From 0e52247a2ed1f211f0c4f682dc999610a368903f Mon Sep 17 00:00:00 2001 From: Cam Macdonell Date: Tue, 7 Sep 2010 17:25:20 -0700 Subject: PCI: fix pci_resource_alignment prototype This fixes the prototype for both pci_resource_alignment() and pci_sriov_resource_alignment(). Patch started as debugging effort from Cam Macdonell. Cc: Cam Macdonell Cc: Avi Kivity [chrisw: add iov bits] Signed-off-by: Chris Wright Signed-off-by: Jesse Barnes diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index ce6a366..553d8ee 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -608,7 +608,7 @@ int pci_iov_resource_bar(struct pci_dev *dev, int resno, * the VF BAR size multiplied by the number of VFs. The alignment * is just the VF BAR size. */ -int pci_sriov_resource_alignment(struct pci_dev *dev, int resno) +resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno) { struct resource tmp; enum pci_bar_type type; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 7754a67..6beb11b 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -264,7 +264,8 @@ extern int pci_iov_init(struct pci_dev *dev); extern void pci_iov_release(struct pci_dev *dev); extern int pci_iov_resource_bar(struct pci_dev *dev, int resno, enum pci_bar_type *type); -extern int pci_sriov_resource_alignment(struct pci_dev *dev, int resno); +extern resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, + int resno); extern void pci_restore_iov_state(struct pci_dev *dev); extern int pci_iov_bus_range(struct pci_bus *bus); @@ -320,7 +321,7 @@ static inline int pci_ats_enabled(struct pci_dev *dev) } #endif /* CONFIG_PCI_IOV */ -static inline int pci_resource_alignment(struct pci_dev *dev, +static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, struct resource *res) { #ifdef CONFIG_PCI_IOV -- cgit v0.10.2 From ee05d6939ed17b55e9c2466af32c208e0d547eb8 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 14 Sep 2010 15:15:52 +0200 Subject: vhost-net: fix range checking in mrg bufs case In mergeable buffer case, we use headcount, log_num and seg as indexes in same-size arrays, and we know that headcount <= seg and log_num equals either 0 or seg. Therefore, the right thing to do is range-check seg, not headcount as we do now: these will be different if guest chains s/g descriptors (this does not happen now, but we can not trust the guest). Long term, we should add BUG_ON checks to verify two other indexes are what we think they should be. Reported-by: Jason Wang Signed-off-by: Michael S. Tsirkin diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 29e850a..7c80082 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -243,7 +243,7 @@ static int get_rx_bufs(struct vhost_virtqueue *vq, int r, nlogs = 0; while (datalen > 0) { - if (unlikely(headcount >= VHOST_NET_MAX_SG)) { + if (unlikely(seg >= VHOST_NET_MAX_SG)) { r = -ENOBUFS; goto err; } -- cgit v0.10.2 From 747584be04bb98a856bab5cd1bfe56d341881b83 Mon Sep 17 00:00:00 2001 From: Phil Carmody Date: Tue, 14 Sep 2010 13:34:43 -0700 Subject: [IA64] unwind: remove preprocesser noise, and correct comment The expression in the comment was mis-bracketted. There was also no need to introduce a coding-style breaking macro for a single use, so just made it a static const. Signed-off-by: Phil Carmody Signed-off-by: Tony Luck diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c index b6c0e63..f47217b 100644 --- a/arch/ia64/kernel/unwind.c +++ b/arch/ia64/kernel/unwind.c @@ -1204,10 +1204,10 @@ desc_spill_sprel_p (unsigned char qp, unw_word t, unsigned char abreg, unw_word static inline unw_hash_index_t hash (unsigned long ip) { -# define hashmagic 0x9e3779b97f4a7c16UL /* based on (sqrt(5)/2-1)*2^64 */ + /* magic number = ((sqrt(5)-1)/2)*2^64 */ + static const unsigned long hashmagic = 0x9e3779b97f4a7c16UL; - return (ip >> 4)*hashmagic >> (64 - UNW_LOG_HASH_SIZE); -#undef hashmagic + return (ip >> 4) * hashmagic >> (64 - UNW_LOG_HASH_SIZE); } static inline long -- cgit v0.10.2 From 04a344069052d94b4ea1f95d930cbfa39b4ca292 Mon Sep 17 00:00:00 2001 From: Phil Carmody Date: Tue, 14 Sep 2010 13:35:39 -0700 Subject: [IA64] unwind - optimise linked-list searches for modules It's clear from the comment in the code about keeping the kernel's unwind table at the front of the list that some attention has been paid to access patterns. Tests on other architectures have shown that a move-to-front optimisation improves searches dramatically. Signed-off-by: Phil Carmody Signed-off-by: Tony Luck diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c index f47217b..fed6afa 100644 --- a/arch/ia64/kernel/unwind.c +++ b/arch/ia64/kernel/unwind.c @@ -1531,7 +1531,7 @@ build_script (struct unw_frame_info *info) struct unw_labeled_state *ls, *next; unsigned long ip = info->ip; struct unw_state_record sr; - struct unw_table *table; + struct unw_table *table, *prev; struct unw_reg_info *r; struct unw_insn insn; u8 *dp, *desc_end; @@ -1560,11 +1560,26 @@ build_script (struct unw_frame_info *info) STAT(parse_start = ia64_get_itc()); + prev = NULL; for (table = unw.tables; table; table = table->next) { if (ip >= table->start && ip < table->end) { + /* + * Leave the kernel unwind table at the very front, + * lest moving it breaks some assumption elsewhere. + * Otherwise, move the matching table to the second + * position in the list so that traversals can benefit + * from commonality in backtrace paths. + */ + if (prev && prev != unw.tables) { + /* unw is safe - we're already spinlocked */ + prev->next = table->next; + table->next = unw.tables->next; + unw.tables->next = table; + } e = lookup(table, ip - table->segment_base); break; } + prev = table; } if (!e) { /* no info, return default unwinder (leaf proc, no mem stack, no saved regs) */ -- cgit v0.10.2 From 99f76891a33d130776da3b01935d978b1e75fe68 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 13 Sep 2010 13:38:55 +0100 Subject: ARM: 6375/1: plat-nomadik: MTU timer trivial bug fix timer0 to 3 are all on mtu block 0, so don't calculate the clock event rate based upon mtu block 1's clock speed. Acked-by: Alessandro Rubini Signed-off-by: Jonas Aaberg Signed-off-by: Linus Walleij Signed-off-by: Russell King diff --git a/arch/arm/plat-nomadik/timer.c b/arch/arm/plat-nomadik/timer.c index ea3ca86..d673888 100644 --- a/arch/arm/plat-nomadik/timer.c +++ b/arch/arm/plat-nomadik/timer.c @@ -131,17 +131,12 @@ void __init nmdk_timer_init(void) { unsigned long rate; struct clk *clk0; - struct clk *clk1; u32 cr; clk0 = clk_get_sys("mtu0", NULL); BUG_ON(IS_ERR(clk0)); - clk1 = clk_get_sys("mtu1", NULL); - BUG_ON(IS_ERR(clk1)); - clk_enable(clk0); - clk_enable(clk1); /* * Tick rate is 2.4MHz for Nomadik and 110MHz for ux500: @@ -170,15 +165,8 @@ void __init nmdk_timer_init(void) pr_err("timer: failed to initialize clock source %s\n", nmdk_clksrc.name); - /* Timer 1 is used for events, fix according to rate */ - cr = MTU_CRn_32BITS; - rate = clk_get_rate(clk1); - if (rate > 16 << 20) { - rate /= 16; - cr |= MTU_CRn_PRESCALE_16; - } else { - cr |= MTU_CRn_PRESCALE_1; - } + /* Timer 1 is used for events */ + clockevents_calc_mult_shift(&nmdk_clkevt, rate, MTU_MIN_RANGE); writel(cr | MTU_CRn_ONESHOT, mtu_base + MTU_CR(1)); /* off, currently */ -- cgit v0.10.2 From a0719f52d90aed5b82ecf2f3ed14bc4ced3d1a8a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 13 Sep 2010 13:40:04 +0100 Subject: ARM: 6376/1: plat-nomadik: MTU: Change prescaler limit and comment updates The prescaler 16 is now used only when the timer runs at 32 MHz or more. Some comment updates as well. Acked-by: Alessandro Rubini Signed-off-by: Jonas Aaberg Signed-off-by: Linus Walleij Signed-off-by: Russell King diff --git a/arch/arm/plat-nomadik/timer.c b/arch/arm/plat-nomadik/timer.c index d673888..aedf9c1 100644 --- a/arch/arm/plat-nomadik/timer.c +++ b/arch/arm/plat-nomadik/timer.c @@ -1,5 +1,5 @@ /* - * linux/arch/arm/mach-nomadik/timer.c + * linux/arch/arm/plat-nomadik/timer.c * * Copyright (C) 2008 STMicroelectronics * Copyright (C) 2010 Alessandro Rubini @@ -75,7 +75,7 @@ static void nmdk_clkevt_mode(enum clock_event_mode mode, cr = readl(mtu_base + MTU_CR(1)); writel(0, mtu_base + MTU_LR(1)); writel(cr | MTU_CRn_ENA, mtu_base + MTU_CR(1)); - writel(0x2, mtu_base + MTU_IMSC); + writel(1 << 1, mtu_base + MTU_IMSC); break; case CLOCK_EVT_MODE_SHUTDOWN: case CLOCK_EVT_MODE_UNUSED: @@ -131,7 +131,7 @@ void __init nmdk_timer_init(void) { unsigned long rate; struct clk *clk0; - u32 cr; + u32 cr = MTU_CRn_32BITS; clk0 = clk_get_sys("mtu0", NULL); BUG_ON(IS_ERR(clk0)); @@ -139,12 +139,15 @@ void __init nmdk_timer_init(void) clk_enable(clk0); /* - * Tick rate is 2.4MHz for Nomadik and 110MHz for ux500: - * use a divide-by-16 counter if it's more than 16MHz + * Tick rate is 2.4MHz for Nomadik and 2.4Mhz, 100MHz or 133 MHz + * for ux500. + * Use a divide-by-16 counter if the tick rate is more than 32MHz. + * At 32 MHz, the timer (with 32 bit counter) can be programmed + * to wake-up at a max 127s a head in time. Dividing a 2.4 MHz timer + * with 16 gives too low timer resolution. */ - cr = MTU_CRn_32BITS;; rate = clk_get_rate(clk0); - if (rate > 16 << 20) { + if (rate > 32000000) { rate /= 16; cr |= MTU_CRn_PRESCALE_16; } else { -- cgit v0.10.2 From 63f469324f999a28e67b90eb27a5fe0e379b7064 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 13 Sep 2010 13:44:47 +0100 Subject: ARM: 6377/1: supply _cansleep gpio function to U300 We have to use _cansleep gpio accessors in the MMCI driver so as to avoid slowpath warnings, now U300 has MMCI but doesn't have these functions in place to siply wrap the existing non-sleeping functions into sleepable variants. Signed-off-by: Linus Walleij Signed-off-by: Russell King diff --git a/arch/arm/mach-u300/include/mach/gpio.h b/arch/arm/mach-u300/include/mach/gpio.h index 7b1fc98..d5a71ab 100644 --- a/arch/arm/mach-u300/include/mach/gpio.h +++ b/arch/arm/mach-u300/include/mach/gpio.h @@ -273,6 +273,9 @@ extern void gpio_pullup(unsigned gpio, int value); extern int gpio_get_value(unsigned gpio); extern void gpio_set_value(unsigned gpio, int value); +#define gpio_get_value_cansleep gpio_get_value +#define gpio_set_value_cansleep gpio_set_value + /* wrappers to sleep-enable the previous two functions */ static inline unsigned gpio_to_irq(unsigned gpio) { -- cgit v0.10.2 From 6491848d1ab246f6d243ddef25085fc1d836ff2c Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 14 Sep 2010 09:50:03 +0100 Subject: ARM: 6387/1: errata: check primary part ID in proc-v7.S Kconfig doesn't have any knowledge of specific v7 cores, so it is possible to select errata workarounds that may cause inadvertent behaviour when executed on a core other than those targetted by the fix. This patch improves the variant and revision checking in proc-v7.S so that the primary part number is also considered when applying errata workarounds. Acked-by: Catalin Marinas Signed-off-by: Will Deacon Signed-off-by: Russell King diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 6a8506d..1f16f9e 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -204,8 +204,13 @@ __v7_setup: bne 2f and r5, r0, #0x00f00000 @ variant and r6, r0, #0x0000000f @ revision - orr r0, r6, r5, lsr #20-4 @ combine variant and revision + orr r6, r6, r5, lsr #20-4 @ combine variant and revision + ubfx r0, r0, #4, #12 @ primary part number + /* Cortex-A8 Errata */ + ldr r10, =0x00000c08 @ Cortex-A8 primary part number + teq r0, r10 + bne 2f #ifdef CONFIG_ARM_ERRATA_430973 teq r5, #0x00100000 @ only present in r1p* mrceq p15, 0, r10, c1, c0, 1 @ read aux control register @@ -213,14 +218,14 @@ __v7_setup: mcreq p15, 0, r10, c1, c0, 1 @ write aux control register #endif #ifdef CONFIG_ARM_ERRATA_458693 - teq r0, #0x20 @ only present in r2p0 + teq r6, #0x20 @ only present in r2p0 mrceq p15, 0, r10, c1, c0, 1 @ read aux control register orreq r10, r10, #(1 << 5) @ set L1NEON to 1 orreq r10, r10, #(1 << 9) @ set PLDNOP to 1 mcreq p15, 0, r10, c1, c0, 1 @ write aux control register #endif #ifdef CONFIG_ARM_ERRATA_460075 - teq r0, #0x20 @ only present in r2p0 + teq r6, #0x20 @ only present in r2p0 mrceq p15, 1, r10, c9, c0, 2 @ read L2 cache aux ctrl register tsteq r10, #1 << 22 orreq r10, r10, #(1 << 22) @ set the Write Allocate disable bit -- cgit v0.10.2 From 9f05027c7cb3cfe56a31892bd83391138d41a667 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 14 Sep 2010 09:51:43 +0100 Subject: ARM: 6388/1: errata: DMB operation may be faulty On versions of the Cortex-A9 up to and including r2p2, under rare circumstances, a DMB instruction between 2 write operations may not ensure the correct visibility ordering of the 2 writes. This workaround sets a bit in the diagnostic register of the Cortex-A9, causing the DMB instruction to behave like a DSB, which functions correctly on the affected cores. Acked-by: Catalin Marinas Signed-off-by: Will Deacon Signed-off-by: Russell King diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 553b7cf..ab14c0a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1051,6 +1051,18 @@ config ARM_ERRATA_460075 ACTLR register. Note that setting specific bits in the ACTLR register may not be available in non-secure mode. +config ARM_ERRATA_742230 + bool "ARM errata: DMB operation may be faulty" + depends on CPU_V7 && SMP + help + This option enables the workaround for the 742230 Cortex-A9 + (r1p0..r2p2) erratum. Under rare circumstances, a DMB instruction + between two write operations may not ensure the correct visibility + ordering of the two writes. This workaround sets a specific bit in + the diagnostic register of the Cortex-A9 which causes the DMB + instruction to behave as a DSB, ensuring the correct behaviour of + the two writes. + config PL310_ERRATA_588369 bool "Clean & Invalidate maintenance operations do not invalidate clean lines" depends on CACHE_L2X0 && ARCH_OMAP4 diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 1f16f9e..945f363 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -201,7 +201,7 @@ __v7_setup: mrc p15, 0, r0, c0, c0, 0 @ read main ID register and r10, r0, #0xff000000 @ ARM? teq r10, #0x41000000 - bne 2f + bne 3f and r5, r0, #0x00f00000 @ variant and r6, r0, #0x0000000f @ revision orr r6, r6, r5, lsr #20-4 @ combine variant and revision @@ -231,8 +231,20 @@ __v7_setup: orreq r10, r10, #(1 << 22) @ set the Write Allocate disable bit mcreq p15, 1, r10, c9, c0, 2 @ write the L2 cache aux ctrl register #endif + b 3f + + /* Cortex-A9 Errata */ +2: ldr r10, =0x00000c09 @ Cortex-A9 primary part number + teq r0, r10 + bne 3f +#ifdef CONFIG_ARM_ERRATA_742230 + cmp r6, #0x22 @ only present up to r2p2 + mrcle p15, 0, r10, c15, c0, 1 @ read diagnostic register + orrle r10, r10, #1 << 4 @ set bit #4 + mcrle p15, 0, r10, c15, c0, 1 @ write diagnostic register +#endif -2: mov r10, #0 +3: mov r10, #0 #ifdef HARVARD_CACHE mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate #endif -- cgit v0.10.2 From a672e99b129e286df2e2697a1b603d82321117f3 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 14 Sep 2010 09:53:02 +0100 Subject: ARM: 6389/1: errata: incorrect hazard handling in the SCU may lead to data corruption On the r2p0, r2p1 and r2p2 versions of the Cortex-A9, data corruption can occur if a shared cache