ struct inode *coda_cnode_make(struct CodaFid *, struct super_block *);
 struct inode *coda_iget(struct super_block *sb, struct CodaFid *fid, struct coda_vattr *attr);
 struct inode *coda_cnode_makectl(struct super_block *sb);
 struct inode *coda_fid_to_inode(struct CodaFid *fid, struct super_block *sb);
+struct coda_file_info *coda_ftoc(struct file *file);
 void coda_replace_fid(struct inode *, struct CodaFid *, struct CodaFid *);
 
 #endif

fs/coda/coda_int.h

@@ -13,9 +13,19 @@ extern int coda_fake_statfs;
 void coda_destroy_inodecache(void);
 int __init coda_init_inodecache(void);
 int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync);
+
+#ifdef CONFIG_SYSCTL
 void coda_sysctl_init(void);
 void coda_sysctl_clean(void);
+#else
+static inline void coda_sysctl_init(void)
+{
+}
 
+static inline void coda_sysctl_clean(void)
+{
+}
+#endif
 #endif  /*  _CODA_INT_  */
 
 

fs/coda/coda_linux.c

@@ -18,7 +18,7 @@
 #include <linux/string.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
+#include "coda_psdev.h"
 #include "coda_linux.h"
 
 /* initialize the debugging variables */
@@ -66,6 +66,25 @@ unsigned short coda_flags_to_cflags(unsigned short flags)
 	return coda_flags;
 }
 
+static struct timespec64 coda_to_timespec64(struct coda_timespec ts)
+{
+	struct timespec64 ts64 = {
+		.tv_sec = ts.tv_sec,
+		.tv_nsec = ts.tv_nsec,
+	};
+
+	return ts64;
+}
+
+static struct coda_timespec timespec64_to_coda(struct timespec64 ts64)
+{
+	struct coda_timespec ts = {
+		.tv_sec = ts64.tv_sec,
+		.tv_nsec = ts64.tv_nsec,
+	};
+
+	return ts;
+}
 
 /* utility functions below */
 void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr)
@@ -105,11 +124,11 @@ void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr)
 	if (attr->va_size != -1)
 		inode->i_blocks = (attr->va_size + 511) >> 9;
 	if (attr->va_atime.tv_sec != -1) 
-		inode->i_atime = timespec_to_timespec64(attr->va_atime);
+		inode->i_atime = coda_to_timespec64(attr->va_atime);
 	if (attr->va_mtime.tv_sec != -1)
-		inode->i_mtime = timespec_to_timespec64(attr->va_mtime);
+		inode->i_mtime = coda_to_timespec64(attr->va_mtime);
         if (attr->va_ctime.tv_sec != -1)
-		inode->i_ctime = timespec_to_timespec64(attr->va_ctime);
+		inode->i_ctime = coda_to_timespec64(attr->va_ctime);
 }
 
 
@@ -130,12 +149,12 @@ void coda_iattr_to_vattr(struct iattr *iattr, struct coda_vattr *vattr)
         vattr->va_uid = (vuid_t) -1; 
         vattr->va_gid = (vgid_t) -1;
         vattr->va_size = (off_t) -1;
-	vattr->va_atime.tv_sec = (time_t) -1;
+	vattr->va_atime.tv_sec = (int64_t) -1;
-	vattr->va_atime.tv_nsec =  (time_t) -1;
+	vattr->va_atime.tv_nsec = (long) -1;
-        vattr->va_mtime.tv_sec = (time_t) -1;
+	vattr->va_mtime.tv_sec = (int64_t) -1;
-        vattr->va_mtime.tv_nsec = (time_t) -1;
+	vattr->va_mtime.tv_nsec = (long) -1;
-	vattr->va_ctime.tv_sec = (time_t) -1;
+	vattr->va_ctime.tv_sec = (int64_t) -1;
-	vattr->va_ctime.tv_nsec = (time_t) -1;
+	vattr->va_ctime.tv_nsec = (long) -1;
         vattr->va_type = C_VNON;
 	vattr->va_fileid = -1;
 	vattr->va_gen = -1;
@@ -175,13 +194,13 @@ void coda_iattr_to_vattr(struct iattr *iattr, struct coda_vattr *vattr)
                 vattr->va_size = iattr->ia_size;
 	}
         if ( valid & ATTR_ATIME ) {
-		vattr->va_atime = timespec64_to_timespec(iattr->ia_atime);
+		vattr->va_atime = timespec64_to_coda(iattr->ia_atime);
 	}
         if ( valid & ATTR_MTIME ) {
-		vattr->va_mtime = timespec64_to_timespec(iattr->ia_mtime);
+		vattr->va_mtime = timespec64_to_coda(iattr->ia_mtime);
 	}
         if ( valid & ATTR_CTIME ) {
-		vattr->va_ctime = timespec64_to_timespec(iattr->ia_ctime);
+		vattr->va_ctime = timespec64_to_coda(iattr->ia_ctime);
 	}
 }
 

fs/coda/coda_linux.h

@@ -59,22 +59,6 @@ void coda_vattr_to_iattr(struct inode *, struct coda_vattr *);
 void coda_iattr_to_vattr(struct iattr *, struct coda_vattr *);
 unsigned short coda_flags_to_cflags(unsigned short);
 
-/* sysctl.h */
-void coda_sysctl_init(void);
-void coda_sysctl_clean(void);
-
-#define CODA_ALLOC(ptr, cast, size) do { \
-    if (size < PAGE_SIZE) \
-        ptr = kzalloc((unsigned long) size, GFP_KERNEL); \
-    else \
-        ptr = (cast)vzalloc((unsigned long) size); \
-    if (!ptr) \
-	pr_warn("kernel malloc returns 0 at %s:%d\n", __FILE__, __LINE__); \
-} while (0)
-
-
-#define CODA_FREE(ptr, size) kvfree((ptr))
-
 /* inode to cnode access functions */
 
 static inline struct coda_inode_info *ITOC(struct inode *inode)

fs/coda/coda_psdev.h

@@ -3,11 +3,31 @@
 #define __CODA_PSDEV_H
 
 #include <linux/backing-dev.h>
+#include <linux/magic.h>
 #include <linux/mutex.h>
-#include <uapi/linux/coda_psdev.h>
+
+#define CODA_PSDEV_MAJOR 67
+#define MAX_CODADEVS  5	   /* how many do we allow */
 
 struct kstatfs;
 
+/* messages between coda filesystem in kernel and Venus */
+struct upc_req {
+	struct list_head	uc_chain;
+	caddr_t			uc_data;
+	u_short			uc_flags;
+	u_short			uc_inSize;  /* Size is at most 5000 bytes */
+	u_short			uc_outSize;
+	u_short			uc_opcode;  /* copied from data to save lookup */
+	int			uc_unique;
+	wait_queue_head_t	uc_sleep;   /* process' wait queue */
+};
+
+#define CODA_REQ_ASYNC  0x1
+#define CODA_REQ_READ   0x2
+#define CODA_REQ_WRITE  0x4
+#define CODA_REQ_ABORT  0x8
+
 /* communication pending/processing queues */
 struct venus_comm {
 	u_long		    vc_seq;
@@ -19,7 +39,6 @@ struct venus_comm {
 	struct mutex	    vc_mutex;
 };
 
-
 static inline struct venus_comm *coda_vcp(struct super_block *sb)
 {
 	return (struct venus_comm *)((sb)->s_fs_info);
@@ -30,39 +49,43 @@ int venus_rootfid(struct super_block *sb, struct CodaFid *fidp);
 int venus_getattr(struct super_block *sb, struct CodaFid *fid,
 		  struct coda_vattr *attr);
 int venus_setattr(struct super_block *, struct CodaFid *, struct coda_vattr *);
-int venus_lookup(struct super_block *sb, struct CodaFid *fid, 
+int venus_lookup(struct super_block *sb, struct CodaFid *fid,
-		 const char *name, int length, int *type, 
+		 const char *name, int length, int *type,
 		 struct CodaFid *resfid);
 int venus_close(struct super_block *sb, struct CodaFid *fid, int flags,
 		kuid_t uid);
 int venus_open(struct super_block *sb, struct CodaFid *fid, int flags,
 	       struct file **f);
-int venus_mkdir(struct super_block *sb, struct CodaFid *dirfid, 
+int venus_mkdir(struct super_block *sb, struct CodaFid *dirfid,
-		const char *name, int length, 
+		const char *name, int length,
 		struct CodaFid *newfid, struct coda_vattr *attrs);
-int venus_create(struct super_block *sb, struct CodaFid *dirfid, 
+int venus_create(struct super_block *sb, struct CodaFid *dirfid,
 		 const char *name, int length, int excl, int mode,
-		 struct CodaFid *newfid, struct coda_vattr *attrs) ;
+		 struct CodaFid *newfid, struct coda_vattr *attrs);
-int venus_rmdir(struct super_block *sb, struct CodaFid *dirfid, 
+int venus_rmdir(struct super_block *sb, struct CodaFid *dirfid,
 		const char *name, int length);
-int venus_remove(struct super_block *sb, struct CodaFid *dirfid, 
+int venus_remove(struct super_block *sb, struct CodaFid *dirfid,
 		 const char *name, int length);
-int venus_readlink(struct super_block *sb, struct CodaFid *fid, 
+int venus_readlink(struct super_block *sb, struct CodaFid *fid,
 		   char *buffer, int *length);
-int venus_rename(struct super_block *, struct CodaFid *new_fid, 
+int venus_rename(struct super_block *sb, struct CodaFid *new_fid,
-		 struct CodaFid *old_fid, size_t old_length, 
+		 struct CodaFid *old_fid, size_t old_length,
-		 size_t new_length, const char *old_name, 
+		 size_t new_length, const char *old_name,
 		 const char *new_name);
-int venus_link(struct super_block *sb, struct CodaFid *fid, 
+int venus_link(struct super_block *sb, struct CodaFid *fid,
 		  struct CodaFid *dirfid, const char *name, int len );
 int venus_symlink(struct super_block *sb, struct CodaFid *fid,
 		  const char *name, int len, const char *symname, int symlen);
 int venus_access(struct super_block *sb, struct CodaFid *fid, int mask);
 int venus_pioctl(struct super_block *sb, struct CodaFid *fid,
 		 unsigned int cmd, struct PioctlData *data);
-int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out);
+int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out,
+		  size_t nbytes);
 int venus_fsync(struct super_block *sb, struct CodaFid *fid);
 int venus_statfs(struct dentry *dentry, struct kstatfs *sfs);
+int venus_access_intent(struct super_block *sb, struct CodaFid *fid,
+			bool *access_intent_supported,
+			size_t count, loff_t ppos, int type);
 
