From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758573Ab0I0AlH (ORCPT ); Sun, 26 Sep 2010 20:41:07 -0400 Received: from kroah.org ([198.145.64.141]:41352 "EHLO coco.kroah.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758516Ab0I0AlB (ORCPT ); Sun, 26 Sep 2010 20:41:01 -0400 Date: Sun, 26 Sep 2010 17:36:23 -0700 From: Greg KH To: linux-kernel@vger.kernel.org, Andrew Morton , torvalds@linux-foundation.org, stable@kernel.org, lwn@lwn.net Subject: Re: Linux 2.6.35.6 Message-ID: <20100927003623.GB20395@kroah.com> References: <20100927003608.GA20395@kroah.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100927003608.GA20395@kroah.com> User-Agent: Mutt/1.5.17 (2007-11-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org diff --git a/Makefile b/Makefile index 11aaa51..78f9271 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 35 -EXTRAVERSION = .5 +EXTRAVERSION = .6 NAME = Sheep on Meth # *DOCUMENTATION* diff --git a/arch/alpha/kernel/err_marvel.c b/arch/alpha/kernel/err_marvel.c index 52a79df..5c905aa 100644 --- a/arch/alpha/kernel/err_marvel.c +++ b/arch/alpha/kernel/err_marvel.c @@ -109,7 +109,7 @@ marvel_print_err_cyc(u64 err_cyc) #define IO7__ERR_CYC__CYCLE__M (0x7) printk("%s Packet In Error: %s\n" - "%s Error in %s, cycle %ld%s%s\n", + "%s Error in %s, cycle %lld%s%s\n", err_print_prefix, packet_desc[EXTRACT(err_cyc, IO7__ERR_CYC__PACKET)], err_print_prefix, @@ -313,7 +313,7 @@ marvel_print_po7_ugbge_sym(u64 ugbge_sym) } printk("%s Up Hose Garbage Symptom:\n" - "%s Source Port: %ld - Dest PID: %ld - OpCode: %s\n", + "%s Source Port: %lld - Dest PID: %lld - OpCode: %s\n", err_print_prefix, err_print_prefix, EXTRACT(ugbge_sym, IO7__PO7_UGBGE_SYM__UPH_SRC_PORT), @@ -552,7 +552,7 @@ marvel_print_pox_spl_cmplt(u64 spl_cmplt) #define IO7__POX_SPLCMPLT__REM_BYTE_COUNT__M (0xfff) printk("%s Split Completion Error:\n" - "%s Source (Bus:Dev:Func): %ld:%ld:%ld\n", + "%s Source (Bus:Dev:Func): %lld:%lld:%lld\n", err_print_prefix, err_print_prefix, EXTRACT(spl_cmplt, IO7__POX_SPLCMPLT__SOURCE_BUS), diff --git a/arch/alpha/kernel/proto.h b/arch/alpha/kernel/proto.h index 3d2627e..d3e52d3 100644 --- a/arch/alpha/kernel/proto.h +++ b/arch/alpha/kernel/proto.h @@ -156,9 +156,6 @@ extern void SMC669_Init(int); /* es1888.c */ extern void es1888_init(void); -/* ns87312.c */ -extern void ns87312_enable_ide(long ide_base); - /* ../lib/fpreg.c */ extern void alpha_write_fp_reg (unsigned long reg, unsigned long val); extern unsigned long alpha_read_fp_reg (unsigned long reg); diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index affd0f3..14c8898 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -33,7 +33,7 @@ #include "irq_impl.h" #include "pci_impl.h" #include "machvec_impl.h" - +#include "pc873xx.h" /* Note mask bit is true for DISABLED irqs. */ static unsigned long cached_irq_mask = ~0UL; @@ -236,17 +236,30 @@ cabriolet_map_irq(struct pci_dev *dev, u8 slot, u8 pin) } static inline void __init +cabriolet_enable_ide(void) +{ + if (pc873xx_probe() == -1) { + printk(KERN_ERR "Probing for PC873xx Super IO chip failed.\n"); + } else { + printk(KERN_INFO "Found %s Super IO chip at 0x%x\n", + pc873xx_get_model(), pc873xx_get_base()); + + pc873xx_enable_ide(); + } +} + +static inline void __init cabriolet_init_pci(void) { common_init_pci(); - ns87312_enable_ide(0x398); + cabriolet_enable_ide(); } static inline void __init cia_cab_init_pci(void) { cia_init_pci(); - ns87312_enable_ide(0x398); + cabriolet_enable_ide(); } /* diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c index 2304648..4da596b 100644 --- a/arch/alpha/kernel/sys_takara.c +++ b/arch/alpha/kernel/sys_takara.c @@ -29,7 +29,7 @@ #include "irq_impl.h" #include "pci_impl.h" #include "machvec_impl.h" - +#include "pc873xx.h" /* Note mask bit is true for DISABLED irqs. */ static unsigned long cached_irq_mask[2] = { -1, -1 }; @@ -264,7 +264,14 @@ takara_init_pci(void) alpha_mv.pci_map_irq = takara_map_irq_srm; cia_init_pci(); - ns87312_enable_ide(0x26e); + + if (pc873xx_probe() == -1) { + printk(KERN_ERR "Probing for PC873xx Super IO chip failed.\n"); + } else { + printk(KERN_INFO "Found %s Super IO chip at 0x%x\n", + pc873xx_get_model(), pc873xx_get_base()); + pc873xx_enable_ide(); + } } diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c index 809114d..501ac6f 100644 --- a/arch/arm/mach-at91/at91sam9g45_devices.c +++ b/arch/arm/mach-at91/at91sam9g45_devices.c @@ -46,7 +46,7 @@ static struct resource hdmac_resources[] = { .end = AT91_BASE_SYS + AT91_DMA + SZ_512 - 1, .flags = IORESOURCE_MEM, }, - [2] = { + [1] = { .start = AT91SAM9G45_ID_DMA, .end = AT91SAM9G45_ID_DMA, .flags = IORESOURCE_IRQ, diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S index 3567d54..331d42b 100644 --- a/arch/ia64/kernel/fsys.S +++ b/arch/ia64/kernel/fsys.S @@ -420,22 +420,31 @@ EX(.fail_efault, ld8 r14=[r33]) // r14 <- *set ;; RSM_PSR_I(p0, r18, r19) // mask interrupt delivery - mov ar.ccv=0 andcm r14=r14,r17 // filter out SIGKILL & SIGSTOP + mov r8=EINVAL // default to EINVAL #ifdef CONFIG_SMP - mov r17=1 + // __ticket_spin_trylock(r31) + ld4 r17=[r31] ;; - cmpxchg4.acq r18=[r31],r17,ar.ccv // try to acquire the lock - mov r8=EINVAL // default to EINVAL + mov.m ar.ccv=r17 + extr.u r9=r17,17,15 + adds r19=1,r17 + extr.u r18=r17,0,15 + ;; + cmp.eq p6,p7=r9,r18 ;; +(p6) cmpxchg4.acq r9=[r31],r19,ar.ccv +(p6) dep.z r20=r19,1,15 // next serving ticket for unlock +(p7) br.cond.spnt.many .lock_contention + ;; + cmp4.eq p0,p7=r9,r17 + adds r31=2,r31 +(p7) br.cond.spnt.many .lock_contention ld8 r3=[r2] // re-read current->blocked now that we hold the lock - cmp4.ne p6,p0=r18,r0 -(p6) br.cond.spnt.many .lock_contention ;; #else ld8 r3=[r2] // re-read current->blocked now that we hold the lock - mov r8=EINVAL // default to EINVAL #endif add r18=IA64_TASK_PENDING_OFFSET+IA64_SIGPENDING_SIGNAL_OFFSET,r16 add r19=IA64_TASK_SIGNAL_OFFSET,r16 @@ -490,7 +499,9 @@ EX(.fail_efault, ld8 r14=[r33]) // r14 <- *set (p6) br.cond.spnt.few 1b // yes -> retry #ifdef CONFIG_SMP - st4.rel [r31]=r0 // release the lock + // __ticket_spin_unlock(r31) + st2.rel [r31]=r20 + mov r20=0 // i must not leak kernel bits... #endif SSM_PSR_I(p0, p9, r31) ;; @@ -512,7 +523,8 @@ EX(.fail_efault, (p15) st8 [r34]=r3) .sig_pending: #ifdef CONFIG_SMP - st4.rel [r31]=r0 // release the lock + // __ticket_spin_unlock(r31) + st2.rel [r31]=r20 // release the lock #endif SSM_PSR_I(p0, p9, r17) ;; diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h index a5db031..3e0b2d6 100644 --- a/arch/sparc/include/asm/oplib_64.h +++ b/arch/sparc/include/asm/oplib_64.h @@ -185,9 +185,8 @@ extern int prom_getunumber(int syndrome_code, char *buf, int buflen); /* Retain physical memory to the caller across soft resets. */ -extern unsigned long prom_retain(const char *name, - unsigned long pa_low, unsigned long pa_high, - long size, long align); +extern int prom_retain(const char *name, unsigned long size, + unsigned long align, unsigned long *paddr); /* Load explicit I/D TLB entries into the calling processor. */ extern long prom_itlb_load(unsigned long index, @@ -287,26 +286,6 @@ extern void prom_sun4v_guest_soft_state(void); extern int prom_ihandle2path(int handle, char *buffer, int bufsize); /* Client interface level routines. */ -extern long p1275_cmd(const char *, long, ...); - -#if 0 -#define P1275_SIZE(x) ((((long)((x) / 32)) << 32) | (x)) -#else -#define P1275_SIZE(x) x -#endif - -/* We support at most 16 input and 1 output argument */ -#define P1275_ARG_NUMBER 0 -#define P1275_ARG_IN_STRING 1 -#define P1275_ARG_OUT_BUF 2 -#define P1275_ARG_OUT_32B 3 -#define P1275_ARG_IN_FUNCTION 4 -#define P1275_ARG_IN_BUF 5 -#define P1275_ARG_IN_64B 6 - -#define P1275_IN(x) ((x) & 0xf) -#define P1275_OUT(x) (((x) << 4) & 0xf0) -#define P1275_INOUT(i,o) (P1275_IN(i)|P1275_OUT(o)) -#define P1275_ARG(n,x) ((x) << ((n)*3 + 8)) +extern void p1275_cmd_direct(unsigned long *); #endif /* !(__SPARC64_OPLIB_H) */ diff --git a/arch/sparc/prom/cif.S b/arch/sparc/prom/cif.S index 5f27ad7..9c86b4b 100644 --- a/arch/sparc/prom/cif.S +++ b/arch/sparc/prom/cif.S @@ -9,18 +9,18 @@ #include .text - .globl prom_cif_interface -prom_cif_interface: - sethi %hi(p1275buf), %o0 - or %o0, %lo(p1275buf), %o0 - ldx [%o0 + 0x010], %o1 ! prom_cif_stack - save %o1, -192, %sp - ldx [%i0 + 0x008], %l2 ! prom_cif_handler + .globl prom_cif_direct +prom_cif_direct: + sethi %hi(p1275buf), %o1 + or %o1, %lo(p1275buf), %o1 + ldx [%o1 + 0x0010], %o2 ! prom_cif_stack + save %o2, -192, %sp + ldx [%i1 + 0x0008], %l2 ! prom_cif_handler mov %g4, %l0 mov %g5, %l1 mov %g6, %l3 call %l2 - add %i0, 0x018, %o0 ! prom_args + mov %i0, %o0 ! prom_args mov %l0, %g4 mov %l1, %g5 mov %l3, %g6 diff --git a/arch/sparc/prom/console_64.c b/arch/sparc/prom/console_64.c index f55d58a..10322dc 100644 --- a/arch/sparc/prom/console_64.c +++ b/arch/sparc/prom/console_64.c @@ -21,14 +21,22 @@ extern int prom_stdin, prom_stdout; inline int prom_nbgetchar(void) { + unsigned long args[7]; char inc; - if (p1275_cmd("read", P1275_ARG(1,P1275_ARG_OUT_BUF)| - P1275_INOUT(3,1), - prom_stdin, &inc, P1275_SIZE(1)) == 1) + args[0] = (unsigned long) "read"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) prom_stdin; + args[4] = (unsigned long) &inc; + args[5] = 1; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + + if (args[6] == 1) return inc; - else - return -1; + return -1; } /* Non blocking put character to console device, returns -1 if @@ -37,12 +45,22 @@ prom_nbgetchar(void) inline int prom_nbputchar(char c) { + unsigned long args[7]; char outc; outc = c; - if (p1275_cmd("write", P1275_ARG(1,P1275_ARG_IN_BUF)| - P1275_INOUT(3,1), - prom_stdout, &outc, P1275_SIZE(1)) == 1) + + args[0] = (unsigned long) "write"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) prom_stdout; + args[4] = (unsigned long) &outc; + args[5] = 1; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + + if (args[6] == 1) return 0; else return -1; @@ -67,7 +85,15 @@ prom_putchar(char c) void prom_puts(const char *s, int len) { - p1275_cmd("write", P1275_ARG(1,P1275_ARG_IN_BUF)| - P1275_INOUT(3,1), - prom_stdout, s, P1275_SIZE(len)); + unsigned long args[7]; + + args[0] = (unsigned long) "write"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) prom_stdout; + args[4] = (unsigned long) s; + args[5] = len; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); } diff --git a/arch/sparc/prom/devops_64.c b/arch/sparc/prom/devops_64.c index 9dbd803..a017119 100644 --- a/arch/sparc/prom/devops_64.c +++ b/arch/sparc/prom/devops_64.c @@ -18,16 +18,32 @@ int prom_devopen(const char *dstr) { - return p1275_cmd ("open", P1275_ARG(0,P1275_ARG_IN_STRING)| - P1275_INOUT(1,1), - dstr); + unsigned long args[5]; + + args[0] = (unsigned long) "open"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) dstr; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[4]; } /* Close the device described by device handle 'dhandle'. */ int prom_devclose(int dhandle) { - p1275_cmd ("close", P1275_INOUT(1,0), dhandle); + unsigned long args[4]; + + args[0] = (unsigned long) "close"; + args[1] = 1; + args[2] = 0; + args[3] = (unsigned int) dhandle; + + p1275_cmd_direct(args); + return 0; } @@ -37,5 +53,15 @@ prom_devclose(int dhandle) void prom_seek(int dhandle, unsigned int seekhi, unsigned int seeklo) { - p1275_cmd ("seek", P1275_INOUT(3,1), dhandle, seekhi, seeklo); + unsigned long args[7]; + + args[0] = (unsigned long) "seek"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) dhandle; + args[4] = seekhi; + args[5] = seeklo; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); } diff --git a/arch/sparc/prom/misc_64.c b/arch/sparc/prom/misc_64.c index 39fc6af..6cb1581 100644 --- a/arch/sparc/prom/misc_64.c +++ b/arch/sparc/prom/misc_64.c @@ -20,10 +20,17 @@ int prom_service_exists(const char *service_name) { - int err = p1275_cmd("test", P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_INOUT(1, 1), service_name); + unsigned long args[5]; - if (err) + args[0] = (unsigned long) "test"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) service_name; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + if (args[4]) return 0; return 1; } @@ -31,30 +38,47 @@ int prom_service_exists(const char *service_name) void prom_sun4v_guest_soft_state(void) { const char *svc = "SUNW,soft-state-supported"; + unsigned long args[3]; if (!prom_service_exists(svc)) return; - p1275_cmd(svc, P1275_INOUT(0, 0)); + args[0] = (unsigned long) svc; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); } /* Reset and reboot the machine with the command 'bcommand'. */ void prom_reboot(const char *bcommand) { + unsigned long args[4]; + #ifdef CONFIG_SUN_LDOMS if (ldom_domaining_enabled) ldom_reboot(bcommand); #endif - p1275_cmd("boot", P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_INOUT(1, 0), bcommand); + args[0] = (unsigned long) "boot"; + args[1] = 1; + args[2] = 0; + args[3] = (unsigned long) bcommand; + + p1275_cmd_direct(args); } /* Forth evaluate the expression contained in 'fstring'. */ void prom_feval(const char *fstring) { + unsigned long args[5]; + if (!fstring || fstring[0] == 0) return; - p1275_cmd("interpret", P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_INOUT(1, 1), fstring); + args[0] = (unsigned long) "interpret"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) fstring; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); } EXPORT_SYMBOL(prom_feval); @@ -68,6 +92,7 @@ extern void smp_release(void); */ void prom_cmdline(void) { + unsigned long args[3]; unsigned long flags; local_irq_save(flags); @@ -76,7 +101,11 @@ void prom_cmdline(void) smp_capture(); #endif - p1275_cmd("enter", P1275_INOUT(0, 0)); + args[0] = (unsigned long) "enter"; + args[1] = 0; + args[2] = 0; + + p1275_cmd_direct(args); #ifdef CONFIG_SMP smp_release(); @@ -90,22 +119,32 @@ void prom_cmdline(void) */ void notrace prom_halt(void) { + unsigned long args[3]; + #ifdef CONFIG_SUN_LDOMS if (ldom_domaining_enabled) ldom_power_off(); #endif again: - p1275_cmd("exit", P1275_INOUT(0, 0)); + args[0] = (unsigned long) "exit"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); goto again; /* PROM is out to get me -DaveM */ } void prom_halt_power_off(void) { + unsigned long args[3]; + #ifdef CONFIG_SUN_LDOMS if (ldom_domaining_enabled) ldom_power_off(); #endif - p1275_cmd("SUNW,power-off", P1275_INOUT(0, 0)); + args[0] = (unsigned long) "SUNW,power-off"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); /* if nothing else helps, we just halt */ prom_halt(); @@ -114,10 +153,15 @@ void prom_halt_power_off(void) /* Set prom sync handler to call function 'funcp'. */ void prom_setcallback(callback_func_t funcp) { + unsigned long args[5]; if (!funcp) return; - p1275_cmd("set-callback", P1275_ARG(0, P1275_ARG_IN_FUNCTION) | - P1275_INOUT(1, 1), funcp); + args[0] = (unsigned long) "set-callback"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) funcp; + args[4] = (unsigned long) -1; + p1275_cmd_direct(args); } /* Get the idprom and stuff it into buffer 'idbuf'. Returns the @@ -173,57 +217,61 @@ static int prom_get_memory_ihandle(void) } /* Load explicit I/D TLB entries. */ +static long tlb_load(const char *type, unsigned long index, + unsigned long tte_data, unsigned long vaddr) +{ + unsigned long args[9]; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 5; + args[2] = 1; + args[3] = (unsigned long) type; + args[4] = (unsigned int) prom_get_mmu_ihandle(); + args[5] = vaddr; + args[6] = tte_data; + args[7] = index; + args[8] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (long) args[8]; +} + long prom_itlb_load(unsigned long index, unsigned long tte_data, unsigned long vaddr) { - return p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(2, P1275_ARG_IN_64B) | - P1275_ARG(3, P1275_ARG_IN_64B) | - P1275_INOUT(5, 1)), - "SUNW,itlb-load", - prom_get_mmu_ihandle(), - /* And then our actual args are pushed backwards. */ - vaddr, - tte_data, - index); + return tlb_load("SUNW,itlb-load", index, tte_data, vaddr); } long prom_dtlb_load(unsigned long index, unsigned long tte_data, unsigned long vaddr) { - return p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(2, P1275_ARG_IN_64B) | - P1275_ARG(3, P1275_ARG_IN_64B) | - P1275_INOUT(5, 1)), - "SUNW,dtlb-load", - prom_get_mmu_ihandle(), - /* And then our actual args are pushed backwards. */ - vaddr, - tte_data, - index); + return tlb_load("SUNW,dtlb-load", index, tte_data, vaddr); } int prom_map(int mode, unsigned long size, unsigned long vaddr, unsigned long paddr) { - int ret = p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(3, P1275_ARG_IN_64B) | - P1275_ARG(4, P1275_ARG_IN_64B) | - P1275_ARG(6, P1275_ARG_IN_64B) | - P1275_INOUT(7, 1)), - prom_map_name, - prom_get_mmu_ihandle(), - mode, - size, - vaddr, - 0, - paddr); - + unsigned long args[11]; + int ret; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 7; + args[2] = 1; + args[3] = (unsigned long) prom_map_name; + args[4] = (unsigned int) prom_get_mmu_ihandle(); + args[5] = (unsigned int) mode; + args[6] = size; + args[7] = vaddr; + args[8] = 0; + args[9] = paddr; + args[10] = (unsigned long) -1; + + p1275_cmd_direct(args); + + ret = (int) args[10]; if (ret == 0) ret = -1; return ret; @@ -231,40 +279,51 @@ int prom_map(int mode, unsigned long size, void prom_unmap(unsigned long size, unsigned long vaddr) { - p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(2, P1275_ARG_IN_64B) | - P1275_ARG(3, P1275_ARG_IN_64B) | - P1275_INOUT(4, 0)), - prom_unmap_name, - prom_get_mmu_ihandle(), - size, - vaddr); + unsigned long args[7]; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 4; + args[2] = 0; + args[3] = (unsigned long) prom_unmap_name; + args[4] = (unsigned int) prom_get_mmu_ihandle(); + args[5] = size; + args[6] = vaddr; + + p1275_cmd_direct(args); } /* Set aside physical memory which is not touched or modified * across soft resets. */ -unsigned long prom_retain(const char *name, - unsigned long pa_low, unsigned long pa_high, - long size, long align) +int prom_retain(const char *name, unsigned long size, + unsigned long align, unsigned long *paddr) { - /* XXX I don't think we return multiple values correctly. - * XXX OBP supposedly returns pa_low/pa_high here, how does - * XXX it work? + unsigned long args[11]; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 5; + args[2] = 3; + args[3] = (unsigned long) "SUNW,retain"; + args[4] = (unsigned int) prom_get_memory_ihandle(); + args[5] = align; + args[6] = size; + args[7] = (unsigned long) name; + args[8] = (unsigned long) -1; + args[9] = (unsigned long) -1; + args[10] = (unsigned long) -1; + + p1275_cmd_direct(args); + + if (args[8]) + return (int) args[8]; + + /* Next we get "phys_high" then "phys_low". On 64-bit + * the phys_high cell is don't care since the phys_low + * cell has the full value. */ + *paddr = args[10]; - /* If align is zero, the pa_low/pa_high args are passed, - * else they are not. - */ - if (align == 0) - return p1275_cmd("SUNW,retain", - (P1275_ARG(0, P1275_ARG_IN_BUF) | P1275_INOUT(5, 2)), - name, pa_low, pa_high, size, align); - else - return p1275_cmd("SUNW,retain", - (P1275_ARG(0, P1275_ARG_IN_BUF) | P1275_INOUT(3, 2)), - name, size, align); + return 0; } /* Get "Unumber" string for the SIMM at the given @@ -277,62 +336,129 @@ int prom_getunumber(int syndrome_code, unsigned long phys_addr, char *buf, int buflen) { - return p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(3, P1275_ARG_OUT_BUF) | - P1275_ARG(6, P1275_ARG_IN_64B) | - P1275_INOUT(8, 2)), - "SUNW,get-unumber", prom_get_memory_ihandle(), - buflen, buf, P1275_SIZE(buflen), - 0, phys_addr, syndrome_code); + unsigned long args[12]; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 7; + args[2] = 2; + args[3] = (unsigned long) "SUNW,get-unumber"; + args[4] = (unsigned int) prom_get_memory_ihandle(); + args[5] = buflen; + args[6] = (unsigned long) buf; + args[7] = 0; + args[8] = phys_addr; + args[9] = (unsigned int) syndrome_code; + args[10] = (unsigned long) -1; + args[11] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[10]; } /* Power management extensions. */ void prom_sleepself(void) { - p1275_cmd("SUNW,sleep-self", P1275_INOUT(0, 0)); + unsigned long args[3]; + + args[0] = (unsigned long) "SUNW,sleep-self"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); } int prom_sleepsystem(void) { - return p1275_cmd("SUNW,sleep-system", P1275_INOUT(0, 1)); + unsigned long args[4]; + + args[0] = (unsigned long) "SUNW,sleep-system"; + args[1] = 0; + args[2] = 1; + args[3] = (unsigned long) -1; + p1275_cmd_direct(args); + + return (int) args[3]; } int prom_wakeupsystem(void) { - return p1275_cmd("SUNW,wakeup-system", P1275_INOUT(0, 1)); + unsigned long args[4]; + + args[0] = (unsigned long) "SUNW,wakeup-system"; + args[1] = 0; + args[2] = 1; + args[3] = (unsigned long) -1; + p1275_cmd_direct(args); + + return (int) args[3]; } #ifdef CONFIG_SMP void prom_startcpu(int cpunode, unsigned long pc, unsigned long arg) { - p1275_cmd("SUNW,start-cpu", P1275_INOUT(3, 0), cpunode, pc, arg); + unsigned long args[6]; + + args[0] = (unsigned long) "SUNW,start-cpu"; + args[1] = 3; + args[2] = 0; + args[3] = (unsigned int) cpunode; + args[4] = pc; + args[5] = arg; + p1275_cmd_direct(args); } void prom_startcpu_cpuid(int cpuid, unsigned long pc, unsigned long arg) { - p1275_cmd("SUNW,start-cpu-by-cpuid", P1275_INOUT(3, 0), - cpuid, pc, arg); + unsigned long args[6]; + + args[0] = (unsigned long) "SUNW,start-cpu-by-cpuid"; + args[1] = 3; + args[2] = 0; + args[3] = (unsigned int) cpuid; + args[4] = pc; + args[5] = arg; + p1275_cmd_direct(args); } void prom_stopcpu_cpuid(int cpuid) { - p1275_cmd("SUNW,stop-cpu-by-cpuid", P1275_INOUT(1, 0), - cpuid); + unsigned long args[4]; + + args[0] = (unsigned long) "SUNW,stop-cpu-by-cpuid"; + args[1] = 1; + args[2] = 0; + args[3] = (unsigned int) cpuid; + p1275_cmd_direct(args); } void prom_stopself(void) { - p1275_cmd("SUNW,stop-self", P1275_INOUT(0, 0)); + unsigned long args[3]; + + args[0] = (unsigned long) "SUNW,stop-self"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); } void prom_idleself(void) { - p1275_cmd("SUNW,idle-self", P1275_INOUT(0, 0)); + unsigned long args[3]; + + args[0] = (unsigned long) "SUNW,idle-self"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); } void prom_resumecpu(int cpunode) { - p1275_cmd("SUNW,resume-cpu", P1275_INOUT(1, 0), cpunode); + unsigned long args[4]; + + args[0] = (unsigned long) "SUNW,resume-cpu"; + args[1] = 1; + args[2] = 0; + args[3] = (unsigned int) cpunode; + p1275_cmd_direct(args); } #endif diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c index 2d8b70d..fa6e4e2 100644 --- a/arch/sparc/prom/p1275.c +++ b/arch/sparc/prom/p1275.c @@ -22,13 +22,11 @@ struct { long prom_callback; /* 0x00 */ void (*prom_cif_handler)(long *); /* 0x08 */ unsigned long prom_cif_stack; /* 0x10 */ - unsigned long prom_args [23]; /* 0x18 */ - char prom_buffer [3000]; } p1275buf; extern void prom_world(int); -extern void prom_cif_interface(void); +extern void prom_cif_direct(unsigned long *args); extern void prom_cif_callback(void); /* @@ -36,114 +34,20 @@ extern void prom_cif_callback(void); */ DEFINE_RAW_SPINLOCK(prom_entry_lock); -long p1275_cmd(const char *service, long fmt, ...) +void p1275_cmd_direct(unsigned long *args) { - char *p, *q; unsigned long flags; - int nargs, nrets, i; - va_list list; - long attrs, x; - - p = p1275buf.prom_buffer; raw_local_save_flags(flags); raw_local_irq_restore(PIL_NMI); raw_spin_lock(&prom_entry_lock); - p1275buf.prom_args[0] = (unsigned long)p; /* service */ - strcpy (p, service); - p = (char *)(((long)(strchr (p, 0) + 8)) & ~7); - p1275buf.prom_args[1] = nargs = (fmt & 0x0f); /* nargs */ - p1275buf.prom_args[2] = nrets = ((fmt & 0xf0) >> 4); /* nrets */ - attrs = fmt >> 8; - va_start(list, fmt); - for (i = 0; i < nargs; i++, attrs >>= 3) { - switch (attrs & 0x7) { - case P1275_ARG_NUMBER: - p1275buf.prom_args[i + 3] = - (unsigned)va_arg(list, long); - break; - case P1275_ARG_IN_64B: - p1275buf.prom_args[i + 3] = - va_arg(list, unsigned long); - break; - case P1275_ARG_IN_STRING: - strcpy (p, va_arg(list, char *)); - p1275buf.prom_args[i + 3] = (unsigned long)p; - p = (char *)(((long)(strchr (p, 0) + 8)) & ~7); - break; - case P1275_ARG_OUT_BUF: - (void) va_arg(list, char *); - p1275buf.prom_args[i + 3] = (unsigned long)p; - x = va_arg(list, long); - i++; attrs >>= 3; - p = (char *)(((long)(p + (int)x + 7)) & ~7); - p1275buf.prom_args[i + 3] = x; - break; - case P1275_ARG_IN_BUF: - q = va_arg(list, char *); - p1275buf.prom_args[i + 3] = (unsigned long)p; - x = va_arg(list, long); - i++; attrs >>= 3; - memcpy (p, q, (int)x); - p = (char *)(((long)(p + (int)x + 7)) & ~7); - p1275buf.prom_args[i + 3] = x; - break; - case P1275_ARG_OUT_32B: - (void) va_arg(list, char *); - p1275buf.prom_args[i + 3] = (unsigned long)p; - p += 32; - break; - case P1275_ARG_IN_FUNCTION: - p1275buf.prom_args[i + 3] = - (unsigned long)prom_cif_callback; - p1275buf.prom_callback = va_arg(list, long); - break; - } - } - va_end(list); - prom_world(1); - prom_cif_interface(); + prom_cif_direct(args); prom_world(0); - attrs = fmt >> 8; - va_start(list, fmt); - for (i = 0; i < nargs; i++, attrs >>= 3) { - switch (attrs & 0x7) { - case P1275_ARG_NUMBER: - (void) va_arg(list, long); - break; - case P1275_ARG_IN_STRING: - (void) va_arg(list, char *); - break; - case P1275_ARG_IN_FUNCTION: - (void) va_arg(list, long); - break; - case P1275_ARG_IN_BUF: - (void) va_arg(list, char *); - (void) va_arg(list, long); - i++; attrs >>= 3; - break; - case P1275_ARG_OUT_BUF: - p = va_arg(list, char *); - x = va_arg(list, long); - memcpy (p, (char *)(p1275buf.prom_args[i + 3]), (int)x); - i++; attrs >>= 3; - break; - case P1275_ARG_OUT_32B: - p = va_arg(list, char *); - memcpy (p, (char *)(p1275buf.prom_args[i + 3]), 32); - break; - } - } - va_end(list); - x = p1275buf.prom_args [nargs + 3]; - raw_spin_unlock(&prom_entry_lock); raw_local_irq_restore(flags); - - return x; } void prom_cif_init(void *cif_handler, void *cif_stack) diff --git a/arch/sparc/prom/tree_64.c b/arch/sparc/prom/tree_64.c index 3c0d2dd..9d3f913 100644 --- a/arch/sparc/prom/tree_64.c +++ b/arch/sparc/prom/tree_64.c @@ -16,22 +16,39 @@ #include #include +static int prom_node_to_node(const char *type, int node) +{ + unsigned long args[5]; + + args[0] = (unsigned long) type; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[4]; +} + /* Return the child of node 'node' or zero if no this node has no * direct descendent. */ inline int __prom_getchild(int node) { - return p1275_cmd ("child", P1275_INOUT(1, 1), node); + return prom_node_to_node("child", node); } inline int prom_getchild(int node) { int cnode; - if(node == -1) return 0; + if (node == -1) + return 0; cnode = __prom_getchild(node); - if(cnode == -1) return 0; - return (int)cnode; + if (cnode == -1) + return 0; + return cnode; } EXPORT_SYMBOL(prom_getchild); @@ -39,10 +56,12 @@ inline int prom_getparent(int node) { int cnode; - if(node == -1) return 0; - cnode = p1275_cmd ("parent", P1275_INOUT(1, 1), node); - if(cnode == -1) return 0; - return (int)cnode; + if (node == -1) + return 0; + cnode = prom_node_to_node("parent", node); + if (cnode == -1) + return 0; + return cnode; } /* Return the next sibling of node 'node' or zero if no more siblings @@ -50,7 +69,7 @@ inline int prom_getparent(int node) */ inline int __prom_getsibling(int node) { - return p1275_cmd(prom_peer_name, P1275_INOUT(1, 1), node); + return prom_node_to_node(prom_peer_name, node); } inline int prom_getsibling(int node) @@ -72,11 +91,21 @@ EXPORT_SYMBOL(prom_getsibling); */ inline int prom_getproplen(int node, const char *prop) { - if((!node) || (!prop)) return -1; - return p1275_cmd ("getproplen", - P1275_ARG(1,P1275_ARG_IN_STRING)| - P1275_INOUT(2, 1), - node, prop); + unsigned long args[6]; + + if (!node || !prop) + return -1; + + args[0] = (unsigned long) "getproplen"; + args[1] = 2; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) prop; + args[5] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[5]; } EXPORT_SYMBOL(prom_getproplen); @@ -87,19 +116,25 @@ EXPORT_SYMBOL(prom_getproplen); inline int prom_getproperty(int node, const char *prop, char *buffer, int bufsize) { + unsigned long args[8]; int plen; plen = prom_getproplen(node, prop); - if ((plen > bufsize) || (plen == 0) || (plen == -1)) { + if ((plen > bufsize) || (plen == 0) || (plen == -1)) return -1; - } else { - /* Ok, things seem all right. */ - return p1275_cmd(prom_getprop_name, - P1275_ARG(1,P1275_ARG_IN_STRING)| - P1275_ARG(2,P1275_ARG_OUT_BUF)| - P1275_INOUT(4, 1), - node, prop, buffer, P1275_SIZE(plen)); - } + + args[0] = (unsigned long) prom_getprop_name; + args[1] = 4; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) prop; + args[5] = (unsigned long) buffer; + args[6] = bufsize; + args[7] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[7]; } EXPORT_SYMBOL(prom_getproperty); @@ -110,7 +145,7 @@ inline int prom_getint(int node, const char *prop) { int intprop; - if(prom_getproperty(node, prop, (char *) &intprop, sizeof(int)) != -1) + if (prom_getproperty(node, prop, (char *) &intprop, sizeof(int)) != -1) return intprop; return -1; @@ -126,7 +161,8 @@ int prom_getintdefault(int node, const char *property, int deflt) int retval; retval = prom_getint(node, property); - if(retval == -1) return deflt; + if (retval == -1) + return deflt; return retval; } @@ -138,7 +174,8 @@ int prom_getbool(int node, const char *prop) int retval; retval = prom_getproplen(node, prop); - if(retval == -1) return 0; + if (retval == -1) + return 0; return 1; } EXPORT_SYMBOL(prom_getbool); @@ -152,7 +189,8 @@ void prom_getstring(int node, const char *prop, char *user_buf, int ubuf_size) int len; len = prom_getproperty(node, prop, user_buf, ubuf_size); - if(len != -1) return; + if (len != -1) + return; user_buf[0] = 0; } EXPORT_SYMBOL(prom_getstring); @@ -164,7 +202,8 @@ int prom_nodematch(int node, const char *name) { char namebuf[128]; prom_getproperty(node, "name", namebuf, sizeof(namebuf)); - if(strcmp(namebuf, name) == 0) return 1; + if (strcmp(namebuf, name) == 0) + return 1; return 0; } @@ -190,16 +229,29 @@ int prom_searchsiblings(int node_start, const char *nodename) } EXPORT_SYMBOL(prom_searchsiblings); +static const char *prom_nextprop_name = "nextprop"; + /* Return the first property type for node 'node'. * buffer should be at least 32B in length */ inline char *prom_firstprop(int node, char *buffer) { + unsigned long args[7]; + *buffer = 0; - if(node == -1) return buffer; - p1275_cmd ("nextprop", P1275_ARG(2,P1275_ARG_OUT_32B)| - P1275_INOUT(3, 0), - node, (char *) 0x0, buffer); + if (node == -1) + return buffer; + + args[0] = (unsigned long) prom_nextprop_name; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = 0; + args[5] = (unsigned long) buffer; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + return buffer; } EXPORT_SYMBOL(prom_firstprop); @@ -210,9 +262,10 @@ EXPORT_SYMBOL(prom_firstprop); */ inline char *prom_nextprop(int node, const char *oprop, char *buffer) { + unsigned long args[7]; char buf[32]; - if(node == -1) { + if (node == -1) { *buffer = 0; return buffer; } @@ -220,10 +273,17 @@ inline char *prom_nextprop(int node, const char *oprop, char *buffer) strcpy (buf, oprop); oprop = buf; } - p1275_cmd ("nextprop", P1275_ARG(1,P1275_ARG_IN_STRING)| - P1275_ARG(2,P1275_ARG_OUT_32B)| - P1275_INOUT(3, 0), - node, oprop, buffer); + + args[0] = (unsigned long) prom_nextprop_name; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) oprop; + args[5] = (unsigned long) buffer; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + return buffer; } EXPORT_SYMBOL(prom_nextprop); @@ -231,12 +291,19 @@ EXPORT_SYMBOL(prom_nextprop); int prom_finddevice(const char *name) { + unsigned long args[5]; + if (!name) return 0; - return p1275_cmd(prom_finddev_name, - P1275_ARG(0,P1275_ARG_IN_STRING)| - P1275_INOUT(1, 1), - name); + args[0] = (unsigned long) "finddevice"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) name; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[4]; } EXPORT_SYMBOL(prom_finddevice); @@ -247,7 +314,7 @@ int prom_node_has_property(int node, const char *prop) *buf = 0; do { prom_nextprop(node, buf, buf); - if(!strcmp(buf, prop)) + if (!strcmp(buf, prop)) return 1; } while (*buf); return 0; @@ -260,6 +327,8 @@ EXPORT_SYMBOL(prom_node_has_property); int prom_setprop(int node, const char *pname, char *value, int size) { + unsigned long args[8]; + if (size == 0) return 0; if ((pname == 0) || (value == 0)) @@ -271,19 +340,37 @@ prom_setprop(int node, const char *pname, char *value, int size) return 0; } #endif - return p1275_cmd ("setprop", P1275_ARG(1,P1275_ARG_IN_STRING)| - P1275_ARG(2,P1275_ARG_IN_BUF)| - P1275_INOUT(4, 1), - node, pname, value, P1275_SIZE(size)); + args[0] = (unsigned long) "setprop"; + args[1] = 4; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) pname; + args[5] = (unsigned long) value; + args[6] = size; + args[7] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[7]; } EXPORT_SYMBOL(prom_setprop); inline int prom_inst2pkg(int inst) { + unsigned long args[5]; int node; - node = p1275_cmd ("instance-to-package", P1275_INOUT(1, 1), inst); - if (node == -1) return 0; + args[0] = (unsigned long) "instance-to-package"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned int) inst; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + node = (int) args[4]; + if (node == -1) + return 0; return node; } @@ -296,17 +383,28 @@ prom_pathtoinode(const char *path) int node, inst; inst = prom_devopen (path); - if (inst == 0) return 0; - node = prom_inst2pkg (inst); - prom_devclose (inst); - if (node == -1) return 0; + if (inst == 0) + return 0; + node = prom_inst2pkg(inst); + prom_devclose(inst); + if (node == -1) + return 0; return node; } int prom_ihandle2path(int handle, char *buffer, int bufsize) { - return p1275_cmd("instance-to-path", - P1275_ARG(1,P1275_ARG_OUT_BUF)| - P1275_INOUT(3, 1), - handle, buffer, P1275_SIZE(bufsize)); + unsigned long args[7]; + + args[0] = (unsigned long) "instance-to-path"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) handle; + args[4] = (unsigned long) buffer; + args[5] = bufsize; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[6]; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5ac0bb4..715a7fa 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -345,10 +345,10 @@ static u32 group_table[] = { DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, 0, 0, 0, 0, [Group4*8] = - ByteOp | DstMem | SrcNone | ModRM, ByteOp | DstMem | SrcNone | ModRM, + ByteOp | DstMem | SrcNone | ModRM | Lock, ByteOp | DstMem | SrcNone | ModRM | Lock, 0, 0, 0, 0, 0, 0, [Group5*8] = - DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, + DstMem | SrcNone | ModRM | Lock, DstMem | SrcNone | ModRM | Lock, SrcMem | ModRM | Stack, 0, SrcMem | ModRM | Stack, SrcMem | ModRM | Src2Mem16 | ImplicitOps, SrcMem | ModRM | Stack, 0, diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index b1ed0a1..92b6ca4 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -799,8 +799,12 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, ret = handler(kvm, &memslot->rmap[gfn_offset], data); for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) { - int idx = gfn_offset; - idx /= KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL + j); + unsigned long idx; + int nr; + + nr = KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL+j); + idx = (memslot->base_gfn+gfn_offset) / nr - + memslot->base_gfn / nr; ret |= handler(kvm, &memslot->lpage_info[j][idx].rmap_pde, data); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 2331bdc..e34452b 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -324,8 +324,32 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, break; } - if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) - continue; + if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) { + struct kvm_mmu_page *child; + unsigned direct_access; + + if (level != gw->level) + continue; + + /* + * For the direct sp, if the guest pte's dirty bit + * changed form clean to dirty, it will corrupt the + * sp's access: allow writable in the read-only sp, + * so we should update the spte at this point to get + * a new sp with the correct access. + */ + direct_access = gw->pt_access & gw->pte_access; + if (!is_dirty_gpte(gw->ptes[gw->level - 1])) + direct_access &= ~ACC_WRITE_MASK; + + child = page_header(*sptep & PT64_BASE_ADDR_MASK); + if (child->role.access == direct_access) + continue; + + mmu_page_remove_parent_pte(child, sptep); + __set_spte(sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); + } if (is_large_pte(*sptep)) { rmap_remove(vcpu->kvm, sptep); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ee03679..7d04388 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -177,6 +177,7 @@ static u64 construct_eptp(unsigned long root_hpa); static DEFINE_PER_CPU(struct vmcs *, vmxarea); static DEFINE_PER_CPU(struct vmcs *, current_vmcs); static DEFINE_PER_CPU(struct list_head, vcpus_on_cpu); +static DEFINE_PER_CPU(struct desc_ptr, host_gdt); static unsigned long *vmx_io_bitmap_a; static unsigned long *vmx_io_bitmap_b; @@ -812,6 +813,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); } #endif + load_gdt(&__get_cpu_var(host_gdt)); } static void vmx_load_host_state(struct vcpu_vmx *vmx) @@ -1314,6 +1316,8 @@ static int hardware_enable(void *garbage) ept_sync_global(); + store_gdt(&__get_cpu_var(host_gdt)); + return 0; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7fa89c3..fd22688 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5438,6 +5438,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, int user_alloc) { int npages = memslot->npages; + int map_flags = MAP_PRIVATE | MAP_ANONYMOUS; + + /* Prevent internal slot pages from being moved by fork()/COW. */ + if (memslot->id >= KVM_MEMORY_SLOTS) + map_flags = MAP_SHARED | MAP_ANONYMOUS; /*To keep backward compatibility with older userspace, *x86 needs to hanlde !user_alloc case. @@ -5450,7 +5455,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, userspace_addr = do_mmap(NULL, 0, npages * PAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS, + map_flags, 0); up_write(¤t->mm->mmap_sem); diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index 78ee8e0..2cda60a 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -26,35 +26,37 @@ .endm #define BEGIN(op) \ -.macro END; \ +.macro endp; \ CFI_ENDPROC; \ ENDPROC(atomic64_##op##_386); \ -.purgem END; \ +.purgem endp; \ .endm; \ ENTRY(atomic64_##op##_386); \ CFI_STARTPROC; \ LOCK v; +#define ENDP endp + #define RET \ UNLOCK v; \ ret -#define RET_END \ +#define RET_ENDP \ RET; \ - END + ENDP #define v %ecx BEGIN(read) movl (v), %eax movl 4(v), %edx -RET_END +RET_ENDP #undef v #define v %esi BEGIN(set) movl %ebx, (v) movl %ecx, 4(v) -RET_END +RET_ENDP #undef v #define v %esi @@ -63,14 +65,14 @@ BEGIN(xchg) movl 4(v), %edx movl %ebx, (v) movl %ecx, 4(v) -RET_END +RET_ENDP #undef v #define v %ecx BEGIN(add) addl %eax, (v) adcl %edx, 4(v) -RET_END +RET_ENDP #undef v #define v %ecx @@ -79,14 +81,14 @@ BEGIN(add_return) adcl 4(v), %edx movl %eax, (v) movl %edx, 4(v) -RET_END +RET_ENDP #undef v #define v %ecx BEGIN(sub) subl %eax, (v) sbbl %edx, 4(v) -RET_END +RET_ENDP #undef v #define v %ecx @@ -98,14 +100,14 @@ BEGIN(sub_return) adcl 4(v), %edx movl %eax, (v) movl %edx, 4(v) -RET_END +RET_ENDP #undef v #define v %esi BEGIN(inc) addl $1, (v) adcl $0, 4(v) -RET_END +RET_ENDP #undef v #define v %esi @@ -116,14 +118,14 @@ BEGIN(inc_return) adcl $0, %edx movl %eax, (v) movl %edx, 4(v) -RET_END +RET_ENDP #undef v #define v %esi BEGIN(dec) subl $1, (v) sbbl $0, 4(v) -RET_END +RET_ENDP #undef v #define v %esi @@ -134,7 +136,7 @@ BEGIN(dec_return) sbbl $0, %edx movl %eax, (v) movl %edx, 4(v) -RET_END +RET_ENDP #undef v #define v %ecx @@ -156,7 +158,7 @@ BEGIN(add_unless) jne 1b xorl %eax, %eax jmp 2b -END +ENDP #undef v #define v %esi @@ -177,7 +179,7 @@ BEGIN(inc_not_zero) testl %edx, %edx jne 1b jmp 2b -END +ENDP #undef v #define v %esi @@ -190,5 +192,5 @@ BEGIN(dec_if_positive) movl %eax, (v) movl %edx, 4(v) 1: -RET_END +RET_ENDP #undef v diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index cfe4faa..009b819 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -671,7 +671,9 @@ static int __init ppro_init(char **cpu_type) case 14: *cpu_type = "i386/core"; break; - case 15: case 23: + case 0x0f: + case 0x16: + case 0x17: *cpu_type = "i386/core_2"; break; case 0x1a: diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 941fcb8..cb1cedc 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -59,6 +59,7 @@ void device_pm_init(struct device *dev) { dev->power.status = DPM_ON; init_completion(&dev->power.completion); + complete_all(&dev->power.completion); pm_runtime_init(dev); } diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index d836a71..adc0f89 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -805,6 +805,8 @@ static const struct intel_driver_description { "G45/G43", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_B43_HB, PCI_DEVICE_ID_INTEL_B43_IG, "B43", NULL, &intel_i965_driver }, + { PCI_DEVICE_ID_INTEL_B43_1_HB, PCI_DEVICE_ID_INTEL_B43_1_IG, + "B43", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_G41_HB, PCI_DEVICE_ID_INTEL_G41_IG, "G41", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_IRONLAKE_D_HB, PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG, @@ -815,17 +817,27 @@ static const struct intel_driver_description { "HD Graphics", NULL, &intel_i965_driver }, { PCI_DEVICE_ID_INTEL_IRONLAKE_MC2_HB, PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG, "HD Graphics", NULL, &intel_i965_driver }, - { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_IG, - "Sandybridge", NULL, &intel_i965_driver }, - { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_IG, - "Sandybridge", NULL, &intel_i965_driver }, + { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT1_IG, + "Sandybridge", NULL, &intel_gen6_driver }, + { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT2_IG, + "Sandybridge", NULL, &intel_gen6_driver }, + { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT2_PLUS_IG, + "Sandybridge", NULL, &intel_gen6_driver }, + { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT1_IG, + "Sandybridge", NULL, &intel_gen6_driver }, + { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT2_IG, + "Sandybridge", NULL, &intel_gen6_driver }, + { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT2_PLUS_IG, + "Sandybridge", NULL, &intel_gen6_driver }, + { PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_HB, PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_IG, + "Sandybridge", NULL, &intel_gen6_driver }, { 0, 0, NULL, NULL, NULL } }; static int __devinit intel_gmch_probe(struct pci_dev *pdev, struct agp_bridge_data *bridge) { - int i; + int i, mask; bridge->driver = NULL; for (i = 0; intel_agp_chipsets[i].name != NULL; i++) { @@ -845,14 +857,19 @@ static int __devinit intel_gmch_probe(struct pci_dev *pdev, dev_info(&pdev->dev, "Intel %s Chipset\n", intel_agp_chipsets[i].name); - if (bridge->driver->mask_memory == intel_i965_mask_memory) { - if (pci_set_dma_mask(intel_private.pcidev, DMA_BIT_MASK(36))) - dev_err(&intel_private.pcidev->dev, - "set gfx device dma mask 36bit failed!\n"); - else - pci_set_consistent_dma_mask(intel_private.pcidev, - DMA_BIT_MASK(36)); - } + if (bridge->driver->mask_memory == intel_gen6_mask_memory) + mask = 40; + else if (bridge->driver->mask_memory == intel_i965_mask_memory) + mask = 36; + else + mask = 32; + + if (pci_set_dma_mask(intel_private.pcidev, DMA_BIT_MASK(mask))) + dev_err(&intel_private.pcidev->dev, + "set gfx device dma mask %d-bit failed!\n", mask); + else + pci_set_consistent_dma_mask(intel_private.pcidev, + DMA_BIT_MASK(mask)); return 1; } @@ -1036,6 +1053,7 @@ static struct pci_device_id agp_intel_pci_table[] = { ID(PCI_DEVICE_ID_INTEL_IRONLAKE_MC2_HB), ID(PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB), ID(PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB), + ID(PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_HB), { } }; diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h index 2547465..bc9a4ad 100644 --- a/drivers/char/agp/intel-agp.h +++ b/drivers/char/agp/intel-agp.h @@ -178,6 +178,8 @@ #define PCI_DEVICE_ID_INTEL_Q33_IG 0x29D2 #define PCI_DEVICE_ID_INTEL_B43_HB 0x2E40 #define PCI_DEVICE_ID_INTEL_B43_IG 0x2E42 +#define PCI_DEVICE_ID_INTEL_B43_1_HB 0x2E90 +#define PCI_DEVICE_ID_INTEL_B43_1_IG 0x2E92 #define PCI_DEVICE_ID_INTEL_GM45_HB 0x2A40 #define PCI_DEVICE_ID_INTEL_GM45_IG 0x2A42 #define PCI_DEVICE_ID_INTEL_EAGLELAKE_HB 0x2E00 @@ -194,10 +196,16 @@ #define PCI_DEVICE_ID_INTEL_IRONLAKE_MA_HB 0x0062 #define PCI_DEVICE_ID_INTEL_IRONLAKE_MC2_HB 0x006a #define PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG 0x0046 -#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB 0x0100 -#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_IG 0x0102 -#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB 0x0104 -#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_IG 0x0106 +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB 0x0100 /* Desktop */ +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT1_IG 0x0102 +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT2_IG 0x0112 +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_GT2_PLUS_IG 0x0122 +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB 0x0104 /* Mobile */ +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT1_IG 0x0106 +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT2_IG 0x0116 +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_GT2_PLUS_IG 0x0126 +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_HB 0x0108 /* Server */ +#define PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_IG 0x010A /* cover 915 and 945 variants */ #define IS_I915 (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_E7221_HB || \ @@ -224,7 +232,8 @@ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_PINEVIEW_HB) #define IS_SNB (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB || \ - agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB) + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB || \ + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_HB) #define IS_G4X (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_EAGLELAKE_HB || \ agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_Q45_HB || \ diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c index ea6997e..ed11c77 100644 --- a/drivers/char/agp/intel-gtt.c +++ b/drivers/char/agp/intel-gtt.c @@ -585,8 +585,7 @@ static void intel_i830_init_gtt_entries(void) gtt_entries = 0; break; } - } else if (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB || - agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB) { + } else if (IS_SNB) { /* * SandyBridge has new memory control reg at 0x50.w */ @@ -1318,6 +1317,16 @@ static unsigned long intel_i965_mask_memory(struct agp_bridge_data *bridge, return addr | bridge->driver->masks[type].mask; } +static unsigned long intel_gen6_mask_memory(struct agp_bridge_data *bridge, + dma_addr_t addr, int type) +{ + /* gen6 has bit11-4 for physical addr bit39-32 */ + addr |= (addr >> 28) & 0xff0; + + /* Type checking must be done elsewhere */ + return addr | bridge->driver->masks[type].mask; +} + static void intel_i965_get_gtt_range(int *gtt_offset, int *gtt_size) { u16 snb_gmch_ctl; @@ -1337,6 +1346,7 @@ static void intel_i965_get_gtt_range(int *gtt_offset, int *gtt_size) break; case PCI_DEVICE_ID_INTEL_SANDYBRIDGE_HB: case PCI_DEVICE_ID_INTEL_SANDYBRIDGE_M_HB: + case PCI_DEVICE_ID_INTEL_SANDYBRIDGE_S_HB: *gtt_offset = MB(2); pci_read_config_word(intel_private.pcidev, SNB_GMCH_CTRL, &snb_gmch_ctl); @@ -1526,6 +1536,39 @@ static const struct agp_bridge_driver intel_i965_driver = { #endif }; +static const struct agp_bridge_driver intel_gen6_driver = { + .owner = THIS_MODULE, + .aperture_sizes = intel_i830_sizes, + .size_type = FIXED_APER_SIZE, + .num_aperture_sizes = 4, + .needs_scratch_page = true, + .configure = intel_i9xx_configure, + .fetch_size = intel_i9xx_fetch_size, + .cleanup = intel_i915_cleanup, + .mask_memory = intel_gen6_mask_memory, + .masks = intel_i810_masks, + .agp_enable = intel_i810_agp_enable, + .cache_flush = global_cache_flush, + .create_gatt_table = intel_i965_create_gatt_table, + .free_gatt_table = intel_i830_free_gatt_table, + .insert_memory = intel_i915_insert_entries, + .remove_memory = intel_i915_remove_entries, + .alloc_by_type = intel_i830_alloc_by_type, + .free_by_type = intel_i810_free_by_type, + .agp_alloc_page = agp_generic_alloc_page, + .agp_alloc_pages = agp_generic_alloc_pages, + .agp_destroy_page = agp_generic_destroy_page, + .agp_destroy_pages = agp_generic_destroy_pages, + .agp_type_to_mask_type = intel_i830_type_to_mask_type, + .chipset_flush = intel_i915_chipset_flush, +#ifdef USE_PCI_DMA_API + .agp_map_page = intel_agp_map_page, + .agp_unmap_page = intel_agp_unmap_page, + .agp_map_memory = intel_agp_map_memory, + .agp_unmap_memory = intel_agp_unmap_memory, +#endif +}; + static const struct agp_bridge_driver intel_g33_driver = { .owner = THIS_MODULE, .aperture_sizes = intel_i830_sizes, diff --git a/drivers/char/mem.c b/drivers/char/mem.c index a398ecd..1f528fa 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -788,10 +788,11 @@ static const struct file_operations zero_fops = { /* * capabilities for /dev/zero * - permits private mappings, "copies" are taken of the source of zeros + * - no writeback happens */ static struct backing_dev_info zero_bdi = { .name = "char/mem", - .capabilities = BDI_CAP_MAP_COPY, + .capabilities = BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK, }; static const struct file_operations full_fops = { diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 942a982..c810481 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -596,6 +596,10 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf, ssize_t ret; bool nonblock; + /* Userspace could be out to fool us */ + if (!count) + return 0; + port = filp->private_data; nonblock = filp->f_flags & O_NONBLOCK; @@ -642,7 +646,7 @@ static unsigned int port_fops_poll(struct file *filp, poll_table *wait) poll_wait(filp, &port->waitqueue, wait); ret = 0; - if (port->inbuf) + if (!will_read_block(port)) ret |= POLLIN | POLLRDNORM; if (!will_write_block(port)) ret |= POLLOUT; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 423dc90..194e0c4 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -175,12 +175,18 @@ static const struct pci_device_id pciidlist[] = { INTEL_VGA_DEVICE(0x2e22, &intel_g45_info), INTEL_VGA_DEVICE(0x2e32, &intel_g45_info), INTEL_VGA_DEVICE(0x2e42, &intel_g45_info), + INTEL_VGA_DEVICE(0x2e92, &intel_g45_info), /* B43_G.1 */ INTEL_VGA_DEVICE(0xa001, &intel_pineview_info), INTEL_VGA_DEVICE(0xa011, &intel_pineview_info), INTEL_VGA_DEVICE(0x0042, &intel_ironlake_d_info), INTEL_VGA_DEVICE(0x0046, &intel_ironlake_m_info), INTEL_VGA_DEVICE(0x0102, &intel_sandybridge_d_info), + INTEL_VGA_DEVICE(0x0112, &intel_sandybridge_d_info), + INTEL_VGA_DEVICE(0x0122, &intel_sandybridge_d_info), INTEL_VGA_DEVICE(0x0106, &intel_sandybridge_m_info), + INTEL_VGA_DEVICE(0x0116, &intel_sandybridge_m_info), + INTEL_VGA_DEVICE(0x0126, &intel_sandybridge_m_info), + INTEL_VGA_DEVICE(0x010A, &intel_sandybridge_d_info), {0, 0, 0} }; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index ac38e46..d1c1243 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2376,11 +2376,19 @@ static bool intel_crtc_mode_fixup(struct drm_crtc *crtc, struct drm_display_mode *adjusted_mode) { struct drm_device *dev = crtc->dev; + if (HAS_PCH_SPLIT(dev)) { /* FDI link clock is fixed at 2.7G */ if (mode->clock * 3 > 27000 * 4) return MODE_CLOCK_HIGH; } + + /* XXX some encoders set the crtcinfo, others don't. + * Obviously we need some form of conflict resolution here... + */ + if (adjusted_mode->crtc_htotal == 0) + drm_mode_set_crtcinfo(adjusted_mode, 0); + return true; } diff --git a/drivers/gpu/drm/nouveau/nv50_instmem.c b/drivers/gpu/drm/nouveau/nv50_instmem.c index 5f21df3..3fcae54 100644 --- a/drivers/gpu/drm/nouveau/nv50_instmem.c +++ b/drivers/gpu/drm/nouveau/nv50_instmem.c @@ -141,6 +141,8 @@ nv50_instmem_init(struct drm_device *dev) chan->file_priv = (struct drm_file *)-2; dev_priv->fifos[0] = dev_priv->fifos[127] = chan; + INIT_LIST_HEAD(&chan->ramht_refs); + /* Channel's PRAMIN object + heap */ ret = nouveau_gpuobj_new_fake(dev, 0, c_offset, c_size, 0, NULL, &chan->ramin); diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c index 5c53624..407cb84 100644 --- a/drivers/message/fusion/mptscsih.c +++ b/drivers/message/fusion/mptscsih.c @@ -2459,6 +2459,8 @@ mptscsih_slave_configure(struct scsi_device *sdev) ioc->name,sdev->tagged_supported, sdev->simple_tags, sdev->ordered_tags)); + blk_queue_dma_alignment (sdev->request_queue, 512 - 1); + return 0; } diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 822f586..0ddf4c6 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -2466,6 +2466,9 @@ int bond_3ad_lacpdu_recv(struct sk_buff *skb, struct net_device *dev, struct pac if (!