line is replaced on one CPU as another CPU is accessing it. This workaround sets two bits in the diagnostic register of the Cortex-A9, reducing the linefill issuing capabilities of the processor and avoiding the erroneous behaviour. Acked-by: Catalin Marinas Signed-off-by: Will Deacon Signed-off-by: Russell King diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index ab14c0a..0f89335 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1063,6 +1063,20 @@ config ARM_ERRATA_742230 instruction to behave as a DSB, ensuring the correct behaviour of the two writes. +config ARM_ERRATA_742231 + bool "ARM errata: Incorrect hazard handling in the SCU may lead to data corruption" + depends on CPU_V7 && SMP + help + This option enables the workaround for the 742231 Cortex-A9 + (r2p0..r2p2) erratum. Under certain conditions, specific to the + Cortex-A9 MPCore micro-architecture, two CPUs working in SMP mode, + accessing some data located in the same cache line, may get corrupted + data due to bad handling of the address hazard when the line gets + replaced from one of the CPUs at the same time as another CPU is + accessing it. This workaround sets specific bits in the diagnostic + register of the Cortex-A9 which reduces the linefill issuing + capabilities of the processor. + config PL310_ERRATA_588369 bool "Clean & Invalidate maintenance operations do not invalidate clean lines" depends on CACHE_L2X0 && ARCH_OMAP4 diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 945f363..0801292 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -243,6 +243,15 @@ __v7_setup: orrle r10, r10, #1 << 4 @ set bit #4 mcrle p15, 0, r10, c15, c0, 1 @ write diagnostic register #endif +#ifdef CONFIG_ARM_ERRATA_742231 + teq r6, #0x20 @ present in r2p0 + teqne r6, #0x21 @ present in r2p1 + teqne r6, #0x22 @ present in r2p2 + mrceq p15, 0, r10, c15, c0, 1 @ read diagnostic register + orreq r10, r10, #1 << 12 @ set bit #12 + orreq r10, r10, #1 << 22 @ set bit #22 + mcreq p15, 0, r10, c15, c0, 1 @ write diagnostic register +#endif 3: mov r10, #0 #ifdef HARVARD_CACHE -- cgit v0.10.2 From 1a8e41cd672f894bbd74874eac601e6cedf838fb Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Thu, 16 Sep 2010 17:57:17 +0100 Subject: ARM: 6395/1: VExpress: Set bit 22 in the PL310 (cache controller) AuxCtlr register Clearing bit 22 in the PL310 Auxiliary Control register (shared attribute override enable) has the side effect of transforming Normal Shared Non-cacheable reads into Cacheable no-allocate reads. Coherent DMA buffers in Linux always have a Cacheable alias via the kernel linear mapping and the processor can speculatively load cache lines into the PL310 controller. With bit 22 cleared, Non-cacheable reads would unexpectedly hit such cache lines leading to buffer corruption. Cc: Nicolas Pitre Cc: Signed-off-by: Catalin Marinas Signed-off-by: Russell King diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c index 577df6c..1c9c13e 100644 --- a/arch/arm/mach-vexpress/ct-ca9x4.c +++ b/arch/arm/mach-vexpress/ct-ca9x4.c @@ -227,7 +227,7 @@ static void ct_ca9x4_init(void) int i; #ifdef CONFIG_CACHE_L2X0 - l2x0_init(MMIO_P2V(CT_CA9X4_L2CC), 0x00000000, 0xfe0fffff); + l2x0_init(MMIO_P2V(CT_CA9X4_L2CC), 0x00400000, 0xfe0fffff); #endif clkdev_add_table(lookups, ARRAY_SIZE(lookups)); -- cgit v0.10.2 From b2b163bb82b12bae2504a5b31399c37d099ad3cc Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 17 Sep 2010 14:56:16 +0100 Subject: ARM: prevent multiple syscall restarts Al Viro reports that calling "sys_sigsuspend(-ERESTARTNOHAND, 0, 0)" with two signals coming and being handled in kernel space results in the syscall restart being done twice. Avoid this by clearing the 'why' flag when we call the signal handling code to prevent further syscall restarts after the first. Acked-by: Al Viro Signed-off-by: Russell King diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index f05a35a..4a560d3 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -48,6 +48,8 @@ work_pending: beq no_work_pending mov r0, sp @ 'regs' mov r2, why @ 'syscall' + tst r1, #_TIF_SIGPENDING @ delivering a signal? + movne why, #0 @ prevent further restarts bl do_notify_resume b ret_slow_syscall @ Check work again -- cgit v0.10.2 From 14eff1812679c76564b775aa95cdd378965f6cfb Mon Sep 17 00:00:00 2001 From: Daniel Walker Date: Fri, 17 Sep 2010 16:42:10 +0100 Subject: ARM: 6398/1: add proc info for ARM11MPCore/Cortex-A9 from ARM Setting of these bits can cause issues on other SMP SoC's not produced by ARM. Acked-by: Catalin Marinas Signed-off-by: Daniel Walker Signed-off-by: Russell King diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 0801292..7563ff0 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -186,13 +186,14 @@ cpu_v7_name: * It is assumed that: * - cache type register is implemented */ -__v7_setup: +__v7_ca9mp_setup: #ifdef CONFIG_SMP mrc p15, 0, r0, c1, c0, 1 tst r0, #(1 << 6) @ SMP/nAMP mode enabled? orreq r0, r0, #(1 << 6) | (1 << 0) @ Enable SMP/nAMP mode and mcreq p15, 0, r0, c1, c0, 1 @ TLB ops broadcasting #endif +__v7_setup: adr r12, __v7_setup_stack @ the local stack stmia r12, {r0-r5, r7, r9, r11, lr} bl v7_flush_dcache_all @@ -349,6 +350,29 @@ cpu_elf_name: .section ".proc.info.init", #alloc, #execinstr + .type __v7_ca9mp_proc_info, #object +__v7_ca9mp_proc_info: + .long 0x410fc090 @ Required ID value + .long 0xff0ffff0 @ Mask for ID + .long PMD_TYPE_SECT | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ | \ + PMD_FLAGS + .long PMD_TYPE_SECT | \ + PMD_SECT_XN | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ + b __v7_ca9mp_setup + .long cpu_arch_name + .long cpu_elf_name + .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP + .long cpu_v7_name + .long v7_processor_functions + .long v7wbi_tlb_fns + .long v6_user_fns + .long v7_cache_fns + .size __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info + /* * Match any ARMv7 processor core. */ -- cgit v0.10.2 From 7acc7c683a747689aaaaad4fce1683fc3f85e552 Mon Sep 17 00:00:00 2001 From: Wey-Yi Guy Date: Wed, 8 Sep 2010 08:30:20 -0700 Subject: iwlwifi: do not perferm force reset while doing scan When uCode error condition detected, driver try to perform either rf reset or firmware reload in order bring device back to working condition. If rf reset is required and scan is in process, there is no need to issue rf reset since scan already reset the rf. If firmware reload is required and scan is in process, skip the reload request. There is a possibility firmware reload during scan cause problem. [ 485.804046] WARNING: at net/mac80211/main.c:310 ieee80211_restart_hw+0x28/0x62() [ 485.804049] Hardware name: Latitude E6400 [ 485.804052] ieee80211_restart_hw called with hardware scan in progress [ 485.804054] Modules linked in: iwlagn iwlcore bnep sco rfcomm l2cap crc16 bluetooth [last unloaded: iwlcore] [ 485.804069] Pid: 812, comm: kworker/u:3 Tainted: G W 2.6.36-rc3-wl+ #74 [ 485.804072] Call Trace: [ 485.804079] [] warn_slowpath_common+0x60/0x75 [ 485.804084] [] warn_slowpath_fmt+0x26/0x2a [ 485.804089] [] ieee80211_restart_hw+0x28/0x62 [ 485.804102] [] iwl_bg_restart+0x113/0x150 [iwlagn] [ 485.804108] [] process_one_work+0x181/0x25c [ 485.804119] [] ? iwl_bg_restart+0x0/0x150 [iwlagn] [ 485.804124] [] worker_thread+0xf9/0x1f2 [ 485.804128] [] ? worker_thread+0x0/0x1f2 [ 485.804133] [] kthread+0x64/0x69 [ 485.804137] [] ? kthread+0x0/0x69 [ 485.804141] [] kernel_thread_helper+0x6/0x10 [ 485.804145] ---[ end trace 3d4ebdc02d524bbb ]--- [ 485.804148] WG> 1 [ 485.804153] Pid: 812, comm: kworker/u:3 Tainted: G W 2.6.36-rc3-wl+ #74 [ 485.804156] Call Trace: [ 485.804161] [] ? ieee80211_restart_hw+0x5c/0x62 [ 485.804172] [] iwl_bg_restart+0x118/0x150 [iwlagn] [ 485.804177] [] process_one_work+0x181/0x25c [ 485.804188] [] ? iwl_bg_restart+0x0/0x150 [iwlagn] [ 485.804192] [] worker_thread+0xf9/0x1f2 [ 485.804197] [] ? worker_thread+0x0/0x1f2 [ 485.804201] [] kthread+0x64/0x69 [ 485.804205] [] ? kthread+0x0/0x69 [ 485.804209] [] kernel_thread_helper+0x6/0x10 Signed-off-by: Wey-Yi Guy diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c index 07dbc27..e23c406 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.c +++ b/drivers/net/wireless/iwlwifi/iwl-core.c @@ -2613,6 +2613,11 @@ int iwl_force_reset(struct iwl_priv *priv, int mode, bool external) if (test_bit(STATUS_EXIT_PENDING, &priv->status)) return -EINVAL; + if (test_bit(STATUS_SCANNING, &priv->status)) { + IWL_DEBUG_INFO(priv, "scan in progress.\n"); + return -EINVAL; + } + if (mode >= IWL_MAX_FORCE_RESET) { IWL_DEBUG_INFO(priv, "invalid reset request.\n"); return -EINVAL; -- cgit v0.10.2 From 04746ff1289f75af26af279eb4b0b3e231677ee4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 17 Sep 2010 22:58:08 -0700 Subject: qlcnic: dont assume NET_IP_ALIGN is 2 qlcnic driver allocates rx skbs and gives to hardware too bytes of extra storage, allowing for corruption of kernel data. NET_IP_ALIGN being 0 on some platforms (including x86), drivers should not assume it's 2. rds_ring->skb_size = rds_ring->dma_size + NET_IP_ALIGN; ... skb = dev_alloc_skb(rds_ring->skb_size); skb_reserve(skb, 2); pci_map_single(pdev, skb->data, rds_ring->dma_size, PCI_DMA_FROMDEVICE); (and rds_ring->skb_size == rds_ring->dma_size) -> bug Because of extra alignment (1500 + 32) -> four extra bytes are available before the struct skb_shared_info, so corruption is not noticed. Note: this driver could use netdev_alloc_skb_ip_align() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller diff --git a/drivers/net/qlcnic/qlcnic_init.c b/drivers/net/qlcnic/qlcnic_init.c index 75ba744..60ab753 100644 --- a/drivers/net/qlcnic/qlcnic_init.c +++ b/drivers/net/qlcnic/qlcnic_init.c @@ -1316,7 +1316,7 @@ qlcnic_alloc_rx_skb(struct qlcnic_adapter *adapter, return -ENOMEM; } - skb_reserve(skb, 2); + skb_reserve(skb, NET_IP_ALIGN); dma = pci_map_single(pdev, skb->data, rds_ring->dma_size, PCI_DMA_FROMDEVICE); -- cgit v0.10.2 From 7cdffc86528ec9c55c83c649b6d64cadeb558136 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sat, 18 Sep 2010 10:19:13 +0200 Subject: pcmcia: preserve configuration information if request_io fails partly If pcmcia_request_io() only fails partly -- for the second of two requested resources -- preserve the configuration settings for the first one. Signed-off-by: Dominik Brodowski diff --git a/drivers/pcmcia/pcmcia_resource.c b/drivers/pcmcia/pcmcia_resource.c index a5c1765..9ba4dad 100644 --- a/drivers/pcmcia/pcmcia_resource.c +++ b/drivers/pcmcia/pcmcia_resource.c @@ -595,7 +595,13 @@ int pcmcia_request_io(struct pcmcia_device *p_dev) if (c->io[1].end) { ret = alloc_io_space(s, &c->io[1], p_dev->io_lines); if (ret) { + struct resource tmp = c->io[0]; + /* release the previously allocated resource */ release_io_space(s, &c->io[0]); + /* but preserve the settings, for they worked... */ + c->io[0].end = resource_size(&tmp); + c->io[0].start = tmp.start; + c->io[0].flags = tmp.flags; goto out; } } else -- cgit v0.10.2 From 79e27dc0677b969e2d53b76fa0fa58467cce946a Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Sat, 18 Sep 2010 19:55:10 +0100 Subject: ARM: 6400/1: at91: fix arch_gettimeoffset fallout 5cfc8ee0bb51 (ARM: convert arm to arch_gettimeoffset()) marked all of at91 AND at91x40 as needing ARCH_USES_GETTIMEOFFSET, and hence no high res timer support / accurate clock_gettime() - But only at91x40 needs it. Cc: stable@kernel.org Signed-off-by: Peter Korsgaard Acked-by: John Stultz Acked-by: Jean-Christophe PLAGNIOL-VILLARD Signed-off-by: Russell King diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 0f89335..88c97bc 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -271,7 +271,6 @@ config ARCH_AT91 bool "Atmel AT91" select ARCH_REQUIRE_GPIOLIB select HAVE_CLK - select ARCH_USES_GETTIMEOFFSET help This enables support for systems based on the Atmel AT91RM9200, AT91SAM9 and AT91CAP9 processors. -- cgit v0.10.2 From d907387c42e9e39261629890e45a08ef4c3ed3fe Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 13 Sep 2010 16:01:24 +0100 Subject: ARM: 6383/1: Implement phys_mem_access_prot() to avoid attributes aliasing ARMv7 onwards requires that there are no aliases to the same physical location using different memory types (i.e. Normal vs Strongly Ordered). Access to SO mappings when the unaligned accesses are handled in hardware is also Unpredictable (pgprot_noncached() mappings in user space). The /dev/mem driver requires uncached mappings with O_SYNC. The patch implements the phys_mem_access_prot() function which generates Strongly Ordered memory attributes if !pfn_valid() (independent of O_SYNC) and Normal Noncacheable (writecombine) if O_SYNC. Signed-off-by: Catalin Marinas Signed-off-by: Russell King diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index ab68cf1..e90b167 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -317,6 +317,10 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; } #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE) +#define __HAVE_PHYS_MEM_ACCESS_PROT +struct file; +extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); #else #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED) diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 6e1c4f6..a486bd0 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -498,6 +499,19 @@ static void __init build_mem_type_table(void) } } +#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE +pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot) +{ + if (!pfn_valid(pfn)) + return pgprot_noncached(vma_prot); + else if (file->f_flags & O_SYNC) + return pgprot_writecombine(vma_prot); + return vma_prot; +} +EXPORT_SYMBOL(phys_mem_access_prot); +#endif + #define vectors_base() (vectors_high() ? 