 /*
  * Statistics

fs/coda/dir.c

@@ -23,7 +23,7 @@
 #include <linux/uaccess.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
+#include "coda_psdev.h"
 #include "coda_linux.h"
 #include "coda_cache.h"
 
@@ -47,8 +47,8 @@ static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsig
 	int type = 0;
 
 	if (length > CODA_MAXNAMLEN) {
-		pr_err("name too long: lookup, %s (%*s)\n",
+		pr_err("name too long: lookup, %s %zu\n",
-		       coda_i2s(dir), (int)length, name);
+		       coda_i2s(dir), length);
 		return ERR_PTR(-ENAMETOOLONG);
 	}
 
@@ -356,8 +356,7 @@ static int coda_venus_readdir(struct file *coda_file, struct dir_context *ctx)
 	ino_t ino;
 	int ret;
 
-	cfi = CODA_FTOC(coda_file);
+	cfi = coda_ftoc(coda_file);
-	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
 	cii = ITOC(file_inode(coda_file));
@@ -426,8 +425,7 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx)
 	struct file *host_file;
 	int ret;
 
-	cfi = CODA_FTOC(coda_file);
+	cfi = coda_ftoc(coda_file);
-	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
 	if (host_file->f_op->iterate || host_file->f_op->iterate_shared) {

fs/coda/file.c

@@ -20,22 +20,43 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/uio.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
+#include "coda_psdev.h"
-
 #include "coda_linux.h"
 #include "coda_int.h"
 
+struct coda_vm_ops {
+	atomic_t refcnt;
+	struct file *coda_file;
+	const struct vm_operations_struct *host_vm_ops;
+	struct vm_operations_struct vm_ops;
+};
+
 static ssize_t
 coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *coda_file = iocb->ki_filp;
-	struct coda_file_info *cfi = CODA_FTOC(coda_file);
+	struct inode *coda_inode = file_inode(coda_file);
+	struct coda_file_info *cfi = coda_ftoc(coda_file);
+	loff_t ki_pos = iocb->ki_pos;
+	size_t count = iov_iter_count(to);
+	ssize_t ret;
 
-	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
+	ret = venus_access_intent(coda_inode->i_sb, coda_i2f(coda_inode),
+				  &cfi->cfi_access_intent,
+				  count, ki_pos, CODA_ACCESS_TYPE_READ);
+	if (ret)
+		goto finish_read;
 
-	return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos, 0);
+	ret = vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos, 0);
+
+finish_read:
+	venus_access_intent(coda_inode->i_sb, coda_i2f(coda_inode),
+			    &cfi->cfi_access_intent,
+			    count, ki_pos, CODA_ACCESS_TYPE_READ_FINISH);
+	return ret;
 }
 
 static ssize_t
@@ -43,13 +64,18 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *coda_file = iocb->ki_filp;
 	struct inode *coda_inode = file_inode(coda_file);
-	struct coda_file_info *cfi = CODA_FTOC(coda_file);
+	struct coda_file_info *cfi = coda_ftoc(coda_file);
-	struct file *host_file;
+	struct file *host_file = cfi->cfi_container;
+	loff_t ki_pos = iocb->ki_pos;
+	size_t count = iov_iter_count(to);
 	ssize_t ret;
 
-	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
+	ret = venus_access_intent(coda_inode->i_sb, coda_i2f(coda_inode),
+				  &cfi->cfi_access_intent,
+				  count, ki_pos, CODA_ACCESS_TYPE_WRITE);
+	if (ret)
+		goto finish_write;
 
-	host_file = cfi->cfi_container;
 	file_start_write(host_file);
 	inode_lock(coda_inode);
 	ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos, 0);
@@ -58,26 +84,73 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
 	coda_inode->i_mtime = coda_inode->i_ctime = current_time(coda_inode);
 	inode_unlock(coda_inode);
 	file_end_write(host_file);
+
+finish_write:
+	venus_access_intent(coda_inode->i_sb, coda_i2f(coda_inode),
+			    &cfi->cfi_access_intent,
+			    count, ki_pos, CODA_ACCESS_TYPE_WRITE_FINISH);
 	return ret;
 }
 
+static void
+coda_vm_open(struct vm_area_struct *vma)
+{
+	struct coda_vm_ops *cvm_ops =
+		container_of(vma->vm_ops, struct coda_vm_ops, vm_ops);
+
+	atomic_inc(&cvm_ops->refcnt);
+
+	if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->open)
+		cvm_ops->host_vm_ops->open(vma);
+}
+
+static void
+coda_vm_close(struct vm_area_struct *vma)
+{
+	struct coda_vm_ops *cvm_ops =
+		container_of(vma->vm_ops, struct coda_vm_ops, vm_ops);
+
+	if (cvm_ops->host_vm_ops && cvm_ops->host_vm_ops->close)
+		cvm_ops->host_vm_ops->close(vma);
+
+	if (atomic_dec_and_test(&cvm_ops->refcnt)) {
+		vma->vm_ops = cvm_ops->host_vm_ops;
+		fput(cvm_ops->coda_file);
+		kfree(cvm_ops);
+	}
+}
+
 static int
 coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 {
-	struct coda_file_info *cfi;
+	struct inode *coda_inode = file_inode(coda_file);
+	struct coda_file_info *cfi = coda_ftoc(coda_file);
+	struct file *host_file = cfi->cfi_container;
+	struct inode *host_inode = file_inode(host_file);
 	struct coda_inode_info *cii;
-	struct file *host_file;
+	struct coda_vm_ops *cvm_ops;
-	struct inode *coda_inode, *host_inode;
+	loff_t ppos;
-
+	size_t count;
-	cfi = CODA_FTOC(coda_file);
+	int ret;
-	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
-	host_file = cfi->cfi_container;
 
 	if (!host_file->f_op->mmap)
 		return -ENODEV;
 
-	coda_inode = file_inode(coda_file);
+	if (WARN_ON(coda_file != vma->vm_file))
-	host_inode = file_inode(host_file);
+		return -EIO;
+
+	count = vma->vm_end - vma->vm_start;
+	ppos = vma->vm_pgoff * PAGE_SIZE;
+
+	ret = venus_access_intent(coda_inode->i_sb, coda_i2f(coda_inode),
+				  &cfi->cfi_access_intent,
+				  count, ppos, CODA_ACCESS_TYPE_MMAP);
+	if (ret)
+		return ret;
+
+	cvm_ops = kmalloc(sizeof(struct coda_vm_ops), GFP_KERNEL);
+	if (!cvm_ops)
+		return -ENOMEM;
 
 	cii = ITOC(coda_inode);
 	spin_lock(&cii->c_lock);
@@ -89,6 +162,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	 * the container file on us! */
 	else if (coda_inode->i_mapping != host_inode->i_mapping) {
 		spin_unlock(&cii->c_lock);
+		kfree(cvm_ops);
 		return -EBUSY;
 	}
 
@@ -97,7 +171,29 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	cfi->cfi_mapcount++;
 	spin_unlock(&cii->c_lock);
 
-	return call_mmap(host_file, vma);
+	vma->vm_file = get_file(host_file);
+	ret = call_mmap(vma->vm_file, vma);
+
+	if (ret) {
+		/* if call_mmap fails, our caller will put coda_file so we
+		 * should drop the reference to the host_file that we got.
+		 */
+		fput(host_file);
+		kfree(cvm_ops);
+	} else {
+		/* here we add redirects for the open/close vm_operations */
+		cvm_ops->host_vm_ops = vma->vm_ops;
+		if (vma->vm_ops)
+			cvm_ops->vm_ops = *vma->vm_ops;
+
+		cvm_ops->vm_ops.open = coda_vm_open;
+		cvm_ops->vm_ops.close = coda_vm_close;
+		cvm_ops->coda_file = coda_file;
+		atomic_set(&cvm_ops->refcnt, 1);
+
+		vma->vm_ops = &cvm_ops->vm_ops;
+	}
+	return ret;
 }
 
 int coda_open(struct inode *coda_inode, struct file *coda_file)
@@ -127,6 +223,8 @@ int coda_open(struct inode *coda_inode, struct file *coda_file)
 	cfi->cfi_magic = CODA_MAGIC;
 	cfi->cfi_mapcount = 0;
 	cfi->cfi_container = host_file;
+	/* assume access intents are supported unless we hear otherwise */
+	cfi->cfi_access_intent = true;
 
 	BUG_ON(coda_file->private_data != NULL);
 	coda_file->private_data = cfi;
@@ -142,8 +240,7 @@ int coda_release(struct inode *coda_inode, struct file *coda_file)
 	struct inode *host_inode;
 	int err;
 