(dev->flags & IFF_MASTER)) goto out; + if (!pskb_may_pull(skb, sizeof(struct lacpdu))) + goto out; + read_lock(&bond->lock); slave = bond_get_slave_by_dev((struct bonding *)netdev_priv(dev), orig_dev); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 8d7dfd2..0cb1ded 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -369,6 +369,9 @@ static int rlb_arp_recv(struct sk_buff *skb, struct net_device *bond_dev, struct goto out; } + if (!pskb_may_pull(skb, arp_hdr_len(bond_dev))) + goto out; + if (skb->len < sizeof(struct arp_pkt)) { pr_debug("Packet is too small to be an ARP\n"); goto out; diff --git a/drivers/net/cxgb3/cxgb3_main.c b/drivers/net/cxgb3/cxgb3_main.c index e3f1b85..3e0f19f 100644 --- a/drivers/net/cxgb3/cxgb3_main.c +++ b/drivers/net/cxgb3/cxgb3_main.c @@ -2296,6 +2296,8 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr) case CHELSIO_GET_QSET_NUM:{ struct ch_reg edata; + memset(&edata, 0, sizeof(struct ch_reg)); + edata.cmd = CHELSIO_GET_QSET_NUM; edata.val = pi->nqsets; if (copy_to_user(useraddr, &edata, sizeof(edata))) diff --git a/drivers/net/eql.c b/drivers/net/eql.c index dda2c79..0cb1cf9 100644 --- a/drivers/net/eql.c +++ b/drivers/net/eql.c @@ -555,6 +555,8 @@ static int eql_g_master_cfg(struct net_device *dev, master_config_t __user *mcp) equalizer_t *eql; master_config_t mc; + memset(&mc, 0, sizeof(master_config_t)); + if (eql_is_master(dev)) { eql = netdev_priv(dev); mc.max_slaves = eql->max_slaves; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 4dd2351..e254274 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1653,6 +1653,8 @@ static int hso_get_count(struct hso_serial *serial, struct uart_icount cnow; struct hso_tiocmget *tiocmget = serial->tiocmget; + memset(&icount, 0, sizeof(struct serial_icounter_struct)); + if (!tiocmget) return -ENOENT; spin_lock_irq(&serial->serial_lock); diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index 435fbbc..8e499e8 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -71,6 +71,49 @@ #define DMA_32BIT_PFN IOVA_PFN(DMA_BIT_MASK(32)) #define DMA_64BIT_PFN IOVA_PFN(DMA_BIT_MASK(64)) +/* page table handling */ +#define LEVEL_STRIDE (9) +#define LEVEL_MASK (((u64)1 << LEVEL_STRIDE) - 1) + +static inline int agaw_to_level(int agaw) +{ + return agaw + 2; +} + +static inline int agaw_to_width(int agaw) +{ + return 30 + agaw * LEVEL_STRIDE; +} + +static inline int width_to_agaw(int width) +{ + return (width - 30) / LEVEL_STRIDE; +} + +static inline unsigned int level_to_offset_bits(int level) +{ + return (level - 1) * LEVEL_STRIDE; +} + +static inline int pfn_level_offset(unsigned long pfn, int level) +{ + return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK; +} + +static inline unsigned long level_mask(int level) +{ + return -1UL << level_to_offset_bits(level); +} + +static inline unsigned long level_size(int level) +{ + return 1UL << level_to_offset_bits(level); +} + +static inline unsigned long align_to_level(unsigned long pfn, int level) +{ + return (pfn + level_size(level) - 1) & level_mask(level); +} /* VT-d pages must always be _smaller_ than MM pages. Otherwise things are never going to work. */ @@ -434,8 +477,6 @@ void free_iova_mem(struct iova *iova) } -static inline int width_to_agaw(int width); - static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw) { unsigned long sagaw; @@ -646,51 +687,6 @@ out: spin_unlock_irqrestore(&iommu->lock, flags); } -/* page table handling */ -#define LEVEL_STRIDE (9) -#define LEVEL_MASK (((u64)1 << LEVEL_STRIDE) - 1) - -static inline int agaw_to_level(int agaw) -{ - return agaw + 2; -} - -static inline int agaw_to_width(int agaw) -{ - return 30 + agaw * LEVEL_STRIDE; - -} - -static inline int width_to_agaw(int width) -{ - return (width - 30) / LEVEL_STRIDE; -} - -static inline unsigned int level_to_offset_bits(int level) -{ - return (level - 1) * LEVEL_STRIDE; -} - -static inline int pfn_level_offset(unsigned long pfn, int level) -{ - return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK; -} - -static inline unsigned long level_mask(int level) -{ - return -1UL << level_to_offset_bits(level); -} - -static inline unsigned long level_size(int level) -{ - return 1UL << level_to_offset_bits(level); -} - -static inline unsigned long align_to_level(unsigned long pfn, int level) -{ - return (pfn + level_size(level) - 1) & level_mask(level); -} - static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, unsigned long pfn) { diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index 66f53c3..12a8e6f 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -221,7 +221,7 @@ static void dell_wmi_notify(u32 value, void *context) return; } - if (dell_new_hk_type) + if (dell_new_hk_type || buffer_entry[1] == 0x0) reported_key = (int)buffer_entry[2]; else reported_key = (int)buffer_entry[1] & 0xffff; diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 51c07a0..f1c1862 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -58,6 +58,12 @@ enum hp_wmi_radio { HPWMI_WWAN = 2, }; +enum hp_wmi_event_ids { + HPWMI_DOCK_EVENT = 1, + HPWMI_BEZEL_BUTTON = 4, + HPWMI_WIRELESS = 5, +}; + static int __devinit hp_wmi_bios_setup(struct platform_device *device); static int __exit hp_wmi_bios_remove(struct platform_device *device); static int hp_wmi_resume_handler(struct device *device); @@ -338,7 +344,7 @@ static void hp_wmi_notify(u32 value, void *context) struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; static struct key_entry *key; union acpi_object *obj; - int eventcode; + int eventcode, key_code; acpi_status status; status = wmi_get_event_data(value, &response); @@ -357,28 +363,32 @@ static void hp_wmi_notify(u32 value, void *context) eventcode = *((u8 *) obj->buffer.pointer); kfree(obj); - if (eventcode == 0x4) - eventcode = hp_wmi_perform_query(HPWMI_HOTKEY_QUERY, 0, - 0); - key = hp_wmi_get_entry_by_scancode(eventcode); - if (key) { - switch (key->type) { - case KE_KEY: - input_report_key(hp_wmi_input_dev, - key->keycode, 1); - input_sync(hp_wmi_input_dev); - input_report_key(hp_wmi_input_dev, - key->keycode, 0); - input_sync(hp_wmi_input_dev); - break; - } - } else if (eventcode == 0x1) { + switch (eventcode) { + case HPWMI_DOCK_EVENT: input_report_switch(hp_wmi_input_dev, SW_DOCK, hp_wmi_dock_state()); input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE, hp_wmi_tablet_state()); input_sync(hp_wmi_input_dev); - } else if (eventcode == 0x5) { + break; + case HPWMI_BEZEL_BUTTON: + key_code = hp_wmi_perform_query(HPWMI_HOTKEY_QUERY, 0, + 0); + key = hp_wmi_get_entry_by_scancode(key_code); + if (key) { + switch (key->type) { + case KE_KEY: + input_report_key(hp_wmi_input_dev, + key->keycode, 1); + input_sync(hp_wmi_input_dev); + input_report_key(hp_wmi_input_dev, + key->keycode, 0); + input_sync(hp_wmi_input_dev); + break; + } + } + break; + case HPWMI_WIRELESS: if (wifi_rfkill) rfkill_set_states(wifi_rfkill, hp_wmi_get_sw_state(HPWMI_WIFI), @@ -391,9 +401,12 @@ static void hp_wmi_notify(u32 value, void *context) rfkill_set_states(wwan_rfkill, hp_wmi_get_sw_state(HPWMI_WWAN), hp_wmi_get_hw_state(HPWMI_WWAN)); - } else + break; + default: printk(KERN_INFO "HP WMI: Unknown key pressed - %x\n", eventcode); + break; + } } static int __init hp_wmi_input_setup(void) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 70b68d3..2a305ef 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -298,11 +298,6 @@ static int s3c_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) s3c_rtc_setaie(alrm->enabled); - if (alrm->enabled) - enable_irq_wake(s3c_rtc_alarmno); - else - disable_irq_wake(s3c_rtc_alarmno); - return 0; } @@ -547,6 +542,10 @@ static int s3c_rtc_suspend(struct platform_device *pdev, pm_message_t state) ticnt_en_save &= S3C64XX_RTCCON_TICEN; } s3c_rtc_enable(pdev, 0); + + if (device_may_wakeup(&pdev->dev)) + enable_irq_wake(s3c_rtc_alarmno); + return 0; } @@ -560,6 +559,10 @@ static int s3c_rtc_resume(struct platform_device *pdev) tmp = readb(s3c_rtc_base + S3C2410_RTCCON); writeb(tmp | ticnt_en_save, s3c_rtc_base + S3C2410_RTCCON); } + + if (device_may_wakeup(&pdev->dev)) + disable_irq_wake(s3c_rtc_alarmno); + return 0; } #else diff --git a/drivers/staging/vt6655/wpactl.c b/drivers/staging/vt6655/wpactl.c index 22c2fab..f79808e 100644 --- a/drivers/staging/vt6655/wpactl.c +++ b/drivers/staging/vt6655/wpactl.c @@ -766,9 +766,14 @@ static int wpa_set_associate(PSDevice pDevice, DBG_PRT(MSG_LEVEL_DEBUG, KERN_INFO "wpa_ie_len = %d\n", param->u.wpa_associate.wpa_ie_len); - if (param->u.wpa_associate.wpa_ie && - copy_from_user(&abyWPAIE[0], param->u.wpa_associate.wpa_ie, param->u.wpa_associate.wpa_ie_len)) - return -EINVAL; + if (param->u.wpa_associate.wpa_ie_len) { + if (!param->u.wpa_associate.wpa_ie) + return -EINVAL; + if (param->u.wpa_associate.wpa_ie_len > sizeof(abyWPAIE)) + return -EINVAL; + if (copy_from_user(&abyWPAIE[0], param->u.wpa_associate.wpa_ie, param->u.wpa_associate.wpa_ie_len)) + return -EFAULT; + } if (param->u.wpa_associate.mode == 1) pMgmt->eConfigMode = WMAC_CONFIG_IBSS_STA; diff --git a/drivers/usb/musb/musb_debugfs.c b/drivers/usb/musb/musb_debugfs.c index c79a5e3..9e8639d 100644 --- a/drivers/usb/musb/musb_debugfs.c +++ b/drivers/usb/musb/musb_debugfs.c @@ -195,15 +195,14 @@ static const struct file_operations musb_regdump_fops = { static int musb_test_mode_open(struct inode *inode, struct file *file) { - file->private_data = inode->i_private; - return single_open(file, musb_test_mode_show, inode->i_private); } static ssize_t musb_test_mode_write(struct file *file, const char __user *ubuf, size_t count, loff_t *ppos) { - struct musb *musb = file->private_data; + struct seq_file *s = file->private_data; + struct musb *musb = s->private; u8 test = 0; char buf[18]; diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c index 30922a7..aa66581 100644 --- a/drivers/usb/serial/mos7720.c +++ b/drivers/usb/serial/mos7720.c @@ -2024,6 +2024,9 @@ static int mos7720_ioctl(struct tty_struct *tty, struct file *file, case TIOCGICOUNT: cnow = mos7720_port->icount; + + memset(&icount, 0, sizeof(struct serial_icounter_struct)); + icount.cts = cnow.cts; icount.dsr = cnow.dsr; icount.rng = cnow.rng; diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c index 1c9b6e9..1a42bc2 100644 --- a/drivers/usb/serial/mos7840.c +++ b/drivers/usb/serial/mos7840.c @@ -2285,6 +2285,9 @@ static int mos7840_ioctl(struct tty_struct *tty, struct file *file, case TIOCGICOUNT: cnow = mos7840_port->icount; smp_rmb(); + + memset(&icount, 0, sizeof(struct serial_icounter_struct)); + icount.cts = cnow.cts; icount.dsr = cnow.dsr; icount.rng = cnow.rng; diff --git a/drivers/video/sis/sis_main.c b/drivers/video/sis/sis_main.c index 559bf17..b52f8e4 100644 --- a/drivers/video/sis/sis_main.c +++ b/drivers/video/sis/sis_main.c @@ -1701,6 +1701,9 @@ static int sisfb_ioctl(struct fb_info *info, unsigned int cmd, break; case FBIOGET_VBLANK: + + memset(&sisvbblank, 0, sizeof(struct fb_vblank)); + sisvbblank.count = 0; sisvbblank.flags = sisfb_setupvbblankflags(ivideo, &sisvbblank.vcount, &sisvbblank.hcount); diff --git a/drivers/video/via/ioctl.c b/drivers/video/via/ioctl.c index da03c07..4d553d0 100644 --- a/drivers/video/via/ioctl.c +++ b/drivers/video/via/ioctl.c @@ -25,6 +25,8 @@ int viafb_ioctl_get_viafb_info(u_long arg) { struct viafb_ioctl_info viainfo; + memset(&viainfo, 0, sizeof(struct viafb_ioctl_info)); + viainfo.viafb_id = VIAID; viainfo.vendor_id = PCI_VIA_VENDOR_ID; diff --git a/fs/aio.c b/fs/aio.c index 1ccf25c..5fb0fd7 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -712,8 +712,16 @@ static ssize_t aio_run_iocb(struct kiocb *iocb) */ ret = retry(iocb); - if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) + if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) { + /* + * There's no easy way to restart the syscall since other AIO's + * may be already running. Just fail this IO with EINTR. + */ + if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR || + ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK)) + ret = -EINTR; aio_complete(iocb, ret, 0); + } out: spin_lock_irq(&ctx->ctx_lock); @@ -1659,6 +1667,9 @@ long do_io_submit(aio_context_t ctx_id, long nr, if (unlikely(nr < 0)) return -EINVAL; + if (unlikely(nr > LONG_MAX/sizeof(*iocbpp))) + nr = LONG_MAX/sizeof(*iocbpp); + if (unlikely(!access_ok(VERIFY_READ, iocbpp, (nr*sizeof(*iocbpp))))) return -EFAULT; diff --git a/fs/char_dev.c b/fs/char_dev.c index f80a4f2..143d393 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -40,7 +40,9 @@ struct backing_dev_info directly_mappable_cdev_bdi = { #endif /* permit direct mmap, for read, write or exec */ BDI_CAP_MAP_DIRECT | - BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP), + BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP | + /* no writeback happens */ + BDI_CAP_NO_ACCT_AND_WRITEBACK), }; static struct kobj_map *cdev_map; diff --git a/fs/compat.c b/fs/compat.c index 6490d21..af7c230 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1150,7 +1150,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, { compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov; + struct iovec *iov = iovstack; ssize_t ret; io_fn_t fn; iov_fn_t fnv; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 6a857e2..83917b5 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -932,7 +932,7 @@ int gfs2_logd(void *data) do { prepare_to_wait(&sdp->sd_logd_waitq, &wait, - TASK_UNINTERRUPTIBLE); + TASK_INTERRUPTIBLE); if (!gfs2_ail_flush_reqd(sdp) && !gfs2_jrnl_flush_reqd(sdp) && !kthread_should_stop()) diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index e46ca68..0c6bbc0 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -96,8 +96,11 @@ static inline __u32 inotify_arg_to_mask(u32 arg) { __u32 mask; - /* everything should accept their own ignored and cares about children */ - mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD); + /* + * everything should accept their own ignored, cares about children, + * and should receive events when the inode is unmounted + */ + mask = (FS_IN_IGNORED | FS_EVENT_ON_CHILD | FS_UNMOUNT); /* mask off the flags used to open the fd */ mask |= (arg & (IN_ALL_EVENTS | IN_ONESHOT)); diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 91c817f..2367fb3 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -163,7 +163,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer, static const struct file_operations proc_vmcore_operations = { .read = read_vmcore, - .llseek = generic_file_llseek, + .llseek = default_llseek, }; static struct vmcore* __init get_new_element(void) diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index e59a810..82a74f6 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -794,6 +794,8 @@ xfs_ioc_fsgetxattr( { struct fsxattr fa; + memset(&fa, 