0xffff0000 : 0) static void __init *early_alloc(unsigned long sz) -- cgit v0.10.2 From d93c333dc867d04111c9dcebdbcaa9ae8b2d5c2d Mon Sep 17 00:00:00 2001 From: Russell King Date: Sun, 19 Sep 2010 16:16:58 +0100 Subject: ARM: Fix build error when using KCONFIG_CONFIG Jonathan Cameron reports that when using the environment variable KCONFIG_CONFIG, he encounters this error: make[2]: *** No rule to make target `.config', needed by `arch/arm/boot/compressed/vmlinux.lds' Reported-by: Jonathan Cameron Signed-off-by: Russell King diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index b23f6bc..65a7c1c 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -116,5 +116,5 @@ CFLAGS_font.o := -Dstatic= $(obj)/font.c: $(FONTC) $(call cmd,shipped) -$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile .config +$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG) @sed "$(SEDFLAGS)" < $< > $@ -- cgit v0.10.2 From e4ff1c39ee1122198e8355069da59297038e55bb Mon Sep 17 00:00:00 2001 From: Arnaud Patard Date: Sun, 22 Aug 2010 22:49:46 +0200 Subject: ARM: kirkwood: Unbreak PCIe I/O port The support for the 2 pcie port of the 6282 has broken i/o port by switching *_IO_PHYS_BASE and *_IO_BUS_BASE. In fact, the patches reintroduced the same bug solved by commit 35f029e2514be209eb0e88c7d927f3bcc42a5cc2. So, I'm adding back *_IO_BUS_BASE in resource declaration and fix definition of KIRKWOOD_PCIE1_IO_BUS_BASE. With this change, the xgi card on my t5325 is working again. Signed-off-by: Arnaud Patard Acked-by: Saeed Bishara Signed-off-by: Nicolas Pitre Cc: stable@kernel.org diff --git a/arch/arm/mach-kirkwood/include/mach/kirkwood.h b/arch/arm/mach-kirkwood/include/mach/kirkwood.h index 93fc2ec..6e924b3 100644 --- a/arch/arm/mach-kirkwood/include/mach/kirkwood.h +++ b/arch/arm/mach-kirkwood/include/mach/kirkwood.h @@ -38,7 +38,7 @@ #define KIRKWOOD_PCIE1_IO_PHYS_BASE 0xf3000000 #define KIRKWOOD_PCIE1_IO_VIRT_BASE 0xfef00000 -#define KIRKWOOD_PCIE1_IO_BUS_BASE 0x00000000 +#define KIRKWOOD_PCIE1_IO_BUS_BASE 0x00100000 #define KIRKWOOD_PCIE1_IO_SIZE SZ_1M #define KIRKWOOD_PCIE_IO_PHYS_BASE 0xf2000000 diff --git a/arch/arm/mach-kirkwood/pcie.c b/arch/arm/mach-kirkwood/pcie.c index 55e7f00..513ad31 100644 --- a/arch/arm/mach-kirkwood/pcie.c +++ b/arch/arm/mach-kirkwood/pcie.c @@ -117,7 +117,7 @@ static void __init pcie0_ioresources_init(struct pcie_port *pp) * IORESOURCE_IO */ pp->res[0].name = "PCIe 0 I/O Space"; - pp->res[0].start = KIRKWOOD_PCIE_IO_PHYS_BASE; + pp->res[0].start = KIRKWOOD_PCIE_IO_BUS_BASE; pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE_IO_SIZE - 1; pp->res[0].flags = IORESOURCE_IO; @@ -139,7 +139,7 @@ static void __init pcie1_ioresources_init(struct pcie_port *pp) * IORESOURCE_IO */ pp->res[0].name = "PCIe 1 I/O Space"; - pp->res[0].start = KIRKWOOD_PCIE1_IO_PHYS_BASE; + pp->res[0].start = KIRKWOOD_PCIE1_IO_BUS_BASE; pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE1_IO_SIZE - 1; pp->res[0].flags = IORESOURCE_IO; -- cgit v0.10.2 From 863636828f1fcd9fdc15e24d620aa53cf18b432f Mon Sep 17 00:00:00 2001 From: Simon Guinot Date: Fri, 17 Sep 2010 23:33:51 +0200 Subject: dmaengine: fix interrupt clearing for mv_xor When using simultaneously the two DMA channels on a same engine, some transfers are never completed. For example, an endless lock can occur while writing heavily on a RAID5 array (with async-tx offload support enabled). Note that this issue can also be reproduced by using the DMA test client. On a same engine, the interrupt cause register is shared between two DMA channels. This patch make sure that the cause bit is only cleared for the requested channel. Signed-off-by: Simon Guinot Tested-by: Luc Saillard Acked-by: Saeed Bishara Signed-off-by: Nicolas Pitre diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 86c5ae9..411d5bf 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -162,7 +162,7 @@ static int mv_is_err_intr(u32 intr_cause) static void mv_xor_device_clear_eoc_cause(struct mv_xor_chan *chan) { - u32 val = (1 << (1 + (chan->idx * 16))); + u32 val = ~(1 << (chan->idx * 16)); dev_dbg(chan->device->common.dev, "%s, val 0x%08x\n", __func__, val); __raw_writel(val, XOR_INTR_CAUSE(chan)); } -- cgit v0.10.2 From c4a90588fa07ea47df7a67fd6cb03d6bc0f99634 Mon Sep 17 00:00:00 2001 From: Eric Miao Date: Tue, 14 Sep 2010 16:14:15 +0800 Subject: ARM: dove: fix __io() definition to use bus based offset Signed-off-by: Eric Miao Acked-by: Saeed Bishara Signed-off-by: Nicolas Pitre diff --git a/arch/arm/mach-dove/include/mach/io.h b/arch/arm/mach-dove/include/mach/io.h index 3b3e472..eb4936f 100644 --- a/arch/arm/mach-dove/include/mach/io.h +++ b/arch/arm/mach-dove/include/mach/io.h @@ -13,8 +13,8 @@ #define IO_SPACE_LIMIT 0xffffffff -#define __io(a) ((void __iomem *)(((a) - DOVE_PCIE0_IO_PHYS_BASE) +\ - DOVE_PCIE0_IO_VIRT_BASE)) -#define __mem_pci(a) (a) +#define __io(a) ((void __iomem *)(((a) - DOVE_PCIE0_IO_BUS_BASE) + \ + DOVE_PCIE0_IO_VIRT_BASE)) +#define __mem_pci(a) (a) #endif -- cgit v0.10.2 From f539dfedbd169e5ed47912bb517c75976ab556f3 Mon Sep 17 00:00:00 2001 From: Simon Guinot Date: Sun, 19 Sep 2010 15:30:59 +0200 Subject: leds: leds-ns2: fix locking This patch replace all the lock functions with the irq safe variant. The ns2_led_{set,get}_mode() functions must be safe in all context. For example, the trigger timer call led_set_brightness() in a softirq context. Signed-off-by: Simon Guinot Signed-off-by: Nicolas Pitre diff --git a/drivers/leds/leds-ns2.c b/drivers/leds/leds-ns2.c index 74dce4b..350eb34 100644 --- a/drivers/leds/leds-ns2.c +++ b/drivers/leds/leds-ns2.c @@ -81,7 +81,7 @@ static int ns2_led_get_mode(struct ns2_led_data *led_dat, int cmd_level; int slow_level; - read_lock(&led_dat->rw_lock); + read_lock_irq(&led_dat->rw_lock); cmd_level = gpio_get_value(led_dat->cmd); slow_level = gpio_get_value(led_dat->slow); @@ -95,7 +95,7 @@ static int ns2_led_get_mode(struct ns2_led_data *led_dat, } } - read_unlock(&led_dat->rw_lock); + read_unlock_irq(&led_dat->rw_lock); return ret; } @@ -104,8 +104,9 @@ static void ns2_led_set_mode(struct ns2_led_data *led_dat, enum ns2_led_modes mode) { int i; + unsigned long flags; - write_lock(&led_dat->rw_lock); + write_lock_irqsave(&led_dat->rw_lock, flags); for (i = 0; i < ARRAY_SIZE(ns2_led_modval); i++) { if (mode == ns2_led_modval[i].mode) { @@ -116,7 +117,7 @@ static void ns2_led_set_mode(struct ns2_led_data *led_dat, } } - write_unlock(&led_dat->rw_lock); + write_unlock_irqrestore(&led_dat->rw_lock, flags); } static void ns2_led_set(struct led_classdev *led_cdev, -- cgit v0.10.2 From 842c74bffcdb1d305ccd9e61e417cceae86b9963 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 20 Sep 2010 10:06:12 -0700 Subject: ip_gre: CONFIG_IPV6_MODULE support ipv6 can be a module, we should test CONFIG_IPV6 and CONFIG_IPV6_MODULE to enable ipv6 bits in ip_gre. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 945b20a..35c93e8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -45,7 +45,7 @@ #include #include -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) #include #include #include @@ -699,7 +699,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if ((dst = rt->rt_gateway) == 0) goto tx_error_icmp; } -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; int addr_type; @@ -774,7 +774,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev goto tx_error; } } -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); @@ -850,7 +850,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if ((iph->ttl = tiph->ttl) == 0) { if (skb->protocol == htons(ETH_P_IP)) iph->ttl = old_iph->ttl; -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit; #endif -- cgit v0.10.2 From df6d02300f7c2fbd0fbe626d819c8e5237d72c62 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 17 Sep 2010 00:38:25 +0200 Subject: wext: fix potential private ioctl memory content leak When a driver doesn't fill the entire buffer, old heap contents may remain, and if it also doesn't update the length properly, this old heap content will be copied back to userspace. It is very unlikely that this happens in any of the drivers using private ioctls since it would show up as junk being reported by iwpriv, but it seems better to be safe here, so use kzalloc. Reported-by: Jeff Mahoney Cc: stable@kernel.org Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/net/wireless/wext-priv.c b/net/wireless/wext-priv.c index 3feb28e..674d426 100644 --- a/net/wireless/wext-priv.c +++ b/net/wireless/wext-priv.c @@ -152,7 +152,7 @@ static int ioctl_private_iw_point(struct iw_point *iwp, unsigned int cmd, } else if (!iwp->pointer) return -EFAULT; - extra = kmalloc(extra_size, GFP_KERNEL); + extra = kzalloc(extra_size, GFP_KERNEL); if (!extra) return -ENOMEM; -- cgit v0.10.2 From 8444cf712c5f71845cba9dc30d8f530ff0d5ff83 Mon Sep 17 00:00:00 2001 From: Thomas Egerer Date: Mon, 20 Sep 2010 11:11:38 -0700 Subject: xfrm: Allow different selector family in temporary state The family parameter xfrm_state_find is used to find a state matching a certain policy. This value is set to the template's family (encap_family) right before xfrm_state_find is called. The family parameter is however also used to construct a temporary state in xfrm_state_find itself which is wrong for inter-family scenarios because it produces a selector for the wrong family. Since this selector is included in the xfrm_user_acquire structure, user space programs misinterpret IPv6 addresses as IPv4 and vice versa. This patch splits up the original init_tempsel function into a part that initializes the selector respectively the props and id of the temporary state, to allow for differing ip address families whithin the state. Signed-off-by: Thomas Egerer Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller diff --git a/include/net/xfrm.h b/include/net/xfrm.h index fc8f36d..4f53532 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -298,8 +298,8 @@ struct xfrm_state_afinfo { const struct xfrm_type *type_map[IPPROTO_MAX]; struct xfrm_mode *mode_map[XFRM_MODE_MAX]; int (*init_flags)(struct xfrm_state *x); - void (*init_tempsel)(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, + void (*init_tempsel)(struct xfrm_selector *sel, struct flowi *fl); + void (*init_temprop)(struct xfrm_state *x, struct xfrm_tmpl *tmpl, xfrm_address_t *daddr, xfrm_address_t *saddr); int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 1ef1366..4794762 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -21,21 +21,25 @@ static int xfrm4_init_flags(struct xfrm_state *x) } static void -__xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) +{ + sel->daddr.a4 = fl->fl4_dst; + sel->saddr.a4 = fl->fl4_src; + sel->dport = xfrm_flowi_dport(fl); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET; + sel->prefixlen_d = 32; + sel->prefixlen_s = 32; + sel->proto = fl->proto; + sel->ifindex = fl->oif; +} + +static void +xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr) { - x->sel.daddr.a4 = fl->fl4_dst; - x->sel.saddr.a4 = fl->fl4_src; - x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = htons(0xffff); - x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = htons(0xffff); - x->sel.family = AF_INET; - x->sel.prefixlen_d = 32; - x->sel.prefixlen_s = 32; - x->sel.proto = fl->proto; - x->sel.ifindex = fl->oif; x->id = tmpl->id; if (x->id.daddr.a4 == 0) x->id.daddr.a4 = daddr->a4; @@ -70,6 +74,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .owner = THIS_MODULE, .init_flags = xfrm4_init_flags, .init_tempsel = __xfrm4_init_tempsel, + .init_temprop = xfrm4_init_temprop, .output = xfrm4_output, .extract_input = xfrm4_extract_input, .extract_output = xfrm4_extract_output, diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index f417b77..a67575d 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -20,23 +20,27 @@ #include static void -__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) { /* Initialize temporary selector matching only * to current session. */ - ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst); - ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src); - x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = htons(0xffff); - x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = htons(0xffff); - x->sel.family = AF_INET6; - x->sel.prefixlen_d = 128; - x->sel.prefixlen_s = 128; - x->sel.proto = fl->proto; - x->sel.ifindex = fl->oif; + ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst); + ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src); + sel->dport = xfrm_flowi_dport(fl); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET6; + sel->prefixlen_d = 128; + sel->prefixlen_s = 128; + sel->proto = fl->proto; + sel->ifindex = fl->oif; +} + +static void +xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr) +{ x->id = tmpl->id; if (ipv6_addr_any((struct in6_addr*)&x->id.daddr)) memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); @@ -168,6 +172,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = { .eth_proto = htons(ETH_P_IPV6), .owner = THIS_MODULE, .init_tempsel = __xfrm6_init_tempsel, + .init_temprop = xfrm6_init_temprop, .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, .output = xfrm6_output, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 2b3ed7a..cbab6e1 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1175,9 +1175,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, tmpl->mode == XFRM_MODE_BEET) { remote = &tmpl->id.daddr; local = &tmpl->saddr; - family = tmpl->encap_family; - if (xfrm_addr_any(local, family)) { - error = xfrm_get_saddr(net, &tmp, remote, family); + if (xfrm_addr_any(local, tmpl->encap_family)) { + error = xfrm_get_saddr(net, &tmp, remote, tmpl->encap_family); if (error) goto fail; local = &tmp; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5208b12f..eb96ce5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -656,15 +656,23 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) EXPORT_SYMBOL(xfrm_sad_getinfo); static int -xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr, - unsigned short family) +xfrm_init_tempstate(struct xfrm_state *x, struct flowi *fl, + struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr, + unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (!afinfo) return -1; - afinfo->init_tempsel(x, fl, tmpl, daddr, saddr); + afinfo->init_tempsel(&x->sel, fl); + + if (family != tmpl->encap_family) { + xfrm_state_put_afinfo(afinfo); + afinfo = xfrm_state_get_afinfo(tmpl->encap_family); + if (!afinfo) + return -1; + } + afinfo->init_temprop(x, tmpl, daddr, saddr); xfrm_state_put_afinfo(afinfo); return 0; } @@ -790,37 +798,38 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, int error = 0; struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; + unsigned short encap_family = tmpl->encap_family; to_put = NULL; spin_lock_bh(&xfrm_state_lock); - h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, family); + h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { - if (x->props.family == family && + if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && !(x->props.flags & XFRM_STATE_WILDRECV) && - xfrm_state_addr_check(x, daddr, saddr, family) && + xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, family, daddr, saddr, + xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr, &best, &acquire_in_progress, &error); } if (best) goto found; - h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, family); + h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) { - if (x->props.family == family && + if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && !(x->props.flags & XFRM_STATE_WILDRECV) && - xfrm_state_addr_check(x, daddr, saddr, family) && + xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, family, daddr, saddr, + xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr, &best, &acquire_in_progress, &error); } @@ -829,7 +838,7 @@ found: if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && (x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi, - tmpl->id.proto, family)) != NULL) { + tmpl->id.proto, encap_family)) != NULL) { to_put = x0; error = -EEXIST; goto out; @@ -839,9 +848,9 @@ found: error = -ENOMEM; goto out; } - /* Initialize temporary selector matching only + /* Initialize temporary state matching only * to current session. */ - xfrm_init_tempsel(x, fl, tmpl, daddr, saddr, family); + xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); error = security_xfrm_state_alloc_acquire(x, pol->security, fl->secid); @@ -856,10 +865,10 @@ found: x->km.state = XFRM_STATE_ACQ; list_add(&x->km.all, &net->xfrm.state_all); hlist_add_head(&x->bydst, net->xfrm.state_bydst+h); - h = xfrm_src_hash(net, daddr, saddr, family); + h = xfrm_src_hash(net, daddr, saddr, encap_family); hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h); if (x->id.spi) { - h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, family); + h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; -- cgit v0.10.2 From 43e3bf203456c4f06bdd6060426976ad2bed9081 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Mon, 20 Sep 2010 13:13:04 -0700 Subject: [IA64] iommu: Add a dummy iommu_table.h file in IA64. We don't need a comlex IOMMU dependency list on IA64 so we just define the IOMMU_* macro as a dummy. Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: Tony Luck diff --git a/arch/ia64/include/asm/iommu_table.h b/arch/ia64/include/asm/iommu_table.h new file mode 100644 index 0000000..92c8d36 --- /dev/null +++ b/arch/ia64/include/asm/iommu_table.h @@ -0,0 +1,6 @@ +#ifndef _ASM_IA64_IOMMU_TABLE_H +#define _ASM_IA64_IOMMU_TABLE_H + +#define IOMMU_INIT_POST(_detect) + +#endif /* _ASM_IA64_IOMMU_TABLE_H */ -- cgit v0.10.2 From 9f081ce5da2c8af297a0a7d15a57fb4beeed374b Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 20 Sep 2010 13:15:07 -0700 Subject: [IA64] Move local_softirq_pending() definition Ugly #include dependencies. We need to have local_softirq_pending() defined before it gets used in . But provides the definition *after* this #include chain: Signed-off-by: Tony Luck diff --git a/arch/ia64/include/asm/hardirq.h b/arch/ia64/include/asm/hardirq.h index d514cd9..8fb7d33 100644 --- a/arch/ia64/include/asm/hardirq.h +++ b/arch/ia64/include/asm/hardirq.h @@ -6,12 +6,6 @@ * David Mosberger-Tang */ - -#include -#include - -#include - /* * No irq_cpustat_t for IA-64. The data is held in the per-CPU data structure. */ @@ -20,6 +14,11 @@ #define local_softirq_pending() (local_cpu_data->softirq_pending) +#include +#include + +#include + extern void __iomem *ipi_base_addr; void ack_bad_irq(unsigned int irq); -- cgit v0.10.2 From 9828e6e6e3f19efcb476c567b9999891d051f52f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 20 Sep 2010 15:40:35 -0700 Subject: rose: Fix signedness issues wrt. digi count. Just use explicit casts, since we really can't change the types of structures exported to userspace which have been around for 15 years or so. Reported-by: Dan Rosenberg Signed-off-by: David S. Miller diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 8e45e76..d952e7e 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -679,7 +679,7 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1) return -EINVAL; - if (addr->srose_ndigis > ROSE_MAX_DIGIS) + if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS) return -EINVAL; if ((dev = rose_dev_get(&addr->srose_addr)) == NULL) { @@ -739,7 +739,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le if (addr_len == sizeof(struct sockaddr_rose) && addr->srose_ndigis > 1) return -EINVAL; - if (addr->srose_ndigis > ROSE_MAX_DIGIS) + if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS) return -EINVAL; /* Source + Destination digis should not exceed ROSE_MAX_DIGIS */ -- cgit v0.10.2 From a4d258036ed9b2a1811c3670c6099203a0f284a0 Mon Sep 17 00:00:00 2001 From: Tom Marshall Date: Mon, 20 Sep 2010 15:42:05 -0700 Subject: tcp: Fix race in tcp_poll If a RST comes in immediately after checking sk->sk_err, tcp_poll will return POLLIN but not POLLOUT. Fix this by checking sk->sk_err at the end of tcp_poll. Additionally, ensure the correct order of operations on SMP machines with memory barriers. Signed-off-by: Tom Marshall Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3fb1428..95d75d4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -386,8 +386,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) */ mask = 0; - if (sk->sk_err) - mask = POLLERR; /* * POLLHUP is certainly not done right. But poll() doesn't @@ -457,6 +455,11 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tp->urg_data & TCP_URG_VALID) mask |= POLLPRI; } + /* This barrier is coupled with smp_wmb() in tcp_reset() */ + smp_rmb(); + if (sk->sk_err) + mask |= POLLERR; + return mask; } EXPORT_SYMBOL(tcp_poll); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e663b78..149e79a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4048,6 +4048,8 @@ static void tcp_reset(struct sock *sk) default: sk->sk_err = ECONNRESET; } + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + smp_wmb(); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_error_report(sk); -- cgit v0.10.2 From 83d9f65bdae6f6b34d75282c6618d3f50846849a Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 29 Aug 2010 18:12:24 -0700 Subject: x86, setup: Fix earlyprintk=serial,ttyS0,115200 Torsten reported that there is garbage output, after commit 8fee13a48e4879fba57725f6d9513df4bfa8e9f3 (x86, setup: enable early console output from the decompressor) It turns out we missed the offset for that case. Reported-by: Torsten Kaiser Signed-off-by: Yinghai Lu LKML-Reference: <4C7B0578.8090807@kernel.org> Signed-off-by: H. Peter Anvin diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c index 030f4b9..407a8e2 100644 --- a/arch/x86/boot/early_serial_console.c +++ b/arch/x86/boot/early_serial_console.c @@ -58,7 +58,7 @@ static void parse_earlyprintk(void) if (arg[pos] == ',') pos++; - if (!strncmp(arg, "ttyS", 4)) { + if (!strncmp(arg + pos, "ttyS", 4)) { static const int bases[] = { 0x3f8, 0x2f8 }; int idx = 0; -- cgit v0.10.2 From 74b3c444a963ba55aef89b33a1bcaada9a4c206f Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 29 Aug 2010 18:13:10 -0700 Subject: x86, setup: Fix earlyprintk=serial,0x3f8,115200 earlyprintk can take and I/O port, so we need to handle this case in the setup code too, otherwise 0x3f8 will be treated as a baud rate. Signed-off-by: Yinghai Lu LKML-Reference: <4C7B05A6.4010801@kernel.org> Signed-off-by: H. Peter Anvin diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c index 407a8e2..5df2869 100644 --- a/arch/x86/boot/early_serial_console.c +++ b/arch/x86/boot/early_serial_console.c @@ -58,7 +58,19 @@ static void parse_earlyprintk(void) if (arg[pos] == ',') pos++; - if (!strncmp(arg + pos, "ttyS", 4)) { + /* + * make sure we have + * "serial,0x3f8,115200" + * "serial,ttyS0,115200" + * "ttyS0,115200" + */ + if (pos == 7 && !strncmp(arg + pos, "0x", 2)) { + port = simple_strtoull(arg + pos, &e, 16); + if (port == 0 || arg + pos == e) + port = DEFAULT_SERIAL_PORT; + else + pos = e - arg; + } else if (!strncmp(arg + pos, "ttyS", 4)) { static const int bases[] = { 0x3f8, 0x2f8 }; int idx = 0; -- cgit v0.10.2 From 8df8fd27123054b02007361bd5483775db84b4a8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 20 Sep 2010 02:28:59 +0000 Subject: qlcnic: dont set skb->truesize skb->truesize is set in core network. Dont change it unless dealing with fragments. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller diff --git a/drivers/net/qlcnic/qlcnic_init.c b/drivers/net/qlcnic/qlcnic_init.c index 60ab753..2c7cf0b 100644 --- a/drivers/net/qlcnic/qlcnic_init.c +++ b/drivers/net/qlcnic/qlcnic_init.c @@ -1404,7 +1404,6 @@ qlcnic_process_rcv(struct qlcnic_adapter *adapter, if (pkt_offset) skb_pull(skb, pkt_offset); - skb->truesize = skb->len + sizeof(struct sk_buff); skb->protocol = eth_type_trans(skb, netdev); napi_gro_receive(&sds_ring->napi, skb); @@ -1466,8 +1465,6 @@ qlcnic_process_lro(struct qlcnic_adapter *adapter, skb_put(skb, lro_length + data_offset); - skb->truesize = skb->len + sizeof(struct sk_buff) + skb_headroom(skb); - skb_pull(skb, l2_hdr_offset); skb->protocol = eth_type_trans(skb, netdev); @@ -1700,8 +1697,6 @@ qlcnic_process_rcv_diag(struct qlcnic_adapter *adapter, if (pkt_offset) skb_pull(skb, pkt_offset); - skb->truesize = skb->len + sizeof(struct sk_buff); - if (!qlcnic_check_loopback_buff(skb->data)) adapter->diag_cnt++; -- cgit v0.10.2 From 7e96dc7045bff8758804b047c0dfb6868f182500 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Sep 2010 13:04:04 -0700 Subject: netxen: dont set skb->truesize skb->truesize is set in core network. Dont change it unless dealing with fragments. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller diff --git a/drivers/net/netxen/netxen_nic_init.c b/drivers/net/netxen/netxen_nic_init.c index cabae7b..b075a35 100644 --- a/drivers/net/netxen/netxen_nic_init.c +++ b/drivers/net/netxen/netxen_nic_init.c @@ -1540,7 +1540,6 @@ netxen_process_rcv(struct netxen_adapter *adapter, if (pkt_offset) skb_pull(skb, pkt_offset); - skb->truesize = skb->len + sizeof(struct sk_buff); skb->protocol = eth_type_trans(skb, netdev); napi_gro_receive(&sds_ring->napi, skb); @@ -1602,8 +1601,6 @@ netxen_process_lro(struct netxen_adapter *adapter, skb_put(skb, lro_length + data_offset); - skb->truesize = skb->len + sizeof(struct sk_buff) + skb_headroom(skb); - skb_pull(skb, l2_hdr_offset); skb->protocol = eth_type_trans(skb, netdev); -- cgit v0.10.2 From 9eecabcb9a924f1e11ba670365fd4babe423045c Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Tue, 21 Sep 2010 22:28:23 +0100 Subject: intel-iommu: Abort IOMMU setup for igfx if BIOS gave no shadow GTT space Yet another BIOS bug; Lenovo this time (X201). Red Hat bug #593516. Signed-off-by: David Woodhouse diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index c3ceebb..dee88c6c 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -3761,6 +3761,23 @@ static void __devinit quirk_iommu_rwbf(struct pci_dev *dev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf); +static void __devinit quirk_calpella_no_shadow_gtt(struct pci_dev *dev) +{ + unsigned short ggc; + + if (pci_read_config_word(dev, 0x52, &ggc)) + return; + + if (!(ggc & 0x800)) { + printk(KERN_INFO "DMAR: BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n"); + dmar_map_gfx = 0; + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_calpella_no_shadow_gtt); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt); + /* On Tylersburg chipsets, some BIOSes have been known to enable the ISOCH DMAR unit for the Azalia sound device, but not give it any TLB entries, which causes it to deadlock. Check for that. We do -- cgit v0.10.2 From eecfd57f6429d9d8e10be186566ef99fced55163 Mon Sep 17 00:00:00 2001 From: Adam Jackson Date: Wed, 25 Aug 2010 21:17:34 +0100 Subject: intel-iommu: Use symbolic values instead of magic numbers in Lenovo w/a Commit 9eecabcb9a924f1e11ba670365fd4babe423045c ("intel-iommu: Abort IOMMU setup for igfx if BIOS gave no shadow GTT space") uses a bunch of magic numbers. Provide #defines for those to make it look slightly saner. Signed-off-by: Adam Jackson Signed-off-by: David Woodhouse diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index dee88c6c..4dfce3d 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -3761,14 +3761,24 @@ static void __devinit quirk_iommu_rwbf(struct pci_dev *dev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf); +#define GGC 0x52 +#define GGC_MEMORY_SIZE_MASK (0xf << 8) +#define GGC_MEMORY_SIZE_NONE (0x0 << 8) +#define GGC_MEMORY_SIZE_1M (0x1 << 8) +#define GGC_MEMORY_SIZE_2M (0x3 << 8) +#define GGC_MEMORY_VT_ENABLED (0x8 << 8) +#define GGC_MEMORY_SIZE_2M_VT (0x9 << 8) +#define GGC_MEMORY_SIZE_3M_VT (0xa << 8) +#define GGC_MEMORY_SIZE_4M_VT (0xb << 8) + static void __devinit quirk_calpella_no_shadow_gtt(struct pci_dev *dev) { unsigned short ggc; - if (pci_read_config_word(dev, 0x52, &ggc)) + if (pci_read_config_word(dev, GGC, &ggc)) return; - if (!(ggc & 0x800)) { + if (!(ggc & GGC_MEMORY_VT_ENABLED)) { printk(KERN_INFO "DMAR: BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n"); dmar_map_gfx = 0; } -- cgit v0.10.2 From 3d13008e7345fa7a79d8f6438150dc15d6ba6e9d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Sep 2010 08:47:45 +0000 Subject: ip: fix truesize mismatch in ip fragmentation Special care should be taken when slow path is hit in ip_fragment() : When walking through frags, we transfert truesize ownership from skb to frags. Then if we hit a slow_path condition, we must undo this or risk uncharging frags->truesize twice, and in the end, having negative socket sk_wmem_alloc counter, or even freeing socket sooner than expected. Many thanks to Nick Bowler, who provided a very clean bug report and test program. Thanks to Jarek for reviewing my first patch and providing a V2 While Nick bisection pointed to commit 2b85a34e911 (net: No more expensive sock_hold()/sock_put() on each tx), underlying bug is older (2.6.12-rc5) A side effect is to extend work done in commit b2722b1c3a893e (ip_fragment: also adjust skb->truesize for packets not owned by a socket) to ipv6 as well. Reported-and-bisected-by: Nick Bowler Tested-by: Nick Bowler Signed-off-by: Eric Dumazet CC: Jarek Poplawski CC: Patrick McHardy Signed-off-by: David S. Miller diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 04b6989..7649d77 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -488,9 +488,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) * we can switch to copy when see the first bad fragment. */ if (skb_has_frags(skb)) { - struct sk_buff *frag; + struct sk_buff *frag, *frag2; int first_len = skb_pagelen(skb); - int truesizes = 0; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || @@ -503,18 +502,18 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) - goto slow_path; + goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) - goto slow_path; + goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } - truesizes += frag->truesize; + skb->truesize -= frag->truesize; } /* Everything is OK. Generate! */ @@ -524,7 +523,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); skb->data_len = first_len - skb_headlen(skb); - skb->truesize -= truesizes; skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); @@ -576,6 +574,15 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) } IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); return err; + +slow_path_clean: + skb_walk_frags(skb, frag2) { + if (frag2 == frag) + break; + frag2->sk = NULL; + frag2->destructor = NULL; + skb->truesize += frag2->truesize; + } } slow_path: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d40b330..980912e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -639,7 +639,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (skb_has_frags(skb)) { int first_len = skb_pagelen(skb); - int truesizes = 0; + struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || @@ -651,18 +651,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) - goto slow_path; + goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) - goto slow_path; + goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; - truesizes += frag->truesize; } + skb->truesize -= frag->truesize; } err = 0; @@ -693,7 +693,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); - skb->truesize -= truesizes; skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); @@ -756,6 +755,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) IPSTATS_MIB_FRAGFAILS); dst_release(&rt->dst); return err; + +slow_path_clean: + skb_walk_frags(skb, frag2) { + if (frag2 == frag) + break; + frag2->sk = NULL; + frag2->destructor = NULL; + skb->truesize += frag2->truesize; + } } slow_path: -- cgit v0.10.2 From 5786aee8bf6d747ea59595601a19e78ad33d6929 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 22 Sep 2010 12:31:53 +0200 Subject: vhost: fix log