-	cfi = CODA_FTOC(coda_file);
+	cfi = coda_ftoc(coda_file);
-	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 
 	err = venus_close(coda_inode->i_sb, coda_i2f(coda_inode),
 			  coda_flags, coda_file->f_cred->fsuid);
@@ -185,8 +282,7 @@ int coda_fsync(struct file *coda_file, loff_t start, loff_t end, int datasync)
 		return err;
 	inode_lock(coda_inode);
 
-	cfi = CODA_FTOC(coda_file);
+	cfi = coda_ftoc(coda_file);
-	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
 	err = vfs_fsync(host_file, datasync);
@@ -207,4 +303,3 @@ const struct file_operations coda_file_operations = {
 	.fsync		= coda_fsync,
 	.splice_read	= generic_file_splice_read,
 };
-

fs/coda/inode.c

@@ -27,7 +27,7 @@
 #include <linux/vmalloc.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
+#include "coda_psdev.h"
 #include "coda_linux.h"
 #include "coda_cache.h"
 
@@ -236,6 +236,7 @@ static void coda_put_super(struct super_block *sb)
 	vcp->vc_sb = NULL;
 	sb->s_fs_info = NULL;
 	mutex_unlock(&vcp->vc_mutex);
+	mutex_destroy(&vcp->vc_mutex);
 
 	pr_info("Bye bye.\n");
 }

fs/coda/pioctl.c

@@ -20,8 +20,7 @@
 #include <linux/uaccess.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
+#include "coda_psdev.h"
-
 #include "coda_linux.h"
 
 /* pioctl ops */

fs/coda/psdev.c

@@ -38,8 +38,7 @@
 #include <linux/uaccess.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
+#include "coda_psdev.h"
-
 #include "coda_linux.h"
 
 #include "coda_int.h"
@@ -100,8 +99,12 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf,
 	ssize_t retval = 0, count = 0;
 	int error;
 
+	/* make sure there is enough to copy out the (opcode, unique) values */
+	if (nbytes < (2 * sizeof(u_int32_t)))
+		return -EINVAL;
+
         /* Peek at the opcode, uniquefier */
-	if (copy_from_user(&hdr, buf, 2 * sizeof(u_long)))
+	if (copy_from_user(&hdr, buf, 2 * sizeof(u_int32_t)))
 	        return -EFAULT;
 
         if (DOWNCALL(hdr.opcode)) {
@@ -119,17 +122,21 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf,
 				hdr.opcode, hdr.unique);
 		        nbytes = size;
 		}
-		CODA_ALLOC(dcbuf, union outputArgs *, nbytes);
+		dcbuf = kvmalloc(nbytes, GFP_KERNEL);
+		if (!dcbuf) {
+			retval = -ENOMEM;
+			goto out;
+		}
 		if (copy_from_user(dcbuf, buf, nbytes)) {
-			CODA_FREE(dcbuf, nbytes);
+			kvfree(dcbuf);
 			retval = -EFAULT;
 			goto out;
 		}
 
 		/* what downcall errors does Venus handle ? */
-		error = coda_downcall(vcp, hdr.opcode, dcbuf);
+		error = coda_downcall(vcp, hdr.opcode, dcbuf, nbytes);
 
-		CODA_FREE(dcbuf, nbytes);
+		kvfree(dcbuf);
 		if (error) {
 			pr_warn("%s: coda_downcall error: %d\n",
 				__func__, error);
@@ -182,8 +189,11 @@ static ssize_t coda_psdev_write(struct file *file, const char __user *buf,
 	if (req->uc_opcode == CODA_OPEN_BY_FD) {
 		struct coda_open_by_fd_out *outp =
 			(struct coda_open_by_fd_out *)req->uc_data;
-		if (!outp->oh.result)
+		if (!outp->oh.result) {
 			outp->fh = fget(outp->fd);
+			if (!outp->fh)
+				return -EBADF;
+		}
 	}
 
         wake_up(&req->uc_sleep);
@@ -252,7 +262,7 @@ static ssize_t coda_psdev_read(struct file * file, char __user * buf,
 		goto out;
 	}
 
-	CODA_FREE(req->uc_data, sizeof(struct coda_in_hdr));
+	kvfree(req->uc_data);
 	kfree(req);
 out:
 	mutex_unlock(&vcp->vc_mutex);
@@ -314,7 +324,7 @@ static int coda_psdev_release(struct inode * inode, struct file * file)
 
 		/* Async requests need to be freed here */
 		if (req->uc_flags & CODA_REQ_ASYNC) {
-			CODA_FREE(req->uc_data, sizeof(struct coda_in_hdr));
+			kvfree(req->uc_data);
 			kfree(req);
 			continue;
 		}
@@ -347,13 +357,13 @@ static const struct file_operations coda_psdev_fops = {
 	.llseek		= noop_llseek,
 };
 
-static int init_coda_psdev(void)
+static int __init init_coda_psdev(void)
 {
 	int i, err = 0;
 	if (register_chrdev(CODA_PSDEV_MAJOR, "coda", &coda_psdev_fops)) {
 		pr_err("%s: unable to get major %d\n",
 		       __func__, CODA_PSDEV_MAJOR);
-              return -EIO;
+		return -EIO;
 	}
 	coda_psdev_class = class_create(THIS_MODULE, "coda");
 	if (IS_ERR(coda_psdev_class)) {
@@ -378,7 +388,7 @@ MODULE_AUTHOR("Jan Harkes, Peter J. Braam");
 MODULE_DESCRIPTION("Coda Distributed File System VFS interface");
 MODULE_ALIAS_CHARDEV_MAJOR(CODA_PSDEV_MAJOR);
 MODULE_LICENSE("GPL");
-MODULE_VERSION("6.6");
+MODULE_VERSION("7.0");
 
 static int __init init_coda(void)
 {

fs/coda/symlink.c

@@ -17,8 +17,7 @@
 #include <linux/pagemap.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
+#include "coda_psdev.h"
-
 #include "coda_linux.h"
 
 static int coda_symlink_filler(struct file *file, struct page *page)

fs/coda/sysctl.c

@@ -12,7 +12,6 @@
 
 #include "coda_int.h"
 
-#ifdef CONFIG_SYSCTL
 static struct ctl_table_header *fs_table_header;
 
 static struct ctl_table coda_table[] = {
@@ -62,13 +61,3 @@ void coda_sysctl_clean(void)
 		fs_table_header = NULL;
 	}
 }
-
-#else
-void coda_sysctl_init(void)
-{
-}
-
-void coda_sysctl_clean(void)
-{
-}
-#endif

fs/coda/upcall.c

@@ -33,7 +33,7 @@
 #include <linux/vfs.h>
 
 #include <linux/coda.h>
-#include <linux/coda_psdev.h>
+#include "coda_psdev.h"
 #include "coda_linux.h"
 #include "coda_cache.h"
 
@@ -46,7 +46,7 @@ static void *alloc_upcall(int opcode, int size)
 {
 	union inputArgs *inp;
 
-	CODA_ALLOC(inp, union inputArgs *, size);
+	inp = kvzalloc(size, GFP_KERNEL);
         if (!inp)
 		return ERR_PTR(-ENOMEM);
 
@@ -85,7 +85,7 @@ int venus_rootfid(struct super_block *sb, struct CodaFid *fidp)
 	if (!error)
 		*fidp = outp->coda_root.VFid;
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;
 }
 
@@ -104,7 +104,7 @@ int venus_getattr(struct super_block *sb, struct CodaFid *fid,
 	if (!error)
 		*attr = outp->coda_getattr.attr;
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
         return error;
 }
 
@@ -123,7 +123,7 @@ int venus_setattr(struct super_block *sb, struct CodaFid *fid,
 
 	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
-        CODA_FREE(inp, insize);
+	kvfree(inp);
         return error;
 }
 
@@ -153,7 +153,7 @@ int venus_lookup(struct super_block *sb, struct CodaFid *fid,
 		*type = outp->coda_lookup.vtype;
 	}
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;
 }
 
@@ -173,7 +173,7 @@ int venus_close(struct super_block *sb, struct CodaFid *fid, int flags,
 
 	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
         return error;
 }
 
@@ -194,7 +194,7 @@ int venus_open(struct super_block *sb, struct CodaFid *fid,
 	if (!error)
 		*fh = outp->coda_open_by_fd.fh;
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;
 }	
 
@@ -224,7 +224,7 @@ int venus_mkdir(struct super_block *sb, struct CodaFid *dirfid,
 		*newfid = outp->coda_mkdir.VFid;
 	}
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;        
 }
 
@@ -262,7 +262,7 @@ int venus_rename(struct super_block *sb, struct CodaFid *old_fid,
 
 	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;
 }
 
@@ -295,7 +295,7 @@ int venus_create(struct super_block *sb, struct CodaFid *dirfid,
 		*newfid = outp->coda_create.VFid;
 	}
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;        
 }
 
@@ -318,7 +318,7 @@ int venus_rmdir(struct super_block *sb, struct CodaFid *dirfid,
 
 	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;
 }
 
@@ -340,7 +340,7 @@ int venus_remove(struct super_block *sb, struct CodaFid *dirfid,
 
 	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;
 }
 
@@ -370,7 +370,7 @@ int venus_readlink(struct super_block *sb, struct CodaFid *fid,
 		*(buffer + retlen) = '\0';
 	}
 
-        CODA_FREE(inp, insize);
+	kvfree(inp);
         return error;
 }
 
@@ -398,7 +398,7 @@ int venus_link(struct super_block *sb, struct CodaFid *fid,
 
 	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
         return error;
 }
 
@@ -433,7 +433,7 @@ int venus_symlink(struct super_block *sb, struct CodaFid *fid,
 