0, sizeof(struct fsxattr)); + xfs_ilock(ip, XFS_ILOCK_SHARED); fa.fsx_xflags = xfs_ip2xflags(ip); fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog; diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 43bdab7..e809eb1 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -16,6 +16,9 @@ struct stable_node; struct mem_cgroup; +struct page *ksm_does_need_to_copy(struct page *page, + struct vm_area_struct *vma, unsigned long address); + #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); @@ -70,19 +73,14 @@ static inline void set_page_stable_node(struct page *page, * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ -struct page *ksm_does_need_to_copy(struct page *page, - struct vm_area_struct *vma, unsigned long address); -static inline struct page *ksm_might_need_to_copy(struct page *page, +static inline int ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct anon_vma *anon_vma = page_anon_vma(page); - if (!anon_vma || - (anon_vma == vma->anon_vma && - page->index == linear_page_index(vma, address))) - return page; - - return ksm_does_need_to_copy(page, vma, address); + return anon_vma && + (anon_vma != vma->anon_vma || + page->index != linear_page_index(vma, address)); } int page_referenced_ksm(struct page *page, @@ -115,10 +113,10 @@ static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, return 0; } -static inline struct page *ksm_might_need_to_copy(struct page *page, +static inline int ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address) { - return page; + return 0; } static inline int page_referenced_ksm(struct page *page, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7cb116a..f24d8fc 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -123,6 +123,7 @@ struct kvm_memory_slot { } *lpage_info[KVM_NR_PAGE_SIZES - 1]; unsigned long userspace_addr; int user_alloc; + int id; }; static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) diff --git a/include/linux/mm.h b/include/linux/mm.h index a2b4804..c1f54d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -78,7 +78,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ +#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) #define VM_GROWSUP 0x00000200 +#else +#define VM_GROWSUP 0x00000000 +#endif #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ @@ -1329,8 +1333,10 @@ unsigned long ra_submit(struct file_ra_state *ra, /* Do stack extension */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); -#ifdef CONFIG_IA64 +#if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); +#else + #define expand_upwards(vma, address) do { } while (0) #endif extern int expand_stack_downwards(struct vm_area_struct *vma, unsigned long address); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b4d109e..8b2db3d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -284,6 +284,13 @@ struct zone { unsigned long watermark[NR_WMARK]; /* + * When free pages are below this point, additional steps are taken + * when reading the number of free pages to avoid per-cpu counter + * drift allowing watermarks to be breached + */ + unsigned long percpu_drift_mark; + + /* * We don't know if the memory that we're going to allocate will be freeable * or/and it will be released eventually, so to avoid totally wasting several * GB of ram we must reserve some of the lower zone memory (otherwise we risk @@ -456,6 +463,12 @@ static inline int zone_is_oom_locked(const struct zone *zone) return test_bit(ZONE_OOM_LOCKED, &zone->flags); } +#ifdef CONFIG_SMP +unsigned long zone_nr_free_pages(struct zone *zone); +#else +#define zone_nr_free_pages(zone) zone_page_state(zone, NR_FREE_PAGES) +#endif /* CONFIG_SMP */ + /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 7f43ccd..eaaea37 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -170,6 +170,28 @@ static inline unsigned long zone_page_state(struct zone *zone, return x; } +/* + * More accurate version that also considers the currently pending + * deltas. For that we need to loop over all cpus to find the current + * deltas. There is no synchronization so the result cannot be + * exactly accurate either. + */ +static inline unsigned long zone_page_state_snapshot(struct zone *zone, + enum zone_stat_item item) +{ + long x = atomic_long_read(&zone->vm_stat[item]); + +#ifdef CONFIG_SMP + int cpu; + for_each_online_cpu(cpu) + x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; + + if (x < 0) + x = 0; +#endif + return x; +} + extern unsigned long global_reclaimable_pages(void); extern unsigned long zone_reclaimable_pages(struct zone *zone); diff --git a/include/net/sock.h b/include/net/sock.h index 0a691ea..e2a9f59 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -749,6 +749,7 @@ struct proto { /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); + void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); /* Keeping track of sockets in use */ diff --git a/include/net/tcp.h b/include/net/tcp.h index a144914..e824cf0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -268,11 +268,21 @@ static inline int between(__u32 seq1, __u32 seq2, __u32 seq3) return seq3 - seq2 >= seq1 - seq2; } -static inline int tcp_too_many_orphans(struct sock *sk, int num) +static inline bool tcp_too_many_orphans(struct sock *sk, int shift) { - return (num > sysctl_tcp_max_orphans) || - (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && - atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]); + struct percpu_counter *ocp = sk->sk_prot->orphan_count; + int orphans = percpu_counter_read_positive(ocp); + + if (orphans << shift > sysctl_tcp_max_orphans) { + orphans = percpu_counter_sum_positive(ocp); + if (orphans << shift > sysctl_tcp_max_orphans) + return true; + } + + if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && + atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]) + return true; + return false; } /* syncookies: remember time of last synqueue overflow */ @@ -509,8 +519,22 @@ extern unsigned int tcp_current_mss(struct sock *sk); /* Bound MSS / TSO packet size with the half of the window */ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) { - if (tp->max_window && pktsize > (tp->max_window >> 1)) - return max(tp->max_window >> 1, 68U - tp->tcp_header_len); + int cutoff; + + /* When peer uses tiny windows, there is no use in packetizing + * to sub-MSS pieces for the sake of SWS or making sure there + * are enough packets in the pipe for fast recovery. + * + * On the other hand, for extremely large MSS devices, handling + * smaller than MSS windows in this way does make sense. + */ + if (tp->max_window >= 512) + cutoff = (tp->max_window >> 1); + else + cutoff = tp->max_window; + + if (cutoff && pktsize > cutoff) + return max_t(int, cutoff, 68U - tp->tcp_header_len); else return pktsize; } diff --git a/include/net/udp.h b/include/net/udp.h index 5348d80..4201dc8 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -151,6 +151,7 @@ static inline void udp_lib_hash(struct sock *sk) } extern void udp_lib_unhash(struct sock *sk); +extern void udp_lib_rehash(struct sock *sk, u16 new_hash); static inline void udp_lib_close(struct sock *sk, long timeout) { diff --git a/kernel/exit.c b/kernel/exit.c index ceffc67..ac90425 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1383,8 +1383,7 @@ static int wait_task_stopped(struct wait_opts *wo, if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; - /* don't need the RCU readlock here as we're holding a spinlock */ - uid = __task_cred(p)->uid; + uid = task_uid(p); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1457,7 +1456,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; - uid = __task_cred(p)->uid; + uid = task_uid(p); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index 7a56b22..6eb6422 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -417,7 +417,8 @@ register_user_hw_breakpoint(struct perf_event_attr *attr, perf_overflow_handler_t triggered, struct task_struct *tsk) { - return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered); + return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk), + triggered); } EXPORT_SYMBOL_GPL(register_user_hw_breakpoint); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 25ce010..7fa52b5 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1121,9 +1121,19 @@ static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask) return nr_alloc; } -static unsigned long preallocate_image_memory(unsigned long nr_pages) +static unsigned long preallocate_image_memory(unsigned long nr_pages, + unsigned long avail_normal) { - return preallocate_image_pages(nr_pages, GFP_IMAGE); + unsigned long alloc; + + if (avail_normal <= alloc_normal) + return 0; + + alloc = avail_normal - alloc_normal; + if (nr_pages < alloc) + alloc = nr_pages; + + return preallocate_image_pages(alloc, GFP_IMAGE); } #ifdef CONFIG_HIGHMEM @@ -1169,15 +1179,22 @@ static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages, */ static void free_unnecessary_pages(void) { - unsigned long save_highmem, to_free_normal, to_free_highmem; + unsigned long save, to_free_normal, to_free_highmem; - to_free_normal = alloc_normal - count_data_pages(); - save_highmem = count_highmem_pages(); - if (alloc_highmem > save_highmem) { - to_free_highmem = alloc_highmem - save_highmem; + save = count_data_pages(); + if (alloc_normal >= save) { + to_free_normal = alloc_normal - save; + save = 0; + } else { + to_free_normal = 0; + save -= alloc_normal; + } + save += count_highmem_pages(); + if (alloc_highmem >= save) { + to_free_highmem = alloc_highmem - save; } else { to_free_highmem = 0; - to_free_normal -= save_highmem - alloc_highmem; + to_free_normal -= save - alloc_highmem; } memory_bm_position_reset(©_bm); @@ -1258,7 +1275,7 @@ int hibernate_preallocate_memory(void) { struct zone *zone; unsigned long saveable, size, max_size, count, highmem, pages = 0; - unsigned long alloc, save_highmem, pages_highmem; + unsigned long alloc, save_highmem, pages_highmem, avail_normal; struct timeval start, stop; int error; @@ -1295,6 +1312,7 @@ int hibernate_preallocate_memory(void) else count += zone_page_state(zone, NR_FREE_PAGES); } + avail_normal = count; count += highmem; count -= totalreserve_pages; @@ -1309,12 +1327,21 @@ int hibernate_preallocate_memory(void) */ if (size >= saveable) { pages = preallocate_image_highmem(save_highmem); - pages += preallocate_image_memory(saveable - pages); + pages += preallocate_image_memory(saveable - pages, avail_normal); goto out; } /* Estimate the minimum size of the image. */ pages = minimum_image_size(saveable); + /* + * To avoid excessive pressure on the normal zone, leave room in it to + * accommodate an image of the minimum size (unless it's already too + * small, in which case don't preallocate pages from it at all). + */ + if (avail_normal > pages) + avail_normal -= pages; + else + avail_normal = 0; if (size < pages) size = min_t(unsigned long, pages, max_size); @@ -1335,16 +1362,34 @@ int hibernate_preallocate_memory(void) */ pages_highmem = preallocate_image_highmem(highmem / 2); alloc = (count - max_size) - pages_highmem; - pages = preallocate_image_memory(alloc); - if (pages < alloc) - goto err_out; - size = max_size - size; - alloc = size; - size = preallocate_highmem_fraction(size, highmem, count); - pages_highmem += size; - alloc -= size; - pages += preallocate_image_memory(alloc); - pages += pages_highmem; + pages = preallocate_image_memory(alloc, avail_normal); + if (pages < alloc) { + /* We have exhausted non-highmem pages, try highmem. */ + alloc -= pages; + pages += pages_highmem; + pages_highmem = preallocate_image_highmem(alloc); + if (pages_highmem < alloc) + goto err_out; + pages += pages_highmem; + /* + * size is the desired number of saveable pages to leave in + * memory, so try to preallocate (all memory - size) pages. + */ + alloc = (count - pages) - size; + pages += preallocate_image_highmem(alloc); + } else { + /* + * There are approximately max_size saveable pages at this point + * and we want to reduce this number down to size. + */ + alloc = max_size - size; + size = preallocate_highmem_fraction(alloc, highmem, count); + pages_highmem += size; + alloc -= size; + size = preallocate_image_memory(alloc, avail_normal); + pages_highmem += preallocate_image_highmem(alloc - size); + pages += pages_highmem + size; + } /* * We only need as many page frames for the image as there are saveable diff --git a/kernel/sched.c b/kernel/sched.c index 6d0dbeb..4fa520b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3349,9 +3349,9 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) rtime = nsecs_to_cputime(p->se.sum_exec_runtime); if (total) { - u64 temp; + u64 temp = rtime; - temp = (u64)(rtime * utime); + temp *= utime; do_div(temp, total); utime = (cputime_t)temp; } else @@ -3382,9 +3382,9 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) rtime = nsecs_to_cputime(cputime.sum_exec_runtime); if (total) { - u64 temp; + u64 temp = rtime; - temp = (u64)(rtime * cputime.utime); + temp *= cputime.utime; do_div(temp, total); utime = (cputime_t)temp; } else diff --git a/kernel/sys.c b/kernel/sys.c index e83ddbb..f4fcc6e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -931,6 +931,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) pgid = pid; if (pgid < 0) return -EINVAL; + rcu_read_lock(); /* From this point forward we keep holding onto the tasklist lock * so that our parent does not change from under us. -DaveM @@ -984,6 +985,7 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); + rcu_read_unlock(); return err; } diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 