ctx signalling The log eventfd signalling got put in dead code. We didn't notice because qemu currently does polling instead of eventfd select. Signed-off-by: Michael S. Tsirkin diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index c579dcc..dd3d6f7 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -858,11 +858,12 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log, if (r < 0) return r; len -= l; - if (!len) + if (!len) { + if (vq->log_ctx) + eventfd_signal(vq->log_ctx, 1); return 0; + } } - if (vq->log_ctx) - eventfd_signal(vq->log_ctx, 1); /* Length written exceeds what we have stored. This is a bug. */ BUG(); return 0; -- cgit v0.10.2 From d485d500cf6b13a33bc7a6c09091deea7ea603ca Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Sep 2010 21:17:29 +0000 Subject: netfilter: tproxy: nf_tproxy_assign_sock() can handle tw sockets transparent field of a socket is either inet_twsk(sk)->tw_transparent for timewait sockets, or inet_sk(sk)->transparent for other sockets (TCP/UDP). Signed-off-by: Eric Dumazet Acked-by: David S. Miller Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller diff --git a/net/netfilter/nf_tproxy_core.c b/net/netfilter/nf_tproxy_core.c index 5490fc3..daab8c4 100644 --- a/net/netfilter/nf_tproxy_core.c +++ b/net/netfilter/nf_tproxy_core.c @@ -70,7 +70,11 @@ nf_tproxy_destructor(struct sk_buff *skb) int nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) { - if (inet_sk(sk)->transparent) { + bool transparent = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_transparent : + inet_sk(sk)->transparent; + + if (transparent) { skb_orphan(skb); skb->sk = sk; skb->destructor = nf_tproxy_destructor; -- cgit v0.10.2 From 7874896a26624214bd7c05eeba7c8ab01548b1b5 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 21 Sep 2010 21:17:30 +0000 Subject: netfilter: nf_ct_sip: default to NF_ACCEPT in sip_help_tcp() I initially noticed this because of the compiler warning below, but it does seem to be a valid concern in the case where ct_sip_get_header() returns 0 in the first iteration of the while loop. net/netfilter/nf_conntrack_sip.c: In function 'sip_help_tcp': net/netfilter/nf_conntrack_sip.c:1379: warning: 'ret' may be used uninitialized in this function Signed-off-by: Simon Horman [Patrick: changed NF_DROP to NF_ACCEPT] Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 53d8922..f64de95 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1376,7 +1376,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, unsigned int msglen, origlen; const char *dptr, *end; s16 diff, tdiff = 0; - int ret; + int ret = NF_ACCEPT; typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust; if (ctinfo != IP_CT_ESTABLISHED && -- cgit v0.10.2 From b46ffb854554ff939701bdd492b81558da5706fc Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Tue, 21 Sep 2010 21:17:31 +0000 Subject: netfilter: fix ipt_REJECT TCP RST routing for indev == outdev ip_route_me_harder can't create the route cache when the outdev is the same with the indev for the skbs whichout a valid protocol set. __mkroute_input functions has this check: 1998 if (skb->protocol != htons(ETH_P_IP)) { 1999 /* Not IP (i.e. ARP). Do not create route, if it is 2000 * invalid for proxy arp. DNAT routes are always valid. 2001 * 2002 * Proxy arp feature have been extended to allow, ARP 2003 * replies back to the same interface, to support 2004 * Private VLAN switch technologies. See arp.c. 2005 */ 2006 if (out_dev == in_dev && 2007 IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { 2008 err = -EINVAL; 2009 goto cleanup; 2010 } 2011 } This patch gives the new skb a valid protocol to bypass this check. In order to make ipt_REJECT work with bridges, you also need to enable ip_forward. This patch also fixes a regression. When we used skb_copy_expand(), we didn't have this issue stated above, as the protocol was properly set. Signed-off-by: Changli Gao Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index b254daf..43eec80 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -112,6 +112,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); + nskb->protocol = htons(ETH_P_IP); if (ip_route_me_harder(nskb, addr_type)) goto free_nskb; -- cgit v0.10.2 From 15cdeadaa5d76009e20c7792aed69f5a73808f97 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Sep 2010 21:17:32 +0000 Subject: netfilter: fix a race in nf_ct_ext_create() As soon as rcu_read_unlock() is called, there is no guarantee current thread can safely derefence t pointer, rcu protected. Fix is to copy t->alloc_size in a temporary variable. Signed-off-by: Eric Dumazet Reviewed-by: Paul E. McKenney Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 7dcf7a4..8d9e4c9 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -48,15 +48,17 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) { unsigned int off, len; struct nf_ct_ext_type *t; + size_t alloc_size; rcu_read_lock(); t = rcu_dereference(nf_ct_ext_types[id]); BUG_ON(t == NULL); off = ALIGN(sizeof(struct nf_ct_ext), t->align); len = off + t->len; + alloc_size = t->alloc_size; rcu_read_unlock(); - *ext = kzalloc(t->alloc_size, gfp); + *ext = kzalloc(alloc_size, gfp); if (!*ext) return NULL; -- cgit v0.10.2 From d6120b8afacec587f5feb37781bc751bc5d68a10 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 21 Sep 2010 21:17:33 +0000 Subject: netfilter: nf_nat_snmp: fix checksum calculation (v4) Fix checksum calculation in nf_nat_snmp_basic. Based on patches by Clark Wang and Stephen Hemminger . https://bugzilla.kernel.org/show_bug.cgi?id=17622 Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 1679e2c..ee5f419 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -893,13 +893,15 @@ static void fast_csum(__sum16 *csum, unsigned char s[4]; if (offset & 1) { - s[0] = s[2] = 0; + s[0] = ~0; s[1] = ~*optr; + s[2] = 0; s[3] = *nptr; } else { - s[1] = s[3] = 0; s[0] = ~*optr; + s[1] = ~0; s[2] = *nptr; + s[3] = 0; } *csum = csum_fold(csum_partial(s, 4, ~csum_unfold(*csum))); -- cgit v0.10.2 From cbdd769ab9de26764bde0520a91536caa1587e13 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 21 Sep 2010 21:17:34 +0000 Subject: netfilter: nf_conntrack_defrag: check socket type before touching nodefrag flag we need to check proper socket type within ipv4_conntrack_defrag function before referencing the nodefrag flag. For example the tun driver receive path produces skbs with AF_UNSPEC socket type, and so current code is causing unwanted fragmented packets going out. Signed-off-by: Jiri Olsa Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index eab8de3..f3a9b42 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -66,9 +66,11 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { + struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(skb->sk); - if (inet && inet->nodefrag) + if (sk && (sk->sk_family == PF_INET) && + inet->nodefrag) return NF_ACCEPT; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -- cgit v0.10.2 From 56b49f4b8f6728b91d10c556c116175051b77b60 Mon Sep 17 00:00:00 2001 From: Ollie Wild Date: Wed, 22 Sep 2010 05:54:54 +0000 Subject: net: Move "struct net" declaration inside the __KERNEL__ macro guard This patch reduces namespace pollution by moving the "struct net" declaration out of the userspace-facing portion of linux/netlink.h. It has no impact on the kernel. (This came up because we have several C++ applications which use "net" as a namespace name.) Signed-off-by: Ollie Wild Signed-off-by: David S. Miller diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 59d0669..1235669 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -27,8 +27,6 @@ #define MAX_LINKS 32 -struct net; - struct sockaddr_nl { sa_family_t nl_family; /* AF_NETLINK */ unsigned short nl_pad; /* zero */ @@ -151,6 +149,8 @@ struct nlattr { #include #include +struct net; + static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) { return (struct nlmsghdr *)skb->data; -- cgit v0.10.2 From ec5a32f67c603b11d68eb283d94eb89a4f6cfce1 Mon Sep 17 00:00:00 2001 From: Luca Tettamanti Date: Wed, 22 Sep 2010 10:41:58 +0000 Subject: atl1: fix resume adapter->cmb.cmb is initialized when the device is opened and freed when it's closed. Accessing it unconditionally during resume results either in a crash (NULL pointer dereference, when the interface has not been opened yet) or data corruption (when the interface has been used and brought down adapter->cmb.cmb points to a deallocated memory area). Cc: stable@kernel.org Signed-off-by: Luca Tettamanti Acked-by: Chris Snook Signed-off-by: David S. Miller diff --git a/drivers/net/atlx/atl1.c b/drivers/net/atlx/atl1.c index 63b9ba0..bbd6e30 100644 --- a/drivers/net/atlx/atl1.c +++ b/drivers/net/atlx/atl1.c @@ -2847,10 +2847,11 @@ static int atl1_resume(struct pci_dev *pdev) pci_enable_wake(pdev, PCI_D3cold, 0); atl1_reset_hw(&adapter->hw); - adapter->cmb.cmb->int_stats = 0; - if (netif_running(netdev)) + if (netif_running(netdev)) { + adapter->cmb.cmb->int_stats = 0; atl1_up(adapter); + } netif_device_attach(netdev); return 0; -- cgit v0.10.2 From 3f5a2a713aad28480d86b0add00c68484b54febc Mon Sep 17 00:00:00 2001 From: Luca Tettamanti Date: Wed, 22 Sep 2010 10:42:31 +0000 Subject: atl1: zero out CMB and SBM in atl1_free_ring_resources They are allocated in atl1_setup_ring_resources, zero out the pointers in atl1_free_ring_resources (like the other resources). Signed-off-by: Luca Tettamanti Acked-by: Chris Snook Signed-off-by: David S. Miller diff --git a/drivers/net/atlx/atl1.c b/drivers/net/atlx/atl1.c index bbd6e30..c73be28 100644 --- a/drivers/net/atlx/atl1.c +++ b/drivers/net/atlx/atl1.c @@ -1251,6 +1251,12 @@ static void atl1_free_ring_resources(struct atl1_adapter *adapter) rrd_ring->desc = NULL; rrd_ring->dma = 0; + + adapter->cmb.dma = 0; + adapter->cmb.cmb = NULL; + + adapter->smb.dma = 0; + adapter->smb.smb = NULL; } static void atl1_setup_mac_ctrl(struct atl1_adapter *adapter) -- cgit v0.10.2 From 9ecd4e1689208afe9b059a5ce1333acb2f42c4d2 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Wed, 22 Sep 2010 17:07:27 -0700 Subject: tracing/x86: Don't use mcount in pvclock.c When using a paravirt clock, pvclock.c can be used by sched_clock(), which in turn is used by the tracing mechanism for timestamps, which leads to infinite recursion. Disable mcount/tracing for pvclock.o. Cc: stable@kernel.org Signed-off-by: Jeremy Fitzhardinge LKML-Reference: <4C9A9A3F.4040201@goop.org> Signed-off-by: Steven Rostedt diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0925676..882bbff 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -11,6 +11,7 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg +CFLAGS_REMOVE_pvclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg endif -- cgit v0.10.2 From 258af47479980d8238a04568b94a4e55aa1cb537 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 22 Sep 2010 22:22:25 -0400 Subject: tracing/x86: Don't use mcount in kvmclock.c The guest can use the paravirt clock in kvmclock.c which is used by sched_clock(), which in turn is used by the tracing mechanism for timestamps, which leads to infinite recursion. Disable mcount/tracing for kvmclock.o. Cc: stable@kernel.org Cc: Jeremy Fitzhardinge Cc: Avi Kivity Signed-off-by: Steven Rostedt diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 882bbff..fedf32a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -12,6 +12,7 @@ CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg CFLAGS_REMOVE_pvclock.o = -pg +CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg endif -- cgit v0.10.2 From 94e2238969e89f5112297ad2a00103089dde7e8f Mon Sep 17 00:00:00 2001 From: Ulrich Weber Date: Wed, 22 Sep 2010 06:45:11 +0000 Subject: xfrm4: strip ECN bits from tos field otherwise ECT(1) bit will get interpreted as RTO_ONLINK and routing will fail with XfrmOutBundleGenError. Signed-off-by: Ulrich Weber Signed-off-by: David S. Miller diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 869078d..a580349 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -61,7 +61,7 @@ static int xfrm4_get_saddr(struct net *net, static int xfrm4_get_tos(struct flowi *fl) { - return fl->fl4_tos; + return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */ } static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst, -- cgit v0.10.2 From 8395ae8303255b31a8625035fc98391c88b0c257 Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Wed, 22 Sep 2010 17:15:08 +0000 Subject: e1000e: 82577/8/9 issues with device in Sx When going to Sx, disable gigabit in PHY (e1000_oem_bits_config_ich8lan) in addition to the MAC before configuring PHY wakeup otherwise the PHY configuration writes might be missed. Also write the LED configuration and SMBus address to the PHY registers (e1000_oem_bits_config_ich8lan and e1000_write_smbus_addr, respectively). The reset is no longer needed since re-auto-negotiation is forced in e1000_oem_bits_config_ich8lan and leaving it in causes issues with auto-negotiating the link. Signed-off-by: Bruce Allan Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index 63930d1..822de48 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -125,6 +125,7 @@ /* SMBus Address Phy Register */ #define HV_SMB_ADDR PHY_REG(768, 26) +#define HV_SMB_ADDR_MASK 0x007F #define HV_SMB_ADDR_PEC_EN 0x0200 #define HV_SMB_ADDR_VALID 0x0080 @@ -895,6 +896,34 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw) } /** + * e1000_write_smbus_addr - Write SMBus address to PHY needed during Sx states + * @hw: pointer to the HW structure + * + * Assumes semaphore already acquired. + * + **/ +static s32 e1000_write_smbus_addr(struct e1000_hw *hw) +{ + u16 phy_data; + u32 strap = er32(STRAP); + s32 ret_val = 0; + + strap &= E1000_STRAP_SMBUS_ADDRESS_MASK; + + ret_val = e1000_read_phy_reg_hv_locked(hw, HV_SMB_ADDR, &phy_data); + if (ret_val) + goto out; + + phy_data &= ~HV_SMB_ADDR_MASK; + phy_data |= (strap >> E1000_STRAP_SMBUS_ADDRESS_SHIFT); + phy_data |= HV_SMB_ADDR_PEC_EN | HV_SMB_ADDR_VALID; + ret_val = e1000_write_phy_reg_hv_locked(hw, HV_SMB_ADDR, phy_data); + +out: + return ret_val; +} + +/** * e1000_sw_lcd_config_ich8lan - SW-based LCD Configuration * @hw: pointer to the HW structure * @@ -970,12 +999,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw) * When both NVM bits are cleared, SW will configure * them instead. */ - data = er32(STRAP); - data &= E1000_STRAP_SMBUS_ADDRESS_MASK; - reg_data = data >> E1000_STRAP_SMBUS_ADDRESS_SHIFT; - reg_data |= HV_SMB_ADDR_PEC_EN | HV_SMB_ADDR_VALID; - ret_val = e1000_write_phy_reg_hv_locked(hw, HV_SMB_ADDR, - reg_data); + ret_val = e1000_write_smbus_addr(hw); if (ret_val) goto out; @@ -3460,13 +3484,20 @@ void e1000e_gig_downshift_workaround_ich8lan(struct e1000_hw *hw) void e1000e_disable_gig_wol_ich8lan(struct e1000_hw *hw) { u32 phy_ctrl; + s32 ret_val; phy_ctrl = er32(PHY_CTRL); phy_ctrl |= E1000_PHY_CTRL_D0A_LPLU | E1000_PHY_CTRL_GBE_DISABLE; ew32(PHY_CTRL, phy_ctrl); - if (hw->mac.type >= e1000_pchlan) - e1000_phy_hw_reset_ich8lan(hw); + if (hw->mac.type >= e1000_pchlan) { + e1000_oem_bits_config_ich8lan(hw, true); + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + return; + e1000_write_smbus_addr(hw); + hw->phy.ops.release(hw); + } } /** -- cgit v0.10.2 From 87fb7410cd8d4396dee0155526568645adba3b99 Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Wed, 22 Sep 2010 17:15:33 +0000 Subject: e1000e: 82579 SMBus address and LEDs incorrect after device reset Since the hardware is prevented from performing automatic PHY configuration (the driver does it instead), the OEM_WRITE_ENABLE bit in the EXTCNF_CTRL register will not get cleared preventing the SMBus address and the LED configuration to be written to the PHY registers. On 82579, do not check the OEM_WRITE_ENABLE bit. Signed-off-by: Bruce Allan Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index 822de48..fc8c3ce 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -990,9 +990,9 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw) cnf_base_addr = data & E1000_EXTCNF_CTRL_EXT_CNF_POINTER_MASK; cnf_base_addr >>= E1000_EXTCNF_CTRL_EXT_CNF_POINTER_SHIFT; - if (!