 	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
         return error;
 }
 
@@ -449,7 +449,7 @@ int venus_fsync(struct super_block *sb, struct CodaFid *fid)
 	inp->coda_fsync.VFid = *fid;
 	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;
 }
 
@@ -467,7 +467,7 @@ int venus_access(struct super_block *sb, struct CodaFid *fid, int mask)
 
 	error = coda_upcall(coda_vcp(sb), insize, &outsize, inp);
 
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;
 }
 
@@ -543,7 +543,7 @@ int venus_pioctl(struct super_block *sb, struct CodaFid *fid,
 	}
 
  exit:
-	CODA_FREE(inp, insize);
+	kvfree(inp);
 	return error;
 }
 
@@ -553,7 +553,7 @@ int venus_statfs(struct dentry *dentry, struct kstatfs *sfs)
         union outputArgs *outp;
         int insize, outsize, error;
         
-	insize = max_t(unsigned int, INSIZE(statfs), OUTSIZE(statfs));
+	insize = SIZE(statfs);
 	UPARG(CODA_STATFS);
 
 	error = coda_upcall(coda_vcp(dentry->d_sb), insize, &outsize, inp);
@@ -565,10 +565,51 @@ int venus_statfs(struct dentry *dentry, struct kstatfs *sfs)
 		sfs->f_ffree  = outp->coda_statfs.stat.f_ffree;
 	}
 
-        CODA_FREE(inp, insize);
+	kvfree(inp);
         return error;
 }
 
+int venus_access_intent(struct super_block *sb, struct CodaFid *fid,
+			bool *access_intent_supported,
+			size_t count, loff_t ppos, int type)
+{
+	union inputArgs *inp;
+	union outputArgs *outp;
+	int insize, outsize, error;
+	bool finalizer =
+		type == CODA_ACCESS_TYPE_READ_FINISH ||
+		type == CODA_ACCESS_TYPE_WRITE_FINISH;
+
+	if (!*access_intent_supported && !finalizer)
+		return 0;
+
+	insize = SIZE(access_intent);
+	UPARG(CODA_ACCESS_INTENT);
+
+	inp->coda_access_intent.VFid = *fid;
+	inp->coda_access_intent.count = count;
+	inp->coda_access_intent.pos = ppos;
+	inp->coda_access_intent.type = type;
+
+	error = coda_upcall(coda_vcp(sb), insize,
+			    finalizer ? NULL : &outsize, inp);
+
+	/*
+	 * we have to free the request buffer for synchronous upcalls
+	 * or when asynchronous upcalls fail, but not when asynchronous
+	 * upcalls succeed
+	 */
+	if (!finalizer || error)
+		kvfree(inp);
+
+	/* Chunked access is not supported or an old Coda client */
+	if (error == -EOPNOTSUPP) {
+		*access_intent_supported = false;
+		error = 0;
+	}
+	return error;
+}
+
 /*
  * coda_upcall and coda_downcall routines.
  */
@@ -598,10 +639,12 @@ static void coda_unblock_signals(sigset_t *old)
  * has seen them,
  * - CODA_CLOSE or CODA_RELEASE upcall  (to avoid reference count problems)
  * - CODA_STORE				(to avoid data loss)
+ * - CODA_ACCESS_INTENT                 (to avoid reference count problems)
  */
 #define CODA_INTERRUPTIBLE(r) (!coda_hard && \
 			       (((r)->uc_opcode != CODA_CLOSE && \
 				 (r)->uc_opcode != CODA_STORE && \
+				 (r)->uc_opcode != CODA_ACCESS_INTENT && \
 				 (r)->uc_opcode != CODA_RELEASE) || \
 				(r)->uc_flags & CODA_REQ_READ))
 
@@ -687,21 +730,25 @@ static int coda_upcall(struct venus_comm *vcp,
 		goto exit;
 	}
 
-	req->uc_data = (void *)buffer;
+	buffer->ih.unique = ++vcp->vc_seq;
-	req->uc_flags = 0;
-	req->uc_inSize = inSize;
-	req->uc_outSize = *outSize ? *outSize : inSize;
-	req->uc_opcode = ((union inputArgs *)buffer)->ih.opcode;
-	req->uc_unique = ++vcp->vc_seq;
-	init_waitqueue_head(&req->uc_sleep);
 
-	/* Fill in the common input args. */
+	req->uc_data = (void *)buffer;
-	((union inputArgs *)buffer)->ih.unique = req->uc_unique;
+	req->uc_flags = outSize ? 0 : CODA_REQ_ASYNC;
+	req->uc_inSize = inSize;
+	req->uc_outSize = (outSize && *outSize) ? *outSize : inSize;
+	req->uc_opcode = buffer->ih.opcode;
+	req->uc_unique = buffer->ih.unique;
+	init_waitqueue_head(&req->uc_sleep);
 
 	/* Append msg to pending queue and poke Venus. */
 	list_add_tail(&req->uc_chain, &vcp->vc_pending);
-
 	wake_up_interruptible(&vcp->vc_waitq);
+
+	if (req->uc_flags & CODA_REQ_ASYNC) {
+		mutex_unlock(&vcp->vc_mutex);
+		return 0;
+	}
+
 	/* We can be interrupted while we wait for Venus to process
 	 * our request.  If the interrupt occurs before Venus has read
 	 * the request, we dequeue and return. If it occurs after the
@@ -743,20 +790,20 @@ static int coda_upcall(struct venus_comm *vcp,
 	sig_req = kmalloc(sizeof(struct upc_req), GFP_KERNEL);
 	if (!sig_req) goto exit;
 
-	CODA_ALLOC((sig_req->uc_data), char *, sizeof(struct coda_in_hdr));
+	sig_inputArgs = kvzalloc(sizeof(struct coda_in_hdr), GFP_KERNEL);
-	if (!sig_req->uc_data) {
+	if (!sig_inputArgs) {
 		kfree(sig_req);
 		goto exit;
 	}
 
 	error = -EINTR;
-	sig_inputArgs = (union inputArgs *)sig_req->uc_data;
 	sig_inputArgs->ih.opcode = CODA_SIGNAL;
 	sig_inputArgs->ih.unique = req->uc_unique;
 
 	sig_req->uc_flags = CODA_REQ_ASYNC;
 	sig_req->uc_opcode = sig_inputArgs->ih.opcode;
 	sig_req->uc_unique = sig_inputArgs->ih.unique;
+	sig_req->uc_data = (void *)sig_inputArgs;
 	sig_req->uc_inSize = sizeof(struct coda_in_hdr);
 	sig_req->uc_outSize = sizeof(struct coda_in_hdr);
 
@@ -804,12 +851,44 @@ exit:
  *
  * CODA_REPLACE -- replace one CodaFid with another throughout the name cache */
 
-int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out)
+int coda_downcall(struct venus_comm *vcp, int opcode, union outputArgs *out,
+		  size_t nbytes)
 {
 	struct inode *inode = NULL;
 	struct CodaFid *fid = NULL, *newfid;
 	struct super_block *sb;
 
+	/*
+	 * Make sure we have received enough data from the cache
+	 * manager to populate the necessary fields in the buffer
+	 */
+	switch (opcode) {
+	case CODA_PURGEUSER:
+		if (nbytes < sizeof(struct coda_purgeuser_out))
+			return -EINVAL;
+		break;
+
+	case CODA_ZAPDIR:
+		if (nbytes < sizeof(struct coda_zapdir_out))
+			return -EINVAL;
+		break;
+
+	case CODA_ZAPFILE:
+		if (nbytes < sizeof(struct coda_zapfile_out))
+			return -EINVAL;
+		break;
+
+	case CODA_PURGEFID:
+		if (nbytes < sizeof(struct coda_purgefid_out))
+			return -EINVAL;
+		break;
+
+	case CODA_REPLACE:
+		if (nbytes < sizeof(struct coda_replace_out))
+			return -EINVAL;
+		break;
+	}
+
 	/* Handle invalidation requests. */
 	mutex_lock(&vcp->vc_mutex);
 	sb = vcp->vc_sb;
@@ -879,4 +958,3 @@ unlock_out:
 	iput(inode);
 	return 0;
 }
-

fs/eventpoll.c

@@ -2313,19 +2313,17 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events,
 		size_t, sigsetsize)
 {
 	int error;
-	sigset_t ksigmask, sigsaved;
 
 	/*
 	 * If the caller wants a certain signal mask to be set during the wait,
 	 * we apply it here.
 	 */
-	error = set_user_sigmask(sigmask, &ksigmask, &sigsaved, sigsetsize);
+	error = set_user_sigmask(sigmask, sigsetsize);
 	if (error)
 		return error;
 
 	error = do_epoll_wait(epfd, events, maxevents, timeout);
-
+	restore_saved_sigmask_unless(error == -EINTR);
-	restore_user_sigmask(sigmask, &sigsaved, error == -EINTR);
 
 	return error;
 }
@@ -2338,19 +2336,17 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd,
 			compat_size_t, sigsetsize)
 {
 	long err;
-	sigset_t ksigmask, sigsaved;
 