123bcef..c0f7157 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -29,6 +29,7 @@ EXPORT_SYMBOL_GPL(default_backing_dev_info); struct backing_dev_info noop_backing_dev_info = { .name = "noop", + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; EXPORT_SYMBOL_GPL(noop_backing_dev_info); @@ -254,6 +255,7 @@ static int __init default_bdi_init(void) err = bdi_init(&default_backing_dev_info); if (!err) bdi_register(&default_backing_dev_info, NULL, "default"); + err = bdi_init(&noop_backing_dev_info); return err; } diff --git a/mm/ksm.c b/mm/ksm.c index 6c3e99b..17ee9df 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1523,8 +1523,6 @@ struct page *ksm_does_need_to_copy(struct page *page, { struct page *new_page; - unlock_page(page); /* any racers will COW it, not modify it */ - new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); if (new_page) { copy_user_highpage(new_page, page, address, vma); @@ -1540,7 +1538,6 @@ struct page *ksm_does_need_to_copy(struct page *page, add_page_to_unevictable_list(new_page); } - page_cache_release(page); return new_page; } diff --git a/mm/memory.c b/mm/memory.c index 53cf85d..7550758 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2626,7 +2626,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned int flags, pte_t orig_pte) { spinlock_t *ptl; - struct page *page; + struct page *page, *swapcache = NULL; swp_entry_t entry; pte_t pte; struct mem_cgroup *ptr = NULL; @@ -2681,10 +2681,25 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, lock_page(page); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); - page = ksm_might_need_to_copy(page, vma, address); - if (!page) { - ret = VM_FAULT_OOM; - goto out; + /* + * Make sure try_to_free_swap or reuse_swap_page or swapoff did not + * release the swapcache from under us. The page pin, and pte_same + * test below, are not enough to exclude that. Even if it is still + * swapcache, we need to check that the page's swap has not changed. + */ + if (unlikely(!PageSwapCache(page) || page_private(page) != entry.val)) + goto out_page; + + if (ksm_might_need_to_copy(page, vma, address)) { + swapcache = page; + page = ksm_does_need_to_copy(page, vma, address); + + if (unlikely(!page)) { + ret = VM_FAULT_OOM; + page = swapcache; + swapcache = NULL; + goto out_page; + } } if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) { @@ -2735,6 +2750,18 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); + if (swapcache) { + /* + * Hold the lock to avoid the swap entry to be reused + * until we take the PT lock for the pte_same() check + * (to avoid false positives from pte_same). For + * further safety release the lock after the swap_free + * so that the swap count won't change under a + * parallel locked swapcache. + */ + unlock_page(swapcache); + page_cache_release(swapcache); + } if (flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte); @@ -2756,15 +2783,17 @@ out_page: unlock_page(page); out_release: page_cache_release(page); + if (swapcache) { + unlock_page(swapcache); + page_cache_release(swapcache); + } return ret; } /* - * This is like a special single-page "expand_downwards()", - * except we must first make sure that 'address-PAGE_SIZE' + * This is like a special single-page "expand_{down|up}wards()", + * except we must first make sure that 'address{-|+}PAGE_SIZE' * doesn't hit another vma. - * - * The "find_vma()" will do the right thing even if we wrap */ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned long address) { @@ -2783,6 +2812,15 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo expand_stack(vma, address - PAGE_SIZE); } + if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { + struct vm_area_struct *next = vma->vm_next; + + /* As VM_GROWSDOWN but s/below/above/ */ + if (next && next->vm_start == address + PAGE_SIZE) + return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; + + expand_upwards(vma, address + PAGE_SIZE); + } return 0; } diff --git a/mm/mmap.c b/mm/mmap.c index 3867cfc..3a94362 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1704,9 +1704,6 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns * PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. */ -#ifndef CONFIG_IA64 -static -#endif int expand_upwards(struct vm_area_struct *vma, unsigned long address) { int error; @@ -1997,6 +1994,7 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, removed_exe_file_vma(mm); fput(new->vm_file); } + unlink_anon_vmas(new); out_free_mpol: mpol_put(pol); out_free_vma: diff --git a/mm/mmzone.c b/mm/mmzone.c index f5b7d17..e35bfb8 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -87,3 +87,24 @@ int memmap_valid_within(unsigned long pfn, return 1; } #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ + +#ifdef CONFIG_SMP +/* Called when a more accurate view of NR_FREE_PAGES is needed */ +unsigned long zone_nr_free_pages(struct zone *zone) +{ + unsigned long nr_free_pages = zone_page_state(zone, NR_FREE_PAGES); + + /* + * While kswapd is awake, it is considered the zone is under some + * memory pressure. Under pressure, there is a risk that + * per-cpu-counter-drift will allow the min watermark to be breached + * potentially causing a live-lock. While kswapd is awake and + * free pages are low, get a better estimate for free pages + */ + if (nr_free_pages < zone->percpu_drift_mark && + !waitqueue_active(&zone->zone_pgdat->kswapd_wait)) + return zone_page_state_snapshot(zone, NR_FREE_PAGES); + + return nr_free_pages; +} +#endif /* CONFIG_SMP */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9bd339e..f7cc624 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -588,13 +588,13 @@ static void free_pcppages_bulk(struct zone *zone, int count, { int migratetype = 0; int batch_free = 0; + int to_free = count; spin_lock(&zone->lock); zone->all_unreclaimable = 0; zone->pages_scanned = 0; - __mod_zone_page_state(zone, NR_FREE_PAGES, count); - while (count) { + while (to_free) { struct page *page; struct list_head *list; @@ -619,8 +619,9 @@ static void free_pcppages_bulk(struct zone *zone, int count, /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ __free_one_page(page, zone, 0, page_private(page)); trace_mm_page_pcpu_drain(page, 0, page_private(page)); - } while (--count && --batch_free && !list_empty(list)); + } while (--to_free && --batch_free && !list_empty(list)); } + __mod_zone_page_state(zone, NR_FREE_PAGES, count); spin_unlock(&zone->lock); } @@ -631,8 +632,8 @@ static void free_one_page(struct zone *zone, struct page *page, int order, zone->all_unreclaimable = 0; zone->pages_scanned = 0; - __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order); __free_one_page(page, zone, order, migratetype); + __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order); spin_unlock(&zone->lock); } @@ -1461,7 +1462,7 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark, { /* free_pages my go negative - that's OK */ long min = mark; - long free_pages = zone_page_state(z, NR_FREE_PAGES) - (1 << order) + 1; + long free_pages = zone_nr_free_pages(z) - (1 << order) + 1; int o; if (alloc_flags & ALLOC_HIGH) @@ -1843,6 +1844,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, struct page *page = NULL; struct reclaim_state reclaim_state; struct task_struct *p = current; + bool drained = false; cond_resched(); @@ -1861,14 +1863,25 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, cond_resched(); - if (order != 0) - drain_all_pages(); + if (unlikely(!(*did_some_progress))) + return NULL; - if (likely(*did_some_progress)) - page = get_page_from_freelist(gfp_mask, nodemask, order, +retry: + page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags, preferred_zone, migratetype); + + /* + * If an allocation failed after direct reclaim, it could be because + * pages are pinned on the per-cpu lists. Drain them and try again + */ + if (!page && !drained) { + drain_all_pages(); + drained = true; + goto retry; + } + return page; } @@ -2412,7 +2425,7 @@ void show_free_areas(void) " all_unreclaimable? %s" "\n", zone->name, - K(zone_page_state(zone, NR_FREE_PAGES)), + K(zone_nr_free_pages(zone)), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), diff --git a/mm/percpu.c b/mm/percpu.c index 6470e77..0a09fff 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1413,9 +1413,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, if (pcpu_first_unit_cpu == NR_CPUS) pcpu_first_unit_cpu = cpu; + pcpu_last_unit_cpu = cpu; } } - pcpu_last_unit_cpu = cpu; pcpu_nr_units = unit; for_each_possible_cpu(cpu) diff --git a/mm/vmscan.c b/mm/vmscan.c index b94fe1b..9753626 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1726,13 +1726,12 @@ static void shrink_zone(int priority, struct zone *zone, * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ -static bool shrink_zones(int priority, struct zonelist *zonelist, +static void shrink_zones(int priority, struct zonelist *zonelist, struct scan_control *sc) { enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask); struct zoneref *z; struct zone *zone; - bool all_unreclaimable = true; for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, sc->nodemask) { @@ -1759,8 +1758,38 @@ static bool shrink_zones(int priority, struct zonelist *zonelist, } shrink_zone(priority, zone, sc); - all_unreclaimable = false; } +} + +static bool zone_reclaimable(struct zone *zone) +{ + return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; +} + +/* + * As hibernation is going on, kswapd is freezed so that it can't mark + * the zone into all_unreclaimable. It can't handle OOM during hibernation. + * So let's check zone's unreclaimable in direct reclaim as well as kswapd. + */ +static bool all_unreclaimable(struct zonelist *zonelist, + struct scan_control *sc) +{ + struct zoneref *z; + struct zone *zone; + bool all_unreclaimable = true; + + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(sc->gfp_mask), sc->nodemask) { + if (!populated_zone(zone)) + continue; + if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) + continue; + if (zone_reclaimable(zone)) { + all_unreclaimable = false; + break; + } + } + return all_unreclaimable; } @@ -1784,7 +1813,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int priority; - bool all_unreclaimable; unsigned long total_scanned = 0; struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long lru_pages = 0; @@ -1815,7 +1843,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, sc->nr_scanned = 0; if (!priority) disable_swap_token(); - all_unreclaimable = shrink_zones(priority, zonelist, sc); + shrink_zones(priority, zonelist, sc); /* * Don't shrink slabs when reclaiming memory from * over limit cgroups @@ -1879,7 +1907,7 @@ out: return sc->nr_reclaimed; /* top priority shrink_zones still had more to do? don't OOM, then */ - if (scanning_global_lru(sc) && !all_unreclaimable) + if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc)) return 1; return 0; @@ -2137,8 +2165,7 @@ loop_again: total_scanned += sc.nr_scanned; if (zone->all_unreclaimable) continue; - if (nr_slab == 0 && - zone->pages_scanned >= (zone_reclaimable_pages(zone) * 6)) + if (nr_slab == 0 && !zone_reclaimable(zone)) zone->all_unreclaimable = 1; /* * If we've done a decent amount of scanning and diff --git a/mm/vmstat.c b/mm/vmstat.c index 7759941..26d5716 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -138,11 +138,24 @@ static void refresh_zone_stat_thresholds(void) int threshold; for_each_populated_zone(zone) { + unsigned long max_drift, tolerate_drift; + threshold = calculate_threshold(zone); for_each_online_cpu(cpu) per_cpu_ptr(zone->pageset, cpu)->stat_threshold = threshold; + + /* + * Only set percpu_drift_mark if there is a danger that + * NR_FREE_PAGES reports the low watermark is ok when in fact + * the min watermark could be breached by an allocation + */ + tolerate_drift = low_wmark_pages(zone) - min_wmark_pages(zone); + max_drift = num_online_cpus() * threshold; + if (max_drift > tolerate_drift) + zone->percpu_drift_mark = high_wmark_pages(zone) + + max_drift; } } @@ -813,7 +826,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n scanned %lu" "\n spanned %lu" "\n present %lu", - zone_page_state(zone, NR_FREE_PAGES), + zone_nr_free_pages(zone), min_wmark_pages(zone), low_wmark_pages(zone), high_wmark_pages(zone), diff --git a/net/Kconfig b/net/Kconfig index 0d68b40..a44092e 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -206,7 +206,7 @@ source "net/dcb/Kconfig" config RPS boolean - depends on SMP && SYSFS + depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y menu "Network testing" diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 8fb75f8..e759b89 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -749,9 +749,11 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb) { if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) && skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu && - !skb_is_gso(skb)) + !skb_is_gso(skb)) { + /* BUG: Should really parse the IP options here. */ + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); return ip_fragment(skb, br_dev_queue_push_xmit); - else + } else return br_dev_queue_push_xmit(skb); } #else diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ce88293..a586e89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2574,6 +2574,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) __copy_skb_header(nskb, skb); nskb->mac_len = skb->mac_len; + /* nskb and skb might have different headroom */ + if (nskb->ip_summed == CHECKSUM_PARTIAL) + nskb->csum_start += skb_headroom(nskb) - headroom; + skb_reset_mac_header(nskb); skb_set_network_header(nskb, skb->mac_len); nskb->transport_header = (nskb->network_header + @@ -2704,7 +2708,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) return -E2BIG; headroom = skb_headroom(p); - nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p)); + nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); if (unlikely(!nskb)) return -ENOMEM; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index fb24658..31cafd4 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -62,8 +62,11 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (!inet->inet_saddr) inet->inet_saddr = rt->rt_src; /* Update source address */ - if (!inet->inet_rcv_saddr) + if (!inet->inet_rcv_saddr) { inet->inet_rcv_saddr = rt->rt_src; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } inet->inet_daddr = rt->rt_dst; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 560acc6..0189deb 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2741,6 +2741,11 @@ slow_output: EXPORT_SYMBOL_GPL(__ip_route_output_key); +static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) +{ + return NULL; +} + static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } @@ -2749,7 +2754,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, - .check = ipv4_dst_check, + .check = ipv4_blackhole_dst_check, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .entries = ATOMIC_INIT(0), }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c259714..c88ca26 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -453,7 +453,8 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) mask |= POLLOUT | POLLWRNORM; } - } + } else + mask |= POLLOUT | POLLWRNORM; if (tp->urg_data & TCP_URG_VALID) mask |= POLLPRI; @@ -2002,11 +2003,8 @@ adjudge_to_death: } } if (sk->sk_state != TCP_CLOSE) { - int orphan_count = percpu_counter_read_positive( - sk->sk_prot->orphan_count); - sk_mem_reclaim(sk); - if (tcp_too_many_orphans(sk, orphan_count)) { + if (tcp_too_many_orphans(sk, 0)) { if (net_ratelimit()) printk(KERN_INFO "TCP: too many of orphaned " "sockets\n"); @@ -3196,7 +3194,7 @@ void __init tcp_init(void) { struct sk_buff *skb = NULL; unsigned long nr_pages, limit; - int order, i, max_share; + int i, max_share, cnt; unsigned long jiffy = jiffies; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -3245,22 +3243,12 @@ void __init tcp_init(void) INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); } - /* Try to be a bit smarter and adjust defaults depending - * on available memory. - */ - for (order = 0; ((1 << order) << PAGE_SHIFT) < - (tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket)); - order++) - ; - if (order >= 4) { - tcp_death_row.sysctl_max_tw_buckets = 180000; - sysctl_tcp_max_orphans = 4096 << (order - 4); - sysctl_max_syn_backlog = 1024; - } else if (order < 3) { - tcp_death_row.sysctl_max_tw_buckets >>= (3 - order); - sysctl_tcp_max_orphans >>= (3 - order); - sysctl_max_syn_backlog = 128; - } + + cnt = tcp_hashinfo.ehash_mask + 1; + + tcp_death_row.sysctl_max_tw_buckets = cnt / 2; + sysctl_tcp_max_orphans = cnt / 2; + sysctl_max_syn_backlog = max(128, cnt / 256); /* Set the pressure threshold to be a fraction of global memory that * is up to 1/2 at 256 MB, decreasing toward zero with the amount of diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 440a5c6..7abd922 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -67,18 +67,18 @@ static void tcp_write_err(struct sock *sk) static int tcp_out_of_resources(struct sock *sk, int do_reset) { struct tcp_sock *tp = tcp_sk(sk); - int orphans = percpu_counter_read_positive(&tcp_orphan_count); + int shift = 0; /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) - orphans <<= 1; + shift++; /* If some dubious ICMP arrived, penalize even more. */ if (sk->sk_err_soft) - orphans <<= 1; + shift++; - if (tcp_too_many_orphans(sk, orphans)) { + if (tcp_too_many_orphans(sk, shift)) { if (net_ratelimit()) printk(KERN_INFO "Out of socket memory\n"); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index eec4ff4..434dd67 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1260,6 +1260,49 @@ void udp_lib_unhash(struct sock *sk) } EXPORT_SYMBOL(udp_lib_unhash); +/* + * inet_rcv_saddr was changed, we must rehash secondary hash + */ +void udp_lib_rehash(struct sock *sk, u16 newhash) +{ + if (sk_hashed(sk)) { + struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_hslot *hslot, *hslot2, *nhslot2; + + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + nhslot2 = udp_hashslot2(udptable, newhash); + udp_sk(sk)->udp_portaddr_hash = newhash; + if (hslot2 != nhslot2) { + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); + /* we must lock primary chain too */ + spin_lock_bh(&hslot->lock); + + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &nhslot2->head); + nhslot2->count++; + spin_unlock(&nhslot2->lock); + + spin_unlock_bh(&hslot->lock); + } + } +} +EXPORT_SYMBOL(udp_lib_rehash); + +static void udp_v4_rehash(struct sock *sk) +{ + u16 new_hash = udp4_portaddr_hash(sock_net(sk), + inet_sk(sk)->inet_rcv_saddr, + inet_sk(sk)->inet_num); + udp_lib_rehash(sk, new_hash); +} + static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -1843,6 +1886,7 @@ struct proto udp_prot = { .backlog_rcv = __udp_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 7126846..0e3754a1 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -104,9 +104,12 @@ ipv4_connected: if (ipv6_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - if (ipv6_addr_any(&np->rcv_saddr)) + if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr); + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } goto out; } @@ -191,6 +194,8 @@ ipv4_connected: if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); inet->inet_rcv_saddr = LOOPBACK4_IPV6; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); } ip6_dst_store(sk, dst, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 87be586..97e1214 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr); } +static void udp_v6_rehash(struct sock *sk) +{ + u16 new_hash = udp6_portaddr_hash(sock_net(sk), + &inet6_sk(sk)->rcv_saddr, + inet_sk(sk)->inet_num); + + udp_lib_rehash(sk, new_hash); +} + static inline int compute_score(struct sock *sk, struct net *net, unsigned short hnum, struct in6_addr *saddr, __be16 sport, @@ -1452,6 +1461,7 @@ struct proto udpv6_prot = { .backlog_rcv = udpv6_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 79986a6..fd55b51 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -824,8 +824,8 @@ static int irda_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = irda_open_tsap(self, addr->sir_lsap_sel, addr->sir_name); if (err < 0) { - kfree(self->ias_obj->name); - kfree(self->ias_obj); + irias_delete_object(self->ias_obj); + self->ias_obj = NULL; goto out; } diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 58c6c4c..1ae6976 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -132,7 +132,7 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, printk("\n"); } - if (data_len < ETH_HLEN) + if (!pskb_may_pull(skb, sizeof(ETH_HLEN))) goto error; secpath_reset(skb); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 023ba82..5826129 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -1024,7 +1024,8 @@ static int llc_ui_setsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - int rc = -EINVAL, opt; + unsigned int opt; + int rc = -EINVAL; lock_sock(sk); if (unlikely(level != SOL_LLC || optlen != sizeof(int))) diff --git a/net/rds/recv.c b/net/rds/recv.c index 795a00b..c93588c 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -297,7 +297,7 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr) { struct rds_notifier *notifier; - struct rds_rdma_notify cmsg; + struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */ unsigned int count = 0, max_messages = ~0U; unsigned long flags; LIST_HEAD(copy); diff --git a/net/sctp/output.c b/net/sctp/output.c index a646681..bcc4590 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -92,7 +92,6 @@ struct sctp_packet *sctp_packet_config(struct sctp_packet *packet, SCTP_DEBUG_PRINTK("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); - sctp_packet_reset(packet); packet->vtag = vtag; if (ecn_capable && sctp_packet_empty(packet)) { diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index fef2cc5..617bea4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -673,6 +673,7 @@ static int unix_autobind(struct socket *sock) static u32 ordernum = 1; struct unix_address *addr; int err; + unsigned int retries = 0; mutex_lock(&u->readlock); @@ -698,9 +699,17 @@ retry: if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type, addr->hash)) { spin_unlock(&unix_table_lock); - /* Sanity yield. It is unusual case, but yet... */ - if (!(ordernum&0xFF)) - yield(); + /* + * __unix_find_socket_byname() may take long time if many names + * are already in use. + */ + cond_resched(); + /* Give up if all names seems to be in use. */ + if (retries++ == 0xFFFFF) { + err = -ENOSPC; + kfree(addr); + goto out; + } goto retry; } addr->hash ^= sk->sk_type; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 6261745..e0d1e2b 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1259,6 +1259,7 @@ long keyctl_session_to_parent(void) keyring_r = NULL; me = current; + rcu_read_lock(); write_lock_irq(&tasklist_lock); parent = me->real_parent; @@ -1291,7 +1292,8 @@ long keyctl_session_to_parent(void) goto not_permitted; /* the keyrings must have the same UID */ - if (pcred->tgcred->session_keyring->uid != mycred->euid || + if ((pcred->tgcred->session_keyring && + pcred->tgcred->session_keyring->uid != mycred->euid) || mycred->tgcred->session_keyring->uid != mycred->euid) goto not_permitted; @@ -1306,6 +1308,7 @@ long keyctl_session_to_parent(void) set_ti_thread_flag(task_thread_info(parent), TIF_NOTIFY_RESUME); write_unlock_irq(&tasklist_lock); + rcu_read_unlock(); if (oldcred) put_cred(oldcred); return 0; @@ -1314,6 +1317,7 @@ already_same: ret = 0; not_permitted: write_unlock_irq(&tasklist_lock); + rcu_read_unlock(); put_cred(cred); return ret; diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index f1e7bab..b8d730c 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -202,6 +202,7 @@ struct sigmatel_spec { unsigned int spdif_mute: 1; unsigned int check_volume_offset:1; unsigned int auto_mic:1; + unsigned int linear_tone_beep:1; /* gpio lines */ unsigned int eapd_mask; @@ -3802,7 +3803,7 @@ static int stac92xx_parse_auto_config(struct hda_codec *codec, hda_nid_t dig_out return err; if (codec->beep) { /* IDT/STAC codecs have linear beep tone parameter */ - codec->beep->linear_tone = 1; + codec->beep->linear_tone = spec->linear_tone_beep; /* if no beep switch is available, make its own one */ caps = query_amp_caps(codec, nid, HDA_OUTPUT); if (!(caps & AC_AMPCAP_MUTE)) { @@ -5005,6 +5006,7 @@ static int patch_stac9200(struct hda_codec *codec) codec->no_trigger_sense = 1; codec->spec = spec; + spec->linear_tone_beep = 1; spec->num_pins = ARRAY_SIZE(stac9200_pin_nids); spec->pin_nids = stac9200_pin_nids; spec->board_config = snd_hda_check_board_config(codec, STAC_9200_MODELS, @@ -5068,6 +5070,7 @@ static int patch_stac925x(struct hda_codec *codec) codec->no_trigger_sense = 1; codec->spec = spec; + spec->linear_tone_beep = 1; spec->num_pins = ARRAY_SIZE(stac925x_pin_nids); spec->pin_nids = stac925x_pin_nids; @@ -5153,6 +5156,7 @@ static int patch_stac92hd73xx(struct hda_codec *codec) codec->no_trigger_sense = 1; codec->spec = spec; + spec->linear_tone_beep = 0; codec->slave_dig_outs = stac92hd73xx_slave_dig_outs; spec->num_pins = ARRAY_SIZE(stac92hd73xx_pin_nids); spec->pin_nids = stac92hd73xx_pin_nids; @@ -5300,6 +5304,7 @@ static int patch_stac92hd83xxx(struct hda_codec *codec) codec->no_trigger_sense = 1; codec->spec = spec; + spec->linear_tone_beep = 1; codec->slave_dig_outs = stac92hd83xxx_slave_dig_outs; spec->digbeep_nid = 0x21; spec->mux_nids = stac92hd83xxx_mux_nids; @@ -5522,6 +5527,7 @@ static int patch_stac92hd71bxx(struct hda_codec *codec) codec->no_trigger_sense = 1; codec->spec = spec; + spec->linear_tone_beep = 0; codec->patch_ops = stac92xx_patch_ops; spec->num_pins = STAC92HD71BXX_NUM_PINS; switch (codec->vendor_id) { @@ -5779,6 +5785,7 @@ static int patch_stac922x(struct hda_codec *codec) codec->no_trigger_sense = 1; codec->spec = spec; + spec->linear_tone_beep = 1; spec->num_pins = ARRAY_SIZE(stac922x_pin_nids); spec->pin_nids = stac922x_pin_nids; spec->board_config = snd_hda_check_board_config(codec, STAC_922X_MODELS, @@ -5883,6 +5890,7 @@ static int patch_stac927x(struct hda_codec *codec) codec->no_trigger_sense = 1; codec->spec = spec; + spec->linear_tone_beep = 1; codec->slave_dig_outs = stac927x_slave_dig_outs; spec->num_pins = ARRAY_SIZE(stac927x_pin_nids); spec->pin_nids = stac927x_pin_nids; @@ -6018,6 +6026,7 @@ static int patch_stac9205(struct hda_codec *codec) codec->no_trigger_sense = 1; codec->spec = spec; + spec->linear_tone_beep = 1; spec->num_pins = ARRAY_SIZE(stac9205_pin_nids); spec->pin_nids = stac9205_pin_nids; spec->board_config = snd_hda_check_board_config(codec, STAC_9205_MODELS, @@ -6174,6 +6183,7 @@ static int patch_stac9872(struct hda_codec *codec) return -ENOMEM; codec->no_trigger_sense = 1; codec->spec = spec; + spec->linear_tone_beep = 1; spec->num_pins = ARRAY_SIZE(stac9872_pin_nids); spec->pin_nids = stac9872_pin_nids; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f032806..2774528 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -566,6 +566,7 @@ int __kvm_set_memory_region(struct kvm *kvm, new = old = *memslot; + new.id = mem->slot; new.base_gfn = base_gfn; new.npages = npages; new.flags = mem->flags;