(data & E1000_EXTCNF_CTRL_OEM_WRITE_ENABLE) && - ((hw->mac.type == e1000_pchlan) || - (hw->mac.type == e1000_pch2lan))) { + if ((!(data & E1000_EXTCNF_CTRL_OEM_WRITE_ENABLE) && + (hw->mac.type == e1000_pchlan)) || + (hw->mac.type == e1000_pch2lan)) { /* * HW configures the SMBus address and LEDs when the * OEM and LCD Write Enable bits are set in the NVM. -- cgit v0.10.2 From 5f3eed6fe0e36e4b56c8dd9160241a868ee0de2a Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Wed, 22 Sep 2010 17:15:54 +0000 Subject: e1000e: 82566DC fails to get link Two recent patches to cleanup the reset[1] and initial PHY configuration[2] code paths for ICH/PCH devices inadvertently left out a 10msec delay and device ID check respectively which are necessary for the 82566DC (device id 0x104b) to be configured properly, otherwise it will not get link. [1] commit e98cac447cc1cc418dff1d610a5c79c4f2bdec7f [2] commit 3f0c16e84438d657d29446f85fe375794a93f159 CC: stable@kernel.org Signed-off-by: Bruce Allan Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index fc8c3ce..6f9cb0d 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -932,7 +932,6 @@ out: **/ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw) { - struct e1000_adapter *adapter = hw->adapter; struct e1000_phy_info *phy = &hw->phy; u32 i, data, cnf_size, cnf_base_addr, sw_cfg_mask; s32 ret_val = 0; @@ -950,7 +949,8 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw) if (phy->type != e1000_phy_igp_3) return ret_val; - if (adapter->pdev->device == E1000_DEV_ID_ICH8_IGP_AMT) { + if ((hw->adapter->pdev->device == E1000_DEV_ID_ICH8_IGP_AMT) || + (hw->adapter->pdev->device == E1000_DEV_ID_ICH8_IGP_C)) { sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG; break; } @@ -1626,6 +1626,9 @@ static s32 e1000_post_phy_reset_ich8lan(struct e1000_hw *hw) if (e1000_check_reset_block(hw)) goto out; + /* Allow time for h/w to get to quiescent state after reset */ + msleep(10); + /* Perform any necessary post-reset workarounds */ switch (hw->mac.type) { case e1000_pchlan: -- cgit v0.10.2 From 831bd2e6a6c09588fdde453ecb858f050ac1b942 Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Wed, 22 Sep 2010 17:16:18 +0000 Subject: e1000e: 82579 unaccounted missed packets On 82579, there is a hardware bug that can cause received packets to not get transferred from the PHY to the MAC due to K1 (a power saving feature of the PHY-MAC interconnect similar to ASPM L1). Since the MAC controls the accounting of missed packets, these will go unnoticed. Workaround the issue by setting the K1 beacon duration according to the link speed. Signed-off-by: Bruce Allan Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller diff --git a/drivers/net/e1000e/hw.h b/drivers/net/e1000e/hw.h index 66ed08f..ba302a5 100644 --- a/drivers/net/e1000e/hw.h +++ b/drivers/net/e1000e/hw.h @@ -57,6 +57,7 @@ enum e1e_registers { E1000_SCTL = 0x00024, /* SerDes Control - RW */ E1000_FCAL = 0x00028, /* Flow Control Address Low - RW */ E1000_FCAH = 0x0002C, /* Flow Control Address High -RW */ + E1000_FEXTNVM4 = 0x00024, /* Future Extended NVM 4 - RW */ E1000_FEXTNVM = 0x00028, /* Future Extended NVM - RW */ E1000_FCT = 0x00030, /* Flow Control Type - RW */ E1000_VET = 0x00038, /* VLAN Ether Type - RW */ diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index 6f9cb0d..89b1e1a 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -105,6 +105,10 @@ #define E1000_FEXTNVM_SW_CONFIG 1 #define E1000_FEXTNVM_SW_CONFIG_ICH8M (1 << 27) /* Bit redefined for ICH8M :/ */ +#define E1000_FEXTNVM4_BEACON_DURATION_MASK 0x7 +#define E1000_FEXTNVM4_BEACON_DURATION_8USEC 0x7 +#define E1000_FEXTNVM4_BEACON_DURATION_16USEC 0x3 + #define PCIE_ICH8_SNOOP_ALL PCIE_NO_SNOOP_ALL #define E1000_ICH_RAR_ENTRIES 7 @@ -238,6 +242,7 @@ static s32 e1000_k1_gig_workaround_hv(struct e1000_hw *hw, bool link); static s32 e1000_set_mdio_slow_mode_hv(struct e1000_hw *hw); static bool e1000_check_mng_mode_ich8lan(struct e1000_hw *hw); static bool e1000_check_mng_mode_pchlan(struct e1000_hw *hw); +static s32 e1000_k1_workaround_lv(struct e1000_hw *hw); static inline u16 __er16flash(struct e1000_hw *hw, unsigned long reg) { @@ -653,6 +658,12 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) goto out; } + if (hw->mac.type == e1000_pch2lan) { + ret_val = e1000_k1_workaround_lv(hw); + if (ret_val) + goto out; + } + /* * Check if there was DownShift, must be checked * immediately after link-up @@ -1583,6 +1594,43 @@ out: } /** + * e1000_k1_gig_workaround_lv - K1 Si workaround + * @hw: pointer to the HW structure + * + * Workaround to set the K1 beacon duration for 82579 parts + **/ +static s32 e1000_k1_workaround_lv(struct e1000_hw *hw) +{ + s32 ret_val = 0; + u16 status_reg = 0; + u32 mac_reg; + + if (hw->mac.type != e1000_pch2lan) + goto out; + + /* Set K1 beacon duration based on 1Gbps speed or otherwise */ + ret_val = e1e_rphy(hw, HV_M_STATUS, &status_reg); + if (ret_val) + goto out; + + if ((status_reg & (HV_M_STATUS_LINK_UP | HV_M_STATUS_AUTONEG_COMPLETE)) + == (HV_M_STATUS_LINK_UP | HV_M_STATUS_AUTONEG_COMPLETE)) { + mac_reg = er32(FEXTNVM4); + mac_reg &= ~E1000_FEXTNVM4_BEACON_DURATION_MASK; + + if (status_reg & HV_M_STATUS_SPEED_1000) + mac_reg |= E1000_FEXTNVM4_BEACON_DURATION_8USEC; + else + mac_reg |= E1000_FEXTNVM4_BEACON_DURATION_16USEC; + + ew32(FEXTNVM4, mac_reg); + } + +out: + return ret_val; +} + +/** * e1000_lan_init_done_ich8lan - Check for PHY config completion * @hw: pointer to the HW structure * -- cgit v0.10.2 From a1ce647378c0262fe72757f989e961b2de6460a5 Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Wed, 22 Sep 2010 17:16:40 +0000 Subject: e1000e: 82579 jumbo frame workaround causing CRC errors The subject workaround was causing CRC errors due to writing the wrong register with updates of the RCTL register. It was also found that the workaround function which modifies the RCTL register was being called in the middle of a read-modify-write operation of the RCTL register, so the function call has been moved appropriately. Lastly, jumbo frames must not be allowed when CRC stripping is disabled by a module parameter because the workaround requires the CRC be stripped. Signed-off-by: Bruce Allan Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index 89b1e1a..bb346ae 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -1475,10 +1475,6 @@ s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable) goto out; /* Enable jumbo frame workaround in the PHY */ - e1e_rphy(hw, PHY_REG(769, 20), &data); - ret_val = e1e_wphy(hw, PHY_REG(769, 20), data & ~(1 << 14)); - if (ret_val) - goto out; e1e_rphy(hw, PHY_REG(769, 23), &data); data &= ~(0x7F << 5); data |= (0x37 << 5); @@ -1487,7 +1483,6 @@ s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable) goto out; e1e_rphy(hw, PHY_REG(769, 16), &data); data &= ~(1 << 13); - data |= (1 << 12); ret_val = e1e_wphy(hw, PHY_REG(769, 16), data); if (ret_val) goto out; @@ -1512,7 +1507,7 @@ s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable) mac_reg = er32(RCTL); mac_reg &= ~E1000_RCTL_SECRC; - ew32(FFLT_DBG, mac_reg); + ew32(RCTL, mac_reg); ret_val = e1000e_read_kmrn_reg(hw, E1000_KMRNCTRLSTA_CTRL_OFFSET, @@ -1538,17 +1533,12 @@ s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable) goto out; /* Write PHY register values back to h/w defaults */ - e1e_rphy(hw, PHY_REG(769, 20), &data); - ret_val = e1e_wphy(hw, PHY_REG(769, 20), data & ~(1 << 14)); - if (ret_val) - goto out; e1e_rphy(hw, PHY_REG(769, 23), &data); data &= ~(0x7F << 5); ret_val = e1e_wphy(hw, PHY_REG(769, 23), data); if (ret_val) goto out; e1e_rphy(hw, PHY_REG(769, 16), &data); - data &= ~(1 << 12); data |= (1 << 13); ret_val = e1e_wphy(hw, PHY_REG(769, 16), data); if (ret_val) diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 2b8ef44..e561d15 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -2704,6 +2704,16 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) u32 psrctl = 0; u32 pages = 0; + /* Workaround Si errata on 82579 - configure jumbo frame flow */ + if (hw->mac.type == e1000_pch2lan) { + s32 ret_val; + + if (adapter->netdev->mtu > ETH_DATA_LEN) + ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true); + else + ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false); + } + /* Program MC offset vector base */ rctl = er32(RCTL); rctl &= ~(3 << E1000_RCTL_MO_SHIFT); @@ -2744,16 +2754,6 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) e1e_wphy(hw, 22, phy_data); } - /* Workaround Si errata on 82579 - configure jumbo frame flow */ - if (hw->mac.type == e1000_pch2lan) { - s32 ret_val; - - if (rctl & E1000_RCTL_LPE) - ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true); - else - ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false); - } - /* Setup buffer sizes */ rctl &= ~E1000_RCTL_SZ_4096; rctl |= E1000_RCTL_BSEX; @@ -4833,6 +4833,15 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) return -EINVAL; } + /* Jumbo frame workaround on 82579 requires CRC be stripped */ + if ((adapter->hw.mac.type == e1000_pch2lan) && + !(adapter->flags2 & FLAG2_CRC_STRIPPING) && + (new_mtu > ETH_DATA_LEN)) { + e_err("Jumbo Frames not supported on 82579 when CRC " + "stripping is disabled.\n"); + return -EINVAL; + } + /* 82573 Errata 17 */ if (((adapter->hw.mac.type == e1000_82573) || (adapter->hw.mac.type == e1000_82574)) && -- cgit v0.10.2 From 605c82bab5abe0816e5e32716875c245f89f39da Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Wed, 22 Sep 2010 17:17:01 +0000 Subject: e1000e: 82579 do not gate auto config of PHY by hardware during nominal use For non-managed versions of 82579, set the bit that prevents the hardware from automatically configuring the PHY after resets only when the driver performs a reset, clear the bit after resets. This is so the hardware can configure the PHY automatically when the part is reset in a manner that is not controlled by the driver (e.g. in a virtual environment via PCI FLR) otherwise the PHY will be mis-configured causing issues such as failing to link at 1000Mbps. For managed versions of 82579, keep the previous behavior since the manageability firmware will handle the PHY configuration. Signed-off-by: Bruce Allan Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index bb346ae..57b5435 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -243,6 +243,7 @@ static s32 e1000_set_mdio_slow_mode_hv(struct e1000_hw *hw); static bool e1000_check_mng_mode_ich8lan(struct e1000_hw *hw); static bool e1000_check_mng_mode_pchlan(struct e1000_hw *hw); static s32 e1000_k1_workaround_lv(struct e1000_hw *hw); +static void e1000_gate_hw_phy_config_ich8lan(struct e1000_hw *hw, bool gate); static inline u16 __er16flash(struct e1000_hw *hw, unsigned long reg) { @@ -278,7 +279,7 @@ static inline void __ew32flash(struct e1000_hw *hw, unsigned long reg, u32 val) static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) { struct e1000_phy_info *phy = &hw->phy; - u32 ctrl; + u32 ctrl, fwsm; s32 ret_val = 0; phy->addr = 1; @@ -300,7 +301,8 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) * disabled, then toggle the LANPHYPC Value bit to force * the interconnect to PCIe mode. */ - if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) { + fwsm = er32(FWSM); + if (!(fwsm & E1000_ICH_FWSM_FW_VALID)) { ctrl = er32(CTRL); ctrl |= E1000_CTRL_LANPHYPC_OVERRIDE; ctrl &= ~E1000_CTRL_LANPHYPC_VALUE; @@ -309,6 +311,13 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) ctrl &= ~E1000_CTRL_LANPHYPC_OVERRIDE; ew32(CTRL, ctrl); msleep(50); + + /* + * Gate automatic PHY configuration by hardware on + * non-managed 82579 + */ + if (hw->mac.type == e1000_pch2lan) + e1000_gate_hw_phy_config_ich8lan(hw, true); } /* @@ -321,6 +330,13 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) if (ret_val) goto out; + /* Ungate automatic PHY configuration on non-managed 82579 */ + if ((hw->mac.type == e1000_pch2lan) && + !(fwsm & E1000_ICH_FWSM_FW_VALID)) { + msleep(10); + e1000_gate_hw_phy_config_ich8lan(hw, false); + } + phy->id = e1000_phy_unknown; ret_val = e1000e_get_phy_id(hw); if (ret_val) @@ -567,13 +583,10 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_adapter *adapter) if (mac->type == e1000_ich8lan) e1000e_set_kmrn_lock_loss_workaround_ich8lan(hw, true); - /* Disable PHY configuration by hardware, config by software */ - if (mac->type == e1000_pch2lan) { - u32 extcnf_ctrl = er32(EXTCNF_CTRL); - - extcnf_ctrl |= E1000_EXTCNF_CTRL_GATE_PHY_CFG; - ew32(EXTCNF_CTRL, extcnf_ctrl); - } + /* Gate automatic PHY configuration by hardware on managed 82579 */ + if ((mac->type == e1000_pch2lan) && + (er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) + e1000_gate_hw_phy_config_ich8lan(hw, true); return 0; } @@ -1621,6 +1634,32 @@ out: } /** + * e1000_gate_hw_phy_config_ich8lan - disable PHY config via hardware + * @hw: pointer to the HW structure + * @gate: boolean set to true to gate, false to ungate + * + * Gate/ungate the automatic PHY configuration via hardware; perform + * the configuration via software instead. + **/ +static void e1000_gate_hw_phy_config_ich8lan(struct e1000_hw *hw, bool gate) +{ + u32 extcnf_ctrl; + + if (hw->mac.type != e1000_pch2lan) + return; + + extcnf_ctrl = er32(EXTCNF_CTRL); + + if (gate) + extcnf_ctrl |= E1000_EXTCNF_CTRL_GATE_PHY_CFG; + else + extcnf_ctrl &= ~E1000_EXTCNF_CTRL_GATE_PHY_CFG; + + ew32(EXTCNF_CTRL, extcnf_ctrl); + return; +} + +/** * e1000_lan_init_done_ich8lan - Check for PHY config completion * @hw: pointer to the HW structure * @@ -1695,6 +1734,13 @@ static s32 e1000_post_phy_reset_ich8lan(struct e1000_hw *hw) /* Configure the LCD with the OEM bits in NVM */ ret_val = e1000_oem_bits_config_ich8lan(hw, true); + /* Ungate automatic PHY configuration on non-managed 82579 */ + if ((hw->mac.type == e1000_pch2lan) && + !(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) { + msleep(10); + e1000_gate_hw_phy_config_ich8lan(hw, false); + } + out: return ret_val; } @@ -1711,6 +1757,11 @@ static s32 e1000_phy_hw_reset_ich8lan(struct e1000_hw *hw) { s32 ret_val = 0; + /* Gate automatic PHY configuration by hardware on non-managed 82579 */ + if ((hw->mac.type == e1000_pch2lan) && + !