 	/*
 	 * If the caller wants a certain signal mask to be set during the wait,
 	 * we apply it here.
 	 */
-	err = set_compat_user_sigmask(sigmask, &ksigmask, &sigsaved, sigsetsize);
+	err = set_compat_user_sigmask(sigmask, sigsetsize);
 	if (err)
 		return err;
 
 	err = do_epoll_wait(epfd, events, maxevents, timeout);
-
+	restore_saved_sigmask_unless(err == -EINTR);
-	restore_user_sigmask(sigmask, &sigsaved, err == -EINTR);
 
 	return err;
 }

fs/hfsplus/xattr.c

@@ -407,7 +407,7 @@ static int copy_name(char *buffer, const char *xattr_name, int name_len)
 	int offset = 0;
 
 	if (!is_known_namespace(xattr_name)) {
-		strncpy(buffer, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN);
+		memcpy(buffer, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN);
 		offset += XATTR_MAC_OSX_PREFIX_LEN;
 		len += XATTR_MAC_OSX_PREFIX_LEN;
 	}

fs/io_uring.c

@@ -2400,7 +2400,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 			  const sigset_t __user *sig, size_t sigsz)
 {
 	struct io_cq_ring *ring = ctx->cq_ring;
-	sigset_t ksigmask, sigsaved;
 	int ret;
 
 	if (io_cqring_events(ring) >= min_events)
@@ -2410,21 +2409,17 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 #ifdef CONFIG_COMPAT
 		if (in_compat_syscall())
 			ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig,
-						      &ksigmask, &sigsaved, sigsz);
+						      sigsz);
 		else
 #endif
-			ret = set_user_sigmask(sig, &ksigmask,
+			ret = set_user_sigmask(sig, sigsz);
-					       &sigsaved, sigsz);
 
 		if (ret)
 			return ret;
 	}
 
 	ret = wait_event_interruptible(ctx->wait, io_cqring_events(ring) >= min_events);
-
+	restore_saved_sigmask_unless(ret == -ERESTARTSYS);
-	if (sig)
-		restore_user_sigmask(sig, &sigsaved, ret == -ERESTARTSYS);
-
 	if (ret == -ERESTARTSYS)
 		ret = -EINTR;
 

fs/proc/Kconfig

@@ -58,7 +58,8 @@ config PROC_VMCORE_DEVICE_DUMP
 	  snapshot.
 
 	  If you say Y here, the collected device dumps will be added
-	  as ELF notes to /proc/vmcore.
+	  as ELF notes to /proc/vmcore. You can still disable device
+	  dump using the kernel command line option 'novmcoredd'.
 
 config PROC_SYSCTL
 	bool "Sysctl support (/proc/sys)" if EXPERT

fs/proc/inode.c

@@ -200,7 +200,8 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	loff_t rv = -EINVAL;
 	if (use_pde(pde)) {
-		loff_t (*llseek)(struct file *, loff_t, int);
+		typeof_member(struct file_operations, llseek) llseek;
+
 		llseek = pde->proc_fops->llseek;
 		if (!llseek)
 			llseek = default_llseek;
@@ -212,10 +213,11 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
 
 static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
-	ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	ssize_t rv = -EIO;
 	if (use_pde(pde)) {
+		typeof_member(struct file_operations, read) read;
+
 		read = pde->proc_fops->read;
 		if (read)
 			rv = read(file, buf, count, ppos);
@@ -226,10 +228,11 @@ static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count,
 
 static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 {
-	ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	ssize_t rv = -EIO;
 	if (use_pde(pde)) {
+		typeof_member(struct file_operations, write) write;
+
 		write = pde->proc_fops->write;
 		if (write)
 			rv = write(file, buf, count, ppos);
@@ -242,8 +245,9 @@ static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts)
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	__poll_t rv = DEFAULT_POLLMASK;
-	__poll_t (*poll)(struct file *, struct poll_table_struct *);
 	if (use_pde(pde)) {
+		typeof_member(struct file_operations, poll) poll;
+
 		poll = pde->proc_fops->poll;
 		if (poll)
 			rv = poll(file, pts);
@@ -256,8 +260,9 @@ static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigne
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	long rv = -ENOTTY;
-	long (*ioctl)(struct file *, unsigned int, unsigned long);
 	if (use_pde(pde)) {
+		typeof_member(struct file_operations, unlocked_ioctl) ioctl;
+
 		ioctl = pde->proc_fops->unlocked_ioctl;
 		if (ioctl)
 			rv = ioctl(file, cmd, arg);
@@ -271,8 +276,9 @@ static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	long rv = -ENOTTY;
-	long (*compat_ioctl)(struct file *, unsigned int, unsigned long);
 	if (use_pde(pde)) {
+		typeof_member(struct file_operations, compat_ioctl) compat_ioctl;
+
 		compat_ioctl = pde->proc_fops->compat_ioctl;
 		if (compat_ioctl)
 			rv = compat_ioctl(file, cmd, arg);
@@ -286,8 +292,9 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	int rv = -EIO;
-	int (*mmap)(struct file *, struct vm_area_struct *);
 	if (use_pde(pde)) {
+		typeof_member(struct file_operations, mmap) mmap;
+
 		mmap = pde->proc_fops->mmap;
 		if (mmap)
 			rv = mmap(file, vma);
@@ -305,7 +312,7 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
 	unsigned long rv = -EIO;
 
 	if (use_pde(pde)) {
-		typeof(proc_reg_get_unmapped_area) *get_area;
+		typeof_member(struct file_operations, get_unmapped_area) get_area;
 
 		get_area = pde->proc_fops->get_unmapped_area;
 #ifdef CONFIG_MMU
@@ -326,8 +333,8 @@ static int proc_reg_open(struct inode *inode, struct file *file)
 {
 	struct proc_dir_entry *pde = PDE(inode);
 	int rv = 0;
-	int (*open)(struct inode *, struct file *);
+	typeof_member(struct file_operations, open) open;
-	int (*release)(struct inode *, struct file *);
+	typeof_member(struct file_operations, release) release;
 	struct pde_opener *pdeo;
 
 	/*

fs/proc/proc_sysctl.c

@@ -499,6 +499,10 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 
 	if (root->set_ownership)
 		root->set_ownership(head, table, &inode->i_uid, &inode->i_gid);
+	else {
+		inode->i_uid = GLOBAL_ROOT_UID;
+		inode->i_gid = GLOBAL_ROOT_GID;
+	}
 
 	return inode;
 }

fs/proc/vmcore.c

@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/crash_dump.h>
 #include <linux/list.h>
+#include <linux/moduleparam.h>
 #include <linux/mutex.h>
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
@@ -54,6 +55,9 @@ static struct proc_dir_entry *proc_vmcore;
 /* Device Dump list and mutex to synchronize access to list */
 static LIST_HEAD(vmcoredd_list);
 static DEFINE_MUTEX(vmcoredd_mutex);
+
+static bool vmcoredd_disabled;
+core_param(novmcoredd, vmcoredd_disabled, bool, 0);
 #endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */
 
 /* Device Dump Size */
@@ -1452,6 +1456,11 @@ int vmcore_add_device_dump(struct vmcoredd_data *data)
 	size_t data_size;
 	int ret;
 
+	if (vmcoredd_disabled) {
+		pr_err_once("Device dump is disabled\n");
+		return -EINVAL;
+	}
+
 	if (!data || !strlen(data->dump_name) ||
 	    !data->vmcoredd_callback || !data->size)
 		return -EINVAL;

fs/reiserfs/journal.c

@@ -94,7 +94,7 @@ static int journal_join(struct reiserfs_transaction_handle *th,
 			struct super_block *sb);
 static void release_journal_dev(struct super_block *super,
 			       struct reiserfs_journal *journal);
-static int dirty_one_transaction(struct super_block *s,
+static void dirty_one_transaction(struct super_block *s,
 				 struct reiserfs_journal_list *jl);
 static void flush_async_commits(struct work_struct *work);
 static void queue_log_writer(struct super_block *s);
@@ -1682,12 +1682,11 @@ next:
 }
 
 /* used by flush_commit_list */
-static int dirty_one_transaction(struct super_block *s,
+static void dirty_one_transaction(struct super_block *s,
 				 struct reiserfs_journal_list *jl)
 {
 	struct reiserfs_journal_cnode *cn;
 	struct reiserfs_journal_list *pjl;
-	int ret = 0;
 
 	jl->j_state |= LIST_DIRTY;
 	cn = jl->j_realblock;
@@ -1716,7 +1715,6 @@ static int dirty_one_transaction(struct super_block *s,
 		}
 		cn = cn->next;
 	}
-	return ret;
 }
 
 static int kupdate_transactions(struct super_block *s,

fs/select.c

@@ -294,12 +294,14 @@ enum poll_time_type {
 	PT_OLD_TIMESPEC = 3,
 };
 
-static int poll_select_copy_remaining(struct timespec64 *end_time,
+static int poll_select_finish(struct timespec64 *end_time,
-				      void __user *p,
+			      void __user *p,
-				      enum poll_time_type pt_type, int ret)
+			      enum poll_time_type pt_type, int ret)
 {
 	struct timespec64 rts;
 
+	restore_saved_sigmask_unless(ret == -ERESTARTNOHAND);
+
 	if (!p)
 		return ret;
 
@@ -714,9 +716,7 @@ static int kern_select(int n, fd_set __user *inp, fd_set __user *outp,
 	}
 
 	ret = core_sys_select(n, inp, outp, exp, to);
-	ret = poll_select_copy_remaining(&end_time, tvp, PT_TIMEVAL, ret);
+	return poll_select_finish(&end_time, tvp, PT_TIMEVAL, ret);
-
-	return ret;
 }
 
 SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
@@ -730,7 +730,6 @@ static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp,
 		       const sigset_t __user *sigmask, size_t sigsetsize,
 		       enum poll_time_type type)
 {
-	sigset_t ksigmask, sigsaved;
 	struct timespec64 ts, end_time, *to = NULL;
 	int ret;
 
@@ -753,15 +752,12 @@ static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp,
 			return -EINVAL;
 	}
 
-	ret = set_user_sigmask(sigmask, &ksigmask, &sigsaved, sigsetsize);
+	ret = set_user_sigmask(sigmask, sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = core_sys_select(n, inp, outp, exp, to);
-	restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND);
+	return poll_select_finish(&end_time, tsp, type, ret);
-	ret = poll_select_copy_remaining(&end_time, tsp, type, ret);
-
-	return ret;
 }
 
 /*
@@ -926,7 +922,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 		if (!count) {
 			count = wait->error;
 			if (signal_pending(current))
-				count = -EINTR;
+				count = -ERESTARTNOHAND;
 		}
 		if (count || timed_out)
 			break;
@@ -965,7 +961,7 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 		struct timespec64 *end_time)
 {
 	struct poll_wqueues table;
- 	int err = -EFAULT, fdcount, len, size;
+	int err = -EFAULT, fdcount, len;
 	/* Allocate small arguments on the stack to save memory and be
 	   faster - use long to make sure the buffer is aligned properly
 	   on 64 bit archs to avoid unaligned access */
@@ -993,8 +989,8 @@ static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 			break;
 
 		len = min(todo, POLLFD_PER_PAGE);
-		size = sizeof(struct poll_list) + sizeof(struct pollfd) * len;
+		walk = walk->next = kmalloc(struct_size(walk, entries, len),
-		walk = walk->next = kmalloc(size, GFP_KERNEL);
+					    GFP_KERNEL);
 		if (!walk) {
 			err = -ENOMEM;
 			goto out_fds;
@@ -1041,7 +1037,7 @@ static long do_restart_poll(struct restart_block *restart_block)
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	if (ret == -EINTR) {
+	if (ret == -ERESTARTNOHAND) {
 		restart_block->fn = do_restart_poll;
 		ret = -ERESTART_RESTARTBLOCK;
 	}
@@ -1062,7 +1058,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	if (ret == -EINTR) {
+	if (ret == -ERESTARTNOHAND) {
 		struct restart_block *restart_block;
 
 		restart_block = &current->restart_block;
@@ -1086,7 +1082,6 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
 		struct __kernel_timespec __user *, tsp, const sigset_t __user *, sigmask,
 		size_t, sigsetsize)
 {
-	sigset_t ksigmask, sigsaved;
 	struct timespec64 ts, end_time, *to = NULL;
 	int ret;
 
@@ -1099,20 +1094,12 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
 			return -EINVAL;
 	}
 
-	ret = set_user_sigmask(sigmask, &ksigmask, &sigsaved, sigsetsize);
+	ret = set_user_sigmask(sigmask, sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = do_sys_poll(ufds, nfds, to);
-
+	return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret);
-	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
-	/* We can restart this syscall, usually */
-	if (ret == -EINTR)
-		ret = -ERESTARTNOHAND;
-
-	ret = poll_select_copy_remaining(&end_time, tsp, PT_TIMESPEC, ret);
-
-	return ret;
 }
 
 #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT)
@@ -1121,7 +1108,6 @@ SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds,
 		struct old_timespec32 __user *, tsp, const sigset_t __user *, sigmask,
 		size_t, sigsetsize)
 {
-	sigset_t ksigmask, sigsaved;
 	struct timespec64 ts, end_time, *to = NULL;
 	int ret;
 
@@ -1134,20 +1120,12 @@ SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds,
 			return -EINVAL;
 	}
 
-	ret = set_user_sigmask(sigmask, &ksigmask, &sigsaved, sigsetsize);
+	ret = set_user_sigmask(sigmask, sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = do_sys_poll(ufds, nfds, to);
-
+	return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret);
-	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
-	/* We can restart this syscall, usually */
-	if (ret == -EINTR)
-		ret = -ERESTARTNOHAND;
-
-	ret = poll_select_copy_remaining(&end_time, tsp, PT_OLD_TIMESPEC, ret);
-
-	return ret;
 }
 #endif
 
@@ -1284,9 +1262,7 @@ static int do_compat_select(int n, compat_ulong_t __user *inp,
 	}
 
 	ret = compat_core_sys_select(n, inp, outp, exp, to);
-	ret = poll_select_copy_remaining(&end_time, tvp, PT_OLD_TIMEVAL, ret);
+	return poll_select_finish(&end_time, tvp, PT_OLD_TIMEVAL, ret);
-
-	return ret;
 }
 
 COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp,
@@ -1319,7 +1295,6 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp,
 	void __user *tsp, compat_sigset_t __user *sigmask,
 	compat_size_t sigsetsize, enum poll_time_type type)
 {
-	sigset_t ksigmask, sigsaved;
 	struct timespec64 ts, end_time, *to = NULL;
 	int ret;
 
@@ -1342,15 +1317,12 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp,
 			return -EINVAL;
 	}
 
-	ret = set_compat_user_sigmask(sigmask, &ksigmask, &sigsaved, sigsetsize);
+	ret = set_compat_user_sigmask(sigmask, sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = compat_core_sys_select(n, inp, outp, exp, to);
-	restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND);
+	return poll_select_finish(&end_time, tsp, type, ret);
-	ret = poll_select_copy_remaining(&end_time, tsp, type, ret);
-
-	return ret;
 }
 
 COMPAT_SYSCALL_DEFINE6(pselect6_time64, int, n, compat_ulong_t __user *, inp,
@@ -1402,7 +1374,6 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds,
 	unsigned int,  nfds, struct old_timespec32 __user *, tsp,
 	const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
 {
-	sigset_t ksigmask, sigsaved;
 	struct timespec64 ts, end_time, *to = NULL;
 	int ret;
 
@@ -1415,20 +1386,12 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds,
 			return -EINVAL;
 	}
 
-	ret = set_compat_user_sigmask(sigmask, &ksigmask, &sigsaved, sigsetsize);
+	ret = set_compat_user_sigmask(sigmask, sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = do_sys_poll(ufds, nfds, to);
-
+	return poll_select_finish(&end_time, tsp, PT_OLD_TIMESPEC, ret);
-	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
-	/* We can restart this syscall, usually */
-	if (ret == -EINTR)
-		ret = -ERESTARTNOHAND;
-
-	ret = poll_select_copy_remaining(&end_time, tsp, PT_OLD_TIMESPEC, ret);
-
-	return ret;
 }
 #endif
 
@@ -1437,7 +1400,6 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds,
 	unsigned int,  nfds, struct __kernel_timespec __user *, tsp,
 	const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
 {
-	sigset_t ksigmask, sigsaved;
 	struct timespec64 ts, end_time, *to = NULL;
 	int ret;
 
@@ -1450,20 +1412,12 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds,
 			return -EINVAL;
 	}
 
-	ret = set_compat_user_sigmask(sigmask, &ksigmask, &sigsaved, sigsetsize);
+	ret = set_compat_user_sigmask(sigmask, sigsetsize);
 	if (ret)
 		return ret;
 
 	ret = do_sys_poll(ufds, nfds, to);
-
+	return poll_select_finish(&end_time, tsp, PT_TIMESPEC, ret);
-	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
-	/* We can restart this syscall, usually */
-	if (ret == -EINTR)
-		ret = -ERESTARTNOHAND;
-
-	ret = poll_select_copy_remaining(&end_time, tsp, PT_TIMESPEC, ret);
-
-	return ret;
 }
 
 #endif

fs/ufs/super.c

@@ -1407,11 +1407,9 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct super_block *sb = dentry->d_sb;
 	struct ufs_sb_private_info *uspi= UFS_SB(sb)->s_uspi;
 	unsigned  flags = UFS_SB(sb)->s_flags;
-	struct ufs_super_block_third *usb3;
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	mutex_lock(&UFS_SB(sb)->s_lock);
-	usb3 = ubh_get_usb_third(uspi);
 	
 	if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2)
 		buf->f_type = UFS2_MAGIC;

include/asm-generic/bug.h

@@ -104,8 +104,10 @@ extern void warn_slowpath_null(const char *file, const int line);
 	warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg)
 #else
 extern __printf(1, 2) void __warn_printk(const char *fmt, ...);
-#define __WARN()		__WARN_TAINT(TAINT_WARN)
+#define __WARN() do { \
-#define __WARN_printf(arg...)	do { __warn_printk(arg); __WARN(); } while (0)
+	printk(KERN_WARNING CUT_HERE); __WARN_TAINT(TAINT_WARN); \
+} while (0)
+#define __WARN_printf(arg...)	__WARN_printf_taint(TAINT_WARN, arg)
 #define __WARN_printf_taint(taint, arg...)				\
 	do { __warn_printk(arg); __WARN_TAINT(taint); } while (0)
 #endif

include/asm-generic/cacheflush.h

@@ -5,24 +5,70 @@
 /* Keep includes the same across arches.  */
 #include <linux/mm.h>
 