(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) + e1000_gate_hw_phy_config_ich8lan(hw, true); + ret_val = e1000e_phy_hw_reset_generic(hw); if (ret_val) goto out; @@ -2975,6 +3026,14 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw) * external PHY is reset. */ ctrl |= E1000_CTRL_PHY_RST; + + /* + * Gate automatic PHY configuration by hardware on + * non-managed 82579 + */ + if ((hw->mac.type == e1000_pch2lan) && + !(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) + e1000_gate_hw_phy_config_ich8lan(hw, true); } ret_val = e1000_acquire_swflag_ich8lan(hw); e_dbg("Issuing a global reset to ich8lan\n"); -- cgit v0.10.2 From 9b74f7348f214b1f99819f0d0da4a1cbabb1e740 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 22 Sep 2010 19:10:44 +0100 Subject: drm/i915: Fix 945GM regression in e259befd A minor typo caused a single fence register to be incorrectly programmed, resulting in occassional tiling corruption. Reported-and-tested-by: Hans de Bruin Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=18962 Signed-off-by: Chris Wilson Cc: stable@kernel.org diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index cf4ffbe..bced9b2 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2400,7 +2400,7 @@ i915_gem_clear_fence_reg(struct drm_gem_object *obj) I915_WRITE64(FENCE_REG_965_0 + (obj_priv->fence_reg * 8), 0); break; case 3: - if (obj_priv->fence_reg > 8) + if (obj_priv->fence_reg >= 8) fence_reg = FENCE_REG_945_8 + (obj_priv->fence_reg - 8) * 4; else case 2: -- cgit v0.10.2 From 1d5b4c0fa9ff79a4f01e5efc1caefd16b190a3dc Mon Sep 17 00:00:00 2001 From: Peter Korsgaard Date: Wed, 22 Sep 2010 21:29:59 +0100 Subject: ARM: 6406/1: at91sam9g45: fix i2c bus speed Use a correct udelay value to get bus speed around 100KHz. The udelay value was most likely copied from the older devices, but the 9g45 is signicantly faster (400MHz, DDR, ..), so a udelay of 2 gives a bus speed of around 190KHz, which is too fast for some devices. A udelay value of 5 gives a bus speed of around 90KHz here. Signed-off-by: Peter Korsgaard Signed-off-by: Nicolas Ferre Signed-off-by: Russell King diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c index 5e71ccd..1276bab 100644 --- a/arch/arm/mach-at91/at91sam9g45_devices.c +++ b/arch/arm/mach-at91/at91sam9g45_devices.c @@ -426,7 +426,7 @@ static struct i2c_gpio_platform_data pdata_i2c0 = { .sda_is_open_drain = 1, .scl_pin = AT91_PIN_PA21, .scl_is_open_drain = 1, - .udelay = 2, /* ~100 kHz */ + .udelay = 5, /* ~100 kHz */ }; static struct platform_device at91sam9g45_twi0_device = { @@ -440,7 +440,7 @@ static struct i2c_gpio_platform_data pdata_i2c1 = { .sda_is_open_drain = 1, .scl_pin = AT91_PIN_PB11, .scl_is_open_drain = 1, - .udelay = 2, /* ~100 kHz */ + .udelay = 5, /* ~100 kHz */ }; static struct platform_device at91sam9g45_twi1_device = { -- cgit v0.10.2 From 2f27bf834e1d0a06e83d7458b535891c552271aa Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 20 Sep 2010 04:10:43 +0100 Subject: ARM: 6401/1: plug a race in the alignment trap handler When the policy for user space is to ignore misaligned accesses from user space, the processor then performs a documented rotation on the accessed data. This is the result of the access being trapped, and the kernel disabling the alignment trap before returning to user space again. In kernel space we always want misaligned accesses to be fixed up. This is enforced by always re-enabling the alignment trap on every entry into kernel space from user space. No such re-enabling is performed when an exception occurs while already in kernel space as the alignment trap is always supposed to be enabled in that case. There is however a small race window when a misaligned access in user space is trapped and the alignment trap disabled, but the CPU didn't return to user space just yet. Any exception would be entered from kernel space at that point and the kernel would then execute with the alignment trap disabled. Thanks to Maxime Bizon for providing a test module that made this issue reproducible. Signed-off-by: Nicolas Pitre Signed-off-by: Russell King diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index d073b64..724ba3b 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -885,8 +885,23 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (ai_usermode & UM_SIGNAL) force_sig(SIGBUS, current); - else - set_cr(cr_no_alignment); + else { + /* + * We're about to disable the alignment trap and return to + * user space. But if an interrupt occurs before actually + * reaching user space, then the IRQ vector entry code will + * notice that we were still in kernel space and therefore + * the alignment trap won't be re-enabled in that case as it + * is presumed to be always on from kernel space. + * Let's prevent that race by disabling interrupts here (they + * are disabled on the way back to user space anyway in + * entry-common.S) and disable the alignment trap only if + * there is no work pending for this thread. + */ + raw_local_irq_disable(); + if (!(current_thread_info()->flags & _TIF_WORK_MASK)) + set_cr(cr_no_alignment); + } return 0; } -- cgit v0.10.2 From e9bf51971157e367aabfc111a8219db010f69cd4 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 20 Sep 2010 14:33:07 +0200 Subject: x86/amd-iommu: Set iommu configuration flags in enable-loop This patch moves the setting of the configuration and feature flags out out the acpi table parsing path and moves it into the iommu-enable path. This is needed to reliably fix resume-from-s3. Cc: stable@kernel.org Signed-off-by: Joerg Roedel diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index 7014e88..ef2d5cd 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -368,6 +368,9 @@ struct amd_iommu { /* capabilities of that IOMMU read from ACPI */ u32 cap; + /* flags read from acpi table */ + u8 acpi_flags; + /* * Capability pointer. There could be more than one IOMMU per PCI * device function if there are more than one AMD IOMMU capability diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 3cc63e2..85e9817 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -649,29 +649,9 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, struct ivhd_entry *e; /* - * First set the recommended feature enable bits from ACPI - * into the IOMMU control registers + * First save the recommended feature enable bits from ACPI */ - h->flags & IVHD_FLAG_HT_TUN_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : - iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); - - h->flags & IVHD_FLAG_PASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_PASSPW_EN); - - h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); - - h->flags & IVHD_FLAG_ISOC_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_ISOC_EN) : - iommu_feature_disable(iommu, CONTROL_ISOC_EN); - - /* - * make IOMMU memory accesses cache coherent - */ - iommu_feature_enable(iommu, CONTROL_COHERENT_EN); + iommu->acpi_flags = h->flags; /* * Done. Now parse the device entries @@ -1116,6 +1096,30 @@ static void init_device_table(void) } } +static void iommu_init_flags(struct amd_iommu *iommu) +{ + iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : + iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); + + iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_PASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_ISOC_EN) : + iommu_feature_disable(iommu, CONTROL_ISOC_EN); + + /* + * make IOMMU memory accesses cache coherent + */ + iommu_feature_enable(iommu, CONTROL_COHERENT_EN); +} + /* * This function finally enables all IOMMUs found in the system after * they have been initialized @@ -1126,6 +1130,7 @@ static void enable_iommus(void) for_each_iommu(iommu) { iommu_disable(iommu); + iommu_init_flags(iommu); iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); iommu_enable_event_buffer(iommu); -- cgit v0.10.2 From 4c894f47bb49284008073d351c0ddaac8860864e Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 23 Sep 2010 15:15:19 +0200 Subject: x86/amd-iommu: Work around S3 BIOS bug This patch adds a workaround for an IOMMU BIOS problem to the AMD IOMMU driver. The result of the bug is that the IOMMU does not execute commands anymore when the system comes out of the S3 state resulting in system failure. The bug in the BIOS is that is does not restore certain hardware specific registers correctly. This workaround reads out the contents of these registers at boot time and restores them on resume from S3. The workaround is limited to the specific IOMMU chipset where this problem occurs. Cc: stable@kernel.org Signed-off-by: Joerg Roedel diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h index d2544f1..cb03037 100644 --- a/arch/x86/include/asm/amd_iommu_proto.h +++ b/arch/x86/include/asm/amd_iommu_proto.h @@ -38,4 +38,10 @@ static inline void amd_iommu_stats_init(void) { } #endif /* !CONFIG_AMD_IOMMU_STATS */ +static inline bool is_rd890_iommu(struct pci_dev *pdev) +{ + return (pdev->vendor == PCI_VENDOR_ID_ATI) && + (pdev->device == PCI_DEVICE_ID_RD890_IOMMU); +} + #endif /* _ASM_X86_AMD_IOMMU_PROTO_H */ diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index ef2d5cd..0861618 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -414,6 +414,15 @@ struct amd_iommu { /* default dma_ops domain for that IOMMU */ struct dma_ops_domain *default_dom; + + /* + * This array is required to work around a potential BIOS bug. + * The BIOS may miss to restore parts of the PCI configuration + * space when the system resumes from S3. The result is that the + * IOMMU does not execute commands anymore which leads to system + * failure. + */ + u32 cache_cfg[4]; }; /* diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 85e9817..5a170cb 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -632,6 +632,13 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu) iommu->last_device = calc_devid(MMIO_GET_BUS(range), MMIO_GET_LD(range)); iommu->evt_msi_num = MMIO_MSI_NUM(misc); + + if (is_rd890_iommu(iommu->dev)) { + pci_read_config_dword(iommu->dev, 0xf0, &iommu->cache_cfg[0]); + pci_read_config_dword(iommu->dev, 0xf4, &iommu->cache_cfg[1]); + pci_read_config_dword(iommu->dev, 0xf8, &iommu->cache_cfg[2]); + pci_read_config_dword(iommu->dev, 0xfc, &iommu->cache_cfg[3]); + } } /* @@ -1120,6 +1127,16 @@ static void iommu_init_flags(struct amd_iommu *iommu) iommu_feature_enable(iommu, CONTROL_COHERENT_EN); } +static void iommu_apply_quirks(struct amd_iommu *iommu) +{ + if (is_rd890_iommu(iommu->dev)) { + pci_write_config_dword(iommu->dev, 0xf0, iommu->cache_cfg[0]); + pci_write_config_dword(iommu->dev, 0xf4, iommu->cache_cfg[1]); + pci_write_config_dword(iommu->dev, 0xf8, iommu->cache_cfg[2]); + pci_write_config_dword(iommu->dev, 0xfc, iommu->cache_cfg[3]); + } +} + /* * This function finally enables all IOMMUs found in the system after * they have been initialized @@ -1130,6 +1147,7 @@ static void enable_iommus(void) for_each_iommu(iommu) { iommu_disable(iommu); + iommu_apply_quirks(iommu); iommu_init_flags(iommu); iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 10d3330..570fdde 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -393,6 +393,9 @@ #define PCI_DEVICE_ID_VLSI_82C147 0x0105 #define PCI_DEVICE_ID_VLSI_VAS96011 0x0702 +/* AMD RD890 Chipset */ +#define PCI_DEVICE_ID_RD890_IOMMU 0x5a23 + #define PCI_VENDOR_ID_ADL 0x1005 #define PCI_DEVICE_ID_ADL_2301 0x2301 -- cgit v0.10.2 From 04e0463e088b41060c08c255eb0d3278a504f094 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 23 Sep 2010 16:12:48 +0200 Subject: x86/amd-iommu: Fix rounding-bug in __unmap_single In the __unmap_single function the dma_addr is rounded down to a page boundary before the dma pages are unmapped. The address is later also used to flush the TLB entries for that mapping. But without the offset into the dma page the amount of pages to flush might be miscalculated in the TLB flushing path. This patch fixes this bug by using the original address to flush the TLB. Cc: stable@kernel.org Signed-off-by: Joerg Roedel diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index fa044e1..679b645 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -1953,6 +1953,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom, size_t size, int dir) { + dma_addr_t flush_addr; dma_addr_t i, start; unsigned int pages; @@ -1960,6 +1961,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom, (dma_addr + size > dma_dom->aperture_size)) return; + flush_addr = dma_addr; pages = iommu_num_pages(dma_addr, size, PAGE_SIZE); dma_addr &= PAGE_MASK; start = dma_addr; @@ -1974,7 +1976,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom, dma_ops_free_addresses(dma_dom, dma_addr, pages); if (amd_iommu_unmap_flush || dma_dom->need_flush) { - iommu_flush_pages(&dma_dom->domain, dma_addr, size); + iommu_flush_pages(&dma_dom->domain, flush_addr, size); dma_dom->need_flush = false; } } -- cgit v0.10.2 From 123d5c0197d8333c3f5cb9572a0c8299dc611233 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 23 Sep 2010 16:15:21 +0100 Subject: drm/i915/sdvo: Cleanup connector on error path We weren't unlinking the freed connector from the drm lists, and so hit some use-after-free if we failed to initialise the connector. Reported-and-tested-by: Woody Suwalski Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=18342 Signed-off-by: Chris Wilson diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index e8e902d..60fcef7 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -2170,8 +2170,7 @@ intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type) return true; err: - intel_sdvo_destroy_enhance_property(connector); - kfree(intel_sdvo_connector); + intel_sdvo_destroy(connector); return false; } @@ -2243,8 +2242,7 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device) return true; err: - intel_sdvo_destroy_enhance_property(connector); - kfree(intel_sdvo_connector); + intel_sdvo_destroy(connector); return false; } -- cgit v0.10.2 From cf9a2f3afc75d41a61cbc91e725b9ce0746c400a Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Thu, 23 Sep 2010 16:17:33 +0100 Subject: drm/i915/sdvo: Handle unsupported GET_SUPPORTED_ENHANCEMENTS gracefully In the event that the external chipset doesn't implement the GET_SUPPORTED_ENHANCEMENTS commands, gracefully treat it as having no enhancments rather than bailing. Reported-and-tested-by: Woody Suwalski Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=18342 Signed-off-by: Chris Wilson diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 60fcef7..ee73e42 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -2520,11 +2520,10 @@ static bool intel_sdvo_create_enhance_property(struct intel_sdvo *intel_sdvo, uint16_t response; } enhancements; - if (!intel_sdvo_get_value(intel_sdvo, - SDVO_CMD_GET_SUPPORTED_ENHANCEMENTS, - &enhancements, sizeof(enhancements))) - return false; - + enhancements.response = 0; + intel_sdvo_get_value(intel_sdvo, + SDVO_CMD_GET_SUPPORTED_ENHANCEMENTS, + &enhancements, sizeof(enhancements)); if (enhancements.response == 0) { DRM_DEBUG_KMS("No enhancement is supported\n"); return true; -- cgit v0.10.2 From 85718fae2a8d845e66762e6464152a255e323777 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Thu, 23 Sep 2010 13:52:07 -0700 Subject: [IA64] Add CONFIG_STACKTRACE_SUPPORT Several Linux features are dependent on stack trace support. Add it so they can be enabled. Signed-off-by: Tony Luck diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index