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+
 /*
  * The cache doesn't need to be flushed when TLB entries change when
  * the cache is mapped to physical memory, not virtual memory
  */
-#define flush_cache_all()			do { } while (0)
+static inline void flush_cache_all(void)
-#define flush_cache_mm(mm)			do { } while (0)
+{
-#define flush_cache_dup_mm(mm)			do { } while (0)
+}
-#define flush_cache_range(vma, start, end)	do { } while (0)
+
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
+static inline void flush_cache_mm(struct mm_struct *mm)
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+{
-#define flush_dcache_page(page)			do { } while (0)
+}
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
+
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
+static inline void flush_cache_dup_mm(struct mm_struct *mm)
-#define flush_icache_range(start, end)		do { } while (0)
+{
-#define flush_icache_page(vma,pg)		do { } while (0)
+}
-#define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
+
-#define flush_cache_vmap(start, end)		do { } while (0)
+static inline void flush_cache_range(struct vm_area_struct *vma,
-#define flush_cache_vunmap(start, end)		do { } while (0)
+				     unsigned long start,
+				     unsigned long end)
+{
+}
+
+static inline void flush_cache_page(struct vm_area_struct *vma,
+				    unsigned long vmaddr,
+				    unsigned long pfn)
+{
+}
+
+static inline void flush_dcache_page(struct page *page)
+{
+}
+
+static inline void flush_dcache_mmap_lock(struct address_space *mapping)
+{
+}
+
+static inline void flush_dcache_mmap_unlock(struct address_space *mapping)
+{
+}
+
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+}
+
+static inline void flush_icache_page(struct vm_area_struct *vma,
+				     struct page *page)
+{
+}
+
+static inline void flush_icache_user_range(struct vm_area_struct *vma,
+					   struct page *page,
+					   unsigned long addr, int len)
+{
+}
+
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+}
+
+static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
+{
+}
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
 	do { \

include/linux/bits.h

@@ -1,13 +1,15 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_BITS_H
 #define __LINUX_BITS_H
+
+#include <linux/const.h>
 #include <asm/bitsperlong.h>
 
-#define BIT(nr)			(1UL << (nr))
+#define BIT(nr)			(UL(1) << (nr))
-#define BIT_ULL(nr)		(1ULL << (nr))
+#define BIT_ULL(nr)		(ULL(1) << (nr))
-#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_MASK(nr)	(ULL(1) << ((nr) % BITS_PER_LONG_LONG))
 #define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
 #define BITS_PER_BYTE		8
 
@@ -17,10 +19,11 @@
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
 #define GENMASK(h, l) \
-	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+	(((~UL(0)) - (UL(1) << (l)) + 1) & \
+	 (~UL(0) >> (BITS_PER_LONG - 1 - (h))))
 
 #define GENMASK_ULL(h, l) \
-	(((~0ULL) - (1ULL << (l)) + 1) & \
+	(((~ULL(0)) - (ULL(1) << (l)) + 1) & \
-	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+	 (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
 
 #endif	/* __LINUX_BITS_H */

include/linux/coda.h

@@ -58,8 +58,7 @@ Mellon the rights to redistribute these changes without encumbrance.
 #ifndef _CODA_HEADER_
 #define _CODA_HEADER_
 
-#if defined(__linux__)
 typedef unsigned long long u_quad_t;
-#endif
+
 #include <uapi/linux/coda.h>
 #endif 

include/linux/compat.h

@@ -138,8 +138,7 @@ typedef struct {
 	compat_sigset_word	sig[_COMPAT_NSIG_WORDS];
 } compat_sigset_t;
 
-int set_compat_user_sigmask(const compat_sigset_t __user *usigmask,
+int set_compat_user_sigmask(const compat_sigset_t __user *umask,
-			    sigset_t *set, sigset_t *oldset,
 			    size_t sigsetsize);
 
 struct compat_sigaction {

include/linux/io.h

@@ -33,6 +33,7 @@ static inline int ioremap_page_range(unsigned long addr, unsigned long end,
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
 void __init ioremap_huge_init(void);
+int arch_ioremap_p4d_supported(void);
 int arch_ioremap_pud_supported(void);
 int arch_ioremap_pmd_supported(void);
 #else

include/linux/kernel.h

@@ -88,6 +88,8 @@
  */
 #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
 
+#define typeof_member(T, m)	typeof(((T*)0)->m)
+
 #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP
 
 #define DIV_ROUND_DOWN_ULL(ll, d) \

include/linux/kprobes.h

@@ -458,4 +458,23 @@ static inline bool is_kprobe_optinsn_slot(unsigned long addr)
 }
 #endif
 
+/* Returns true if kprobes handled the fault */
+static nokprobe_inline bool kprobe_page_fault(struct pt_regs *regs,
+					      unsigned int trap)
+{
+	if (!kprobes_built_in())
+		return false;
+	if (user_mode(regs))
+		return false;
+	/*
+	 * To be potentially processing a kprobe fault and to be allowed
+	 * to call kprobe_running(), we have to be non-preemptible.
+	 */
+	if (preemptible())
+		return false;
+	if (!kprobe_running())
+		return false;
+	return kprobe_fault_handler(regs, trap);
+}
+
 #endif /* _LINUX_KPROBES_H */

include/linux/lz4.h

@@ -278,7 +278,7 @@ int LZ4_decompress_fast(const char *source, char *dest, int originalSize);
  * @compressedSize: is the precise full size of the compressed block
  * @maxDecompressedSize: is the size of 'dest' buffer
  *
- * Decompresses data fom 'source' into 'dest'.
+ * Decompresses data from 'source' into 'dest'.
  * If the source stream is detected malformed, the function will
  * stop decoding and return a negative result.
  * This function is protected against buffer overflow exploits,
@@ -522,7 +522,7 @@ int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode,
 	const char *dictionary, int dictSize);
 
 /**
- * LZ4_decompress_fast_continue() - Decompress blocks in streaming mode
+ * LZ4_decompress_safe_continue() - Decompress blocks in streaming mode
  * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure
  * @source: source address of the compressed data
  * @dest: output buffer address of the uncompressed data
@@ -530,7 +530,7 @@ int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode,
  * @compressedSize: is the precise full size of the compressed block
  * @maxDecompressedSize: is the size of 'dest' buffer
  *
- * These decoding function allows decompression of multiple blocks
+ * This decoding function allows decompression of multiple blocks
  * in "streaming" mode.
  * Previously decoded blocks *must* remain available at the memory position
  * where they were decoded (up to 64 KB)
@@ -569,7 +569,7 @@ int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode,
  *	which must be already allocated with 'originalSize' bytes
  * @originalSize: is the original and therefore uncompressed size
  *
- * These decoding function allows decompression of multiple blocks
+ * This decoding function allows decompression of multiple blocks
  * in "streaming" mode.
  * Previously decoded blocks *must* remain available at the memory position
  * where they were decoded (up to 64 KB)
@@ -610,10 +610,10 @@ int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode,
  * @dictStart: pointer to the start of the dictionary in memory
  * @dictSize: size of dictionary
  *
- * These decoding function works the same as
+ * This decoding function works the same as
  * a combination of LZ4_setStreamDecode() followed by
  * LZ4_decompress_safe_continue()
- * It is stand-alone, and don'tn eed a LZ4_streamDecode_t structure.
+ * It is stand-alone, and doesn't need an LZ4_streamDecode_t structure.
  *
  * Return: number of bytes decompressed into destination buffer
  *	(necessarily <= maxDecompressedSize)
@@ -633,10 +633,10 @@ int LZ4_decompress_safe_usingDict(const char *source, char *dest,
  * @dictStart: pointer to the start of the dictionary in memory
  * @dictSize: size of dictionary
  *
- * These decoding function works the same as
+ * This decoding function works the same as
  * a combination of LZ4_setStreamDecode() followed by
- * LZ4_decompress_safe_continue()
+ * LZ4_decompress_fast_continue()
- * It is stand-alone, and don'tn eed a LZ4_streamDecode_t structure.
+ * It is stand-alone, and doesn't need an LZ4_streamDecode_t structure.
  *
  * Return: number of bytes decompressed into destination buffer
  *	(necessarily <= maxDecompressedSize)

include/linux/memory_hotplug.h

@@ -324,7 +324,7 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
 extern bool is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
 extern void try_offline_node(int nid);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
-extern void remove_memory(int nid, u64 start, u64 size);
+extern int remove_memory(int nid, u64 start, u64 size);
 extern void __remove_memory(int nid, u64 start, u64 size);
 
 #else
@@ -341,7 +341,11 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
 	return -EINVAL;
 }
 
-static inline void remove_memory(int nid, u64 start, u64 size) {}
+static inline int remove_memory(int nid, u64 start, u64 size)
+{
+	return -EBUSY;
+}
+
 static inline void __remove_memory(int nid, u64 start, u64 size) {}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 

include/linux/mm.h

@@ -547,7 +547,7 @@ static inline void vma_set_anonymous(struct vm_area_struct *vma)
 struct mmu_gather;
 struct inode;
 
-#if !defined(__HAVE_ARCH_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
+#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
 static inline int pmd_devmap(pmd_t pmd)
 {
 	return 0;
@@ -956,41 +956,28 @@ static inline bool put_devmap_managed_page(struct page *page)
 	return false;
 }
 
-static inline bool is_device_private_page(const struct page *page)
-{
-	return is_zone_device_page(page) &&
-		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
-}
-
-#ifdef CONFIG_PCI_P2PDMA
-static inline bool is_pci_p2pdma_page(const struct page *page)
-{
-	return is_zone_device_page(page) &&
-		page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
-}
-#else /* CONFIG_PCI_P2PDMA */
-static inline bool is_pci_p2pdma_page(const struct page *page)
-{
-	return false;
-}
-#endif /* CONFIG_PCI_P2PDMA */
-
 #else /* CONFIG_DEV_PAGEMAP_OPS */
 static inline bool put_devmap_managed_page(struct page *page)
 {
 	return false;
 }
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
 
 static inline bool is_device_private_page(const struct page *page)
 {
-	return false;
+	return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) &&
+		IS_ENABLED(CONFIG_DEVICE_PRIVATE) &&
+		is_zone_device_page(page) &&
+		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
 }
 
 static inline bool is_pci_p2pdma_page(const struct page *page)
 {
-	return false;
+	return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) &&
+		IS_ENABLED(CONFIG_PCI_P2PDMA) &&
+		is_zone_device_page(page) &&
+		page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
 }
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
 
 /* 127: arbitrary random number, small enough to assemble well */
 #define page_ref_zero_or_close_to_overflow(page) \
@@ -1556,6 +1543,10 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 int get_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
 
+int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
+int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
+			struct task_struct *task, bool bypass_rlim);
+
 /* Container for pinned pfns / pages */
 struct frame_vector {
 	unsigned int nr_allocated;	/* Number of frames we have space for */
@@ -1763,7 +1754,7 @@ static inline void sync_mm_rss(struct mm_struct *mm)
 }
 #endif
 
-#ifndef __HAVE_ARCH_PTE_DEVMAP
+#ifndef CONFIG_ARCH_HAS_PTE_DEVMAP
 static inline int pte_devmap(pte_t pte)
 {
 	return 0;
@@ -2767,7 +2758,13 @@ extern int randomize_va_space;
 #endif
 
 const char * arch_vma_name(struct vm_area_struct *vma);
+#ifdef CONFIG_MMU
 void print_vma_addr(char *prefix, unsigned long rip);
+#else
+static inline void print_vma_addr(char *prefix, unsigned long rip)
+{
+}
+#endif
 
 void *sparse_buffer_alloc(unsigned long size);
 struct page *sparse_mem_map_populate(unsigned long pnum, int nid,

include/linux/pfn_t.h

@@ -97,7 +97,7 @@ static inline pud_t pfn_t_pud(pfn_t pfn, pgprot_t pgprot)
 #endif
 #endif
 
-#ifdef __HAVE_ARCH_PTE_DEVMAP
+#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
 static inline bool pfn_t_devmap(pfn_t pfn)
 {
 	const u64 flags = PFN_DEV|PFN_MAP;
@@ -115,7 +115,7 @@ pmd_t pmd_mkdevmap(pmd_t pmd);
 	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 pud_t pud_mkdevmap(pud_t pud);
 #endif
-#endif /* __HAVE_ARCH_PTE_DEVMAP */
+#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */
 
 #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
 static inline bool pfn_t_special(pfn_t pfn)

include/linux/pid.h

@@ -4,6 +4,7 @@
 
 #include <linux/rculist.h>
 #include <linux/wait.h>
+#include <linux/refcount.h>
 
 enum pid_type
 {
@@ -57,7 +58,7 @@ struct upid {
 
 struct pid
 {
-	atomic_t count;
+	refcount_t count;
 	unsigned int level;
 	/* lists of tasks that use this pid */
 	struct hlist_head tasks[PIDTYPE_MAX];
@@ -74,7 +75,7 @@ extern const struct file_operations pidfd_fops;
 static inline struct pid *get_pid(struct pid *pid)
 {
 	if (pid)
-		atomic_inc(&pid->count);
+		refcount_inc(&pid->count);
 	return pid;
 }
 

include/linux/poison.h

@@ -21,7 +21,7 @@
  * non-initialized list entries.
  */
 #define LIST_POISON1  ((void *) 0x100 + POISON_POINTER_DELTA)
-#define LIST_POISON2  ((void *) 0x200 + POISON_POINTER_DELTA)
+#define LIST_POISON2  ((void *) 0x122 + POISON_POINTER_DELTA)
 
 /********** include/linux/timer.h **********/
 /*

include/linux/rbtree.h

@@ -32,25 +32,9 @@ struct rb_root {
 	struct rb_node *rb_node;
 };
 
-/*
- * Leftmost-cached rbtrees.
- *
- * We do not cache the rightmost node based on footprint
- * size vs number of potential users that could benefit
- * from O(1) rb_last(). Just not worth it, users that want
- * this feature can always implement the logic explicitly.
- * Furthermore, users that want to cache both pointers may
- * find it a bit asymmetric, but that's ok.
- */
-struct rb_root_cached {
-	struct rb_root rb_root;
-	struct rb_node *rb_leftmost;
-};
-
 #define rb_parent(r)   ((struct rb_node *)((r)->__rb_parent_color & ~3))
 
 #define RB_ROOT	(struct rb_root) { NULL, }
-#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL }
 #define	rb_entry(ptr, type, member) container_of(ptr, type, member)
 
 #define RB_EMPTY_ROOT(root)  (READ_ONCE((root)->rb_node) == NULL)
@@ -72,12 +56,6 @@ extern struct rb_node *rb_prev(const struct rb_node *);
 extern struct rb_node *rb_first(const struct rb_root *);
 extern struct rb_node *rb_last(const struct rb_root *);
 
-extern void rb_insert_color_cached(struct rb_node *,
-				   struct rb_root_cached *, bool);
-extern void rb_erase_cached(struct rb_node *node, struct rb_root_cached *);
-/* Same as rb_first(), but O(1) */
-#define rb_first_cached(root) (root)->rb_leftmost
-
 /* Postorder iteration - always visit the parent after its children */
 extern struct rb_node *rb_first_postorder(const struct rb_root *);
 extern struct rb_node *rb_next_postorder(const struct rb_node *);
@@ -87,8 +65,6 @@ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
 			    struct rb_root *root);
 extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new,
 				struct rb_root *root);
-extern void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new,
-				   struct rb_root_cached *root);
 
 static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
 				struct rb_node **rb_link)
@@ -136,4 +112,50 @@ static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent
 			typeof(*pos), field); 1; }); \
 	     pos = n)
 
+/*
+ * Leftmost-cached rbtrees.
+ *
+ * We do not cache the rightmost node based on footprint
+ * size vs number of potential users that could benefit
+ * from O(1) rb_last(). Just not worth it, users that want
+ * this feature can always implement the logic explicitly.
+ * Furthermore, users that want to cache both pointers may
+ * find it a bit asymmetric, but that's ok.
+ */
+struct rb_root_cached {
+	struct rb_root rb_root;
+	struct rb_node *rb_leftmost;
+};
+
+#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL }
+
+/* Same as rb_first(), but O(1) */
+#define rb_first_cached(root) (root)->rb_leftmost
+
+static inline void rb_insert_color_cached(struct rb_node *node,
+					  struct rb_root_cached *root,
+					  bool leftmost)
+{
+	if (leftmost)
+		root->rb_leftmost = node;
+	rb_insert_color(node, &root->rb_root);
+}
+
+static inline void rb_erase_cached(struct rb_node *node,
+				   struct rb_root_cached *root)
+{
+	if (root->rb_leftmost == node)
+		root->rb_leftmost = rb_next(node);
+	rb_erase(node, &root->rb_root);
+}
+
+static inline void rb_replace_node_cached(struct rb_node *victim,
+					  struct rb_node *new,
+					  struct rb_root_cached *root)
+{
+	if (root->rb_leftmost == victim)
+		root->rb_leftmost = new;
+	rb_replace_node(victim, new, &root->rb_root);
+}
+
 #endif	/* _LINUX_RBTREE_H */

include/linux/rbtree_augmented.h

@@ -30,10 +30,9 @@ struct rb_augment_callbacks {
 	void (*rotate)(struct rb_node *old, struct rb_node *new);
 };
 
-extern void __rb_insert_augmented(struct rb_node *node,
+extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
-				  struct rb_root *root,
-				  bool newleft, struct rb_node **leftmost,
 	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
 /*
  * Fixup the rbtree and update the augmented information when rebalancing.
  *
@@ -48,7 +47,7 @@ static inline void
 rb_insert_augmented(struct rb_node *node, struct rb_root *root,
 		    const struct rb_augment_callbacks *augment)
 {
-	__rb_insert_augmented(node, root, false, NULL, augment->rotate);
+	__rb_insert_augmented(node, root, augment->rotate);
 }
 
 static inline void
@@ -56,8 +55,9 @@ rb_insert_augmented_cached(struct rb_node *node,
 			   struct rb_root_cached *root, bool newleft,
 			   const struct rb_augment_callbacks *augment)
 {
-	__rb_insert_augmented(node, &root->rb_root,
+	if (newleft)
-			      newleft, &root->rb_leftmost, augment->rotate);
+		root->rb_leftmost = node;
+	rb_insert_augmented(node, &root->rb_root, augment);
 }
 
 #define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield,	\
@@ -150,7 +150,6 @@ extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
 
 static __always_inline struct rb_node *
 __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
-		     struct rb_node **leftmost,
 		     const struct rb_augment_callbacks *augment)
 {
 	struct rb_node *child = node->rb_right;
@@ -158,9 +157,6 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 	struct rb_node *parent, *rebalance;
 	unsigned long pc;
 
-	if (leftmost && node == *leftmost)
-		*leftmost = rb_next(node);
-
 	if (!tmp) {
 		/*
 		 * Case 1: node to erase has no more than 1 child (easy!)
@@ -260,8 +256,7 @@ static __always_inline void
 rb_erase_augmented(struct rb_node *node, struct rb_root *root,
 		   const struct rb_augment_callbacks *augment)
 {
-	struct rb_node *rebalance = __rb_erase_augmented(node, root,
+	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
-							 NULL, augment);
 	if (rebalance)
 		__rb_erase_color(rebalance, root, augment->rotate);
 }
@@ -270,11 +265,9 @@ static __always_inline void
 rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root,
 			  const struct rb_augment_callbacks *augment)
 {
-	struct rb_node *rebalance = __rb_erase_augmented(node, &root->rb_root,
+	if (root->rb_leftmost == node)
-							 &root->rb_leftmost,
+		root->rb_leftmost = rb_next(node);
-							 augment);
+	rb_erase_augmented(node, &root->rb_root, augment);
-	if (rebalance)
-		__rb_erase_color(rebalance, &root->rb_root, augment->rotate);
 }
 
 #endif	/* _LINUX_RBTREE_AUGMENTED_H */