ba22849..e93f44e 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -62,6 +62,9 @@ config NEED_SG_DMA_LENGTH config SWIOTLB bool +config STACKTRACE_SUPPORT + def_bool y + config GENERIC_LOCKBREAK def_bool n diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile index db10b1e..395c2f2 100644 --- a/arch/ia64/kernel/Makefile +++ b/arch/ia64/kernel/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_AUDIT) += audit.o obj-$(CONFIG_PCI_MSI) += msi_ia64.o mca_recovery-y += mca_drv.o mca_drv_asm.o obj-$(CONFIG_IA64_MC_ERR_INJECT)+= err_inject.o +obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirtentry.o \ paravirt_patch.o diff --git a/arch/ia64/kernel/stacktrace.c b/arch/ia64/kernel/stacktrace.c new file mode 100644 index 0000000..5af2783 --- /dev/null +++ b/arch/ia64/kernel/stacktrace.c @@ -0,0 +1,39 @@ +/* + * arch/ia64/kernel/stacktrace.c + * + * Stack trace management functions + * + */ +#include +#include +#include + +static void +ia64_do_save_stack(struct unw_frame_info *info, void *arg) +{ + struct stack_trace *trace = arg; + unsigned long ip; + int skip = trace->skip; + + trace->nr_entries = 0; + do { + unw_get_ip(info, &ip); + if (ip == 0) + break; + if (skip == 0) { + trace->entries[trace->nr_entries++] = ip; + if (trace->nr_entries == trace->max_entries) + break; + } else + skip--; + } while (unw_unwind(info) >= 0); +} + +/* + * Save stack-backtrace addresses into a stack_trace buffer. + */ +void save_stack_trace(struct stack_trace *trace) +{ + unw_init_running(ia64_do_save_stack, trace); +} +EXPORT_SYMBOL(save_stack_trace); -- cgit v0.10.2 From 48a4b30124d079c765e6eaea3a7359195d7f0c37 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Thu, 23 Sep 2010 14:02:09 -0700 Subject: [IA64] remove asm/compat.h Missed this file in commit 32974ad4907cdde6c9de612cd1b2ee0568fb9409 [IA64] Remove COMPAT_IA32 support It is no longer needed, so remove it. Signed-off-by: Tony Luck diff --git a/arch/ia64/include/asm/compat.h b/arch/ia64/include/asm/compat.h deleted file mode 100644 index 9301a28..0000000 --- a/arch/ia64/include/asm/compat.h +++ /dev/null @@ -1,208 +0,0 @@ -#ifndef _ASM_IA64_COMPAT_H -#define _ASM_IA64_COMPAT_H -/* - * Architecture specific compatibility types - */ -#include - -#define COMPAT_USER_HZ 100 -#define COMPAT_UTS_MACHINE "i686\0\0\0" - -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_time_t; -typedef s32 compat_clock_t; -typedef s32 compat_key_t; -typedef s32 compat_pid_t; -typedef u16 __compat_uid_t; -typedef u16 __compat_gid_t; -typedef u32 __compat_uid32_t; -typedef u32 __compat_gid32_t; -typedef u16 compat_mode_t; -typedef u32 compat_ino_t; -typedef u16 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; -typedef u16 compat_nlink_t; -typedef u16 compat_ipc_pid_t; -typedef s32 compat_daddr_t; -typedef u32 compat_caddr_t; -typedef __kernel_fsid_t compat_fsid_t; -typedef s32 compat_timer_t; - -typedef s32 compat_int_t; -typedef s32 compat_long_t; -typedef s64 __attribute__((aligned(4))) compat_s64; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; -typedef u64 __attribute__((aligned(4))) compat_u64; - -struct compat_timespec { - compat_time_t tv_sec; - s32 tv_nsec; -}; - -struct compat_timeval { - compat_time_t tv_sec; - s32 tv_usec; -}; - -struct compat_stat { - compat_dev_t st_dev; - u16 __pad1; - compat_ino_t st_ino; - compat_mode_t st_mode; - compat_nlink_t st_nlink; - __compat_uid_t st_uid; - __compat_gid_t st_gid; - compat_dev_t st_rdev; - u16 __pad2; - u32 st_size; - u32 st_blksize; - u32 st_blocks; - u32 st_atime; - u32 st_atime_nsec; - u32 st_mtime; - u32 st_mtime_nsec; - u32 st_ctime; - u32 st_ctime_nsec; - u32 __unused4; - u32 __unused5; -}; - -struct compat_flock { - short l_type; - short l_whence; - compat_off_t l_start; - compat_off_t l_len; - compat_pid_t l_pid; -}; - -#define F_GETLK64 12 -#define F_SETLK64 13 -#define F_SETLKW64 14 - -/* - * IA32 uses 4 byte alignment for 64 bit quantities, - * so we need to pack this structure. - */ -struct compat_flock64 { - short l_type; - short l_whence; - compat_loff_t l_start; - compat_loff_t l_len; - compat_pid_t l_pid; -} __attribute__((packed)); - -struct compat_statfs { - int f_type; - int f_bsize; - int f_blocks; - int f_bfree; - int f_bavail; - int f_files; - int f_ffree; - compat_fsid_t f_fsid; - int f_namelen; /* SunOS ignores this field. */ - int f_frsize; - int f_spare[5]; -}; - -#define COMPAT_RLIM_OLD_INFINITY 0x7fffffff -#define COMPAT_RLIM_INFINITY 0xffffffff - -typedef u32 compat_old_sigset_t; /* at least 32 bits */ - -#define _COMPAT_NSIG 64 -#define _COMPAT_NSIG_BPW 32 - -typedef u32 compat_sigset_word; - -#define COMPAT_OFF_T_MAX 0x7fffffff -#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL - -struct compat_ipc64_perm { - compat_key_t key; - __compat_uid32_t uid; - __compat_gid32_t gid; - __compat_uid32_t cuid; - __compat_gid32_t cgid; - unsigned short mode; - unsigned short __pad1; - unsigned short seq; - unsigned short __pad2; - compat_ulong_t unused1; - compat_ulong_t unused2; -}; - -struct compat_semid64_ds { - struct compat_ipc64_perm sem_perm; - compat_time_t sem_otime; - compat_ulong_t __unused1; - compat_time_t sem_ctime; - compat_ulong_t __unused2; - compat_ulong_t sem_nsems; - compat_ulong_t __unused3; - compat_ulong_t __unused4; -}; - -struct compat_msqid64_ds { - struct compat_ipc64_perm msg_perm; - compat_time_t msg_stime; - compat_ulong_t __unused1; - compat_time_t msg_rtime; - compat_ulong_t __unused2; - compat_time_t msg_ctime; - compat_ulong_t __unused3; - compat_ulong_t msg_cbytes; - compat_ulong_t msg_qnum; - compat_ulong_t msg_qbytes; - compat_pid_t msg_lspid; - compat_pid_t msg_lrpid; - compat_ulong_t __unused4; - compat_ulong_t __unused5; -}; - -struct compat_shmid64_ds { - struct compat_ipc64_perm shm_perm; - compat_size_t shm_segsz; - compat_time_t shm_atime; - compat_ulong_t __unused1; - compat_time_t shm_dtime; - compat_ulong_t __unused2; - compat_time_t shm_ctime; - compat_ulong_t __unused3; - compat_pid_t shm_cpid; - compat_pid_t shm_lpid; - compat_ulong_t shm_nattch; - compat_ulong_t __unused4; - compat_ulong_t __unused5; -}; - -/* - * A pointer passed in from user mode. This should not be used for syscall parameters, - * just declare them as pointers because the syscall entry code will have appropriately - * converted them already. - */ -typedef u32 compat_uptr_t; - -static inline void __user * -compat_ptr (compat_uptr_t uptr) -{ - return (void __user *) (unsigned long) uptr; -} - -static inline compat_uptr_t -ptr_to_compat(void __user *uptr) -{ - return (u32)(unsigned long)uptr; -} - -static __inline__ void __user * -arch_compat_alloc_user_space (long len) -{ - struct pt_regs *regs = task_pt_regs(current); - return (void __user *) (((regs->r12 & 0xffffffff) & -16) - len); -} - -#endif /* _ASM_IA64_COMPAT_H */ -- cgit v0.10.2 From c216488cd1f35c54afbcedf185d5908beb814aef Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 13 Sep 2010 21:23:48 -0700 Subject: [IA64] Use static const char * const in palinfo.c Signed-off-by: Joe Perches Signed-off-by: Tony Luck diff --git a/arch/ia64/kernel/palinfo.c b/arch/ia64/kernel/palinfo.c index fdf6f9d..77597e5 100644 --- a/arch/ia64/kernel/palinfo.c +++ b/arch/ia64/kernel/palinfo.c @@ -434,7 +434,7 @@ register_info(char *page) unsigned long phys_stacked; pal_hints_u_t hints; unsigned long iregs, dregs; - char *info_type[]={ + static const char * const info_type[] = { "Implemented AR(s)", "AR(s) with read side-effects", "Implemented CR(s)", -- cgit v0.10.2 From 3e6b1b25a92df39d2b619ed3cf74322ddef6800e Mon Sep 17 00:00:00 2001 From: Nikitas Angelinas Date: Wed, 8 Sep 2010 22:04:30 +0100 Subject: [IA64] xen: use ARRAY_SIZE macro in xen_pv_ops.c Replace sizeof(xen_branch_target) / sizeof(xen_branch_target[0]) with ARRAY_SIZE(xen_branch_target) in arch/ia64/xen/xen_pv_ops.c Signed-off-by: Nikitas Angelinas Signed-off-by: Tony Luck diff --git a/arch/ia64/xen/xen_pv_ops.c b/arch/ia64/xen/xen_pv_ops.c index 8adc6a1..3e8d350 100644 --- a/arch/ia64/xen/xen_pv_ops.c +++ b/arch/ia64/xen/xen_pv_ops.c @@ -1136,7 +1136,6 @@ __initconst = { static void __init xen_patch_branch(unsigned long tag, unsigned long type) { - const unsigned long nelem = - sizeof(xen_branch_target) / sizeof(xen_branch_target[0]); - __paravirt_patch_apply_branch(tag, type, xen_branch_target, nelem); + __paravirt_patch_apply_branch(tag, type, xen_branch_target, + ARRAY_SIZE(xen_branch_target)); } -- cgit v0.10.2 From 383f9f1741cd03687303f82543bbae11935a2ad6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 7 Sep 2010 14:33:34 +0000 Subject: [IA64] salinfo: sema_init instead of init_MUTEX Get rid of init_MUTEX[_LOCKED]() and use sema_init() instead. Signed-off-by: Thomas Gleixner Signed-off-by: Tony Luck diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index aa8b5fa..45d7543 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -642,7 +642,7 @@ salinfo_init(void) for (i = 0; i < ARRAY_SIZE(salinfo_log_name); i++) { data = salinfo_data + i; data->type = i; - init_MUTEX(&data->mutex); + sema_init(&data->mutex, 1); dir = proc_mkdir(salinfo_log_name[i], salinfo_dir); if (!dir) continue; -- cgit v0.10.2 From ddad53ee8a85649e78f6a3eb8a4af4a7a7c577cb Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Fri, 27 Aug 2010 23:01:30 +0200 Subject: [IA64] Fix missing iounmap in error path in cyclone.c By moving the iounmap up above the test, it takes place whether the test succeeds or fails. Signed-off-by: Julia Lawall Signed-off-by: Tony Luck diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c index 71e3586..d52f1f7 100644 --- a/arch/ia64/kernel/cyclone.c +++ b/arch/ia64/kernel/cyclone.c @@ -59,13 +59,13 @@ int __init init_cyclone_clock(void) return -ENODEV; } base = readq(reg); + iounmap(reg); if(!base){ printk(KERN_ERR "Summit chipset: Could not find valid CBAR" " value.\n"); use_cyclone = 0; return -ENODEV; } - iounmap(reg); /* setup PMCC */ offset = (base + CYCLONE_PMCC_OFFSET); -- cgit v0.10.2 From df0a59a14c693647da4097ba3578c524c452fd0d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 12 Jul 2010 13:49:54 -0700 Subject: [IA64] Remove unnecessary casts of private_data in perfmon.c Signed-off-by: Joe Perches Signed-off-by: Tony Luck diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index cce050e..6b1852f 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -1573,7 +1573,7 @@ pfm_read(struct file *filp, char __user *buf, size_t size, loff_t *ppos) return -EINVAL; } - ctx = (pfm_context_t *)filp->private_data; + ctx = filp->private_data; if (ctx == NULL) { printk(KERN_ERR "perfmon: pfm_read: NULL ctx [%d]\n", task_pid_nr(current)); return -EINVAL; @@ -1673,7 +1673,7 @@ pfm_poll(struct file *filp, poll_table * wait) return 0; } - ctx = (pfm_context_t *)filp->private_data; + ctx = filp->private_data; if (ctx == NULL) { printk(KERN_ERR "perfmon: pfm_poll: NULL ctx [%d]\n", task_pid_nr(current)); return 0; @@ -1733,7 +1733,7 @@ pfm_fasync(int fd, struct file *filp, int on) return -EBADF; } - ctx = (pfm_context_t *)filp->private_data; + ctx = filp->private_data; if (ctx == NULL) { printk(KERN_ERR "perfmon: pfm_fasync NULL ctx [%d]\n", task_pid_nr(current)); return -EBADF; @@ -1841,7 +1841,7 @@ pfm_flush(struct file *filp, fl_owner_t id) return -EBADF; } - ctx = (pfm_context_t *)filp->private_data; + ctx = filp->private_data; if (ctx == NULL) { printk(KERN_ERR "perfmon: pfm_flush: NULL ctx [%d]\n", task_pid_nr(current)); return -EBADF; @@ -1984,7 +1984,7 @@ pfm_close(struct inode *inode, struct file *filp) return -EBADF; } - ctx = (pfm_context_t *)filp->private_data; + ctx = filp->private_data; if (ctx == NULL) { printk(KERN_ERR "perfmon: pfm_close: NULL ctx [%d]\n", task_pid_nr(current)); return -EBADF; @@ -4907,7 +4907,7 @@ restart_args: goto error_args; } - ctx = (pfm_context_t *)file->private_data; + ctx = file->private_data; if (unlikely(ctx == NULL)) { DPRINT(("no context for fd %d\n", fd)); goto error_args; -- cgit v0.10.2 From 63e6be6d98e1a2bcdca86872b67052e51ab6afa1 Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 15 Sep 2010 18:20:34 +0200 Subject: perf, x86: Catch spurious interrupts after disabling counters Some cpus still deliver spurious interrupts after disabling a counter. This caused 'undelivered NMI' messages. This patch fixes this. Introduced by: 4177c42: perf, x86: Try to handle unknown nmis with an enabled PMU Reported-by: Ingo Molnar Signed-off-by: Robert Richter Cc: Don Zickus Cc: gorcunov@gmail.com Cc: fweisbec@gmail.com Cc: ying.huang@intel.com Cc: ming.m.lin@intel.com Cc: yinghai@kernel.org Cc: andi@firstfloor.org Cc: eranian@google.com Cc: Peter Zijlstra LKML-Reference: <20100915162034.GO13563@erda.amd.com> Signed-off-by: Ingo Molnar diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 3efdf28..03a5b03 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -102,6 +102,7 @@ struct cpu_hw_events { */ struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; int enabled; int n_events; @@ -1010,6 +1011,7 @@ static int x86_pmu_start(struct perf_event *event) x86_perf_event_set_period(event); cpuc->events[idx] = event; __set_bit(idx, cpuc->active_mask); + __set_bit(idx, cpuc->running); x86_pmu.enable(event); perf_event_update_userpage(event); @@ -1141,8 +1143,16 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - if (!test_bit(idx, cpuc->active_mask)) + if (!test_bit(idx, cpuc->active_mask)) { + /* + * Though we deactivated the counter some cpus + * might still deliver spurious interrupts still + * in flight. Catch them: + */ + if (__test_and_clear_bit(idx, cpuc->running)) + handled++; continue; + } event = cpuc->events[idx]; hwc = &event->hw; -- cgit v0.10.2 From 979a281c34906fd905d6153ad999487b0c56f396 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 9 Aug 2010 03:55:09 +0200 Subject: ARM: pxa: Fix Vpac270 gpio_power for MMC GPIO 0 is valid, yet this platform doesn't have any power GPIO for MMC. Signed-off-by: Marek Vasut diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c index c9b747c..37d6173 100644 --- a/arch/arm/mach-pxa/vpac270.c +++ b/arch/arm/mach-pxa/vpac270.c @@ -240,6 +240,7 @@ static void __init vpac270_onenand_init(void) {} #if defined(CONFIG_MMC_PXA) || defined(CONFIG_MMC_PXA_MODULE) static struct pxamci_platform_data vpac270_mci_platform_data = { .ocr_mask = MMC_VDD_32_33 | MMC_VDD_33_34, + .gpio_power = -1, .gpio_card_detect = GPIO53_VPAC270_SD_DETECT_N, .gpio_card_ro = GPIO52_VPAC270_SD_READONLY, .detect_delay_ms = 200, -- cgit v0.10.2 From cf625368d3ad664c7c9ae89974599bbfe9947511 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 14 Aug 2010 06:08:30 +0200 Subject: ARM: pxa: Use PIO for PI2C communication on Palm27x Original idea by: Mike Rapoport Signed-off-by: Marek Vasut diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c index 77ad6d3..405b92a 100644 --- a/arch/arm/mach-pxa/palm27x.c +++ b/arch/arm/mach-pxa/palm27x.c @@ -469,9 +469,13 @@ static struct i2c_board_info __initdata palm27x_pi2c_board_info[] = { }, }; +static struct i2c_pxa_platform_data palm27x_i2c_power_info = { + .use_pio = 1, +}; + void __init palm27x_pmic_init(void) { i2c_register_board_info(1, ARRAY_AND_SIZE(palm27x_pi2c_board_info)); - pxa27x_set_i2c_power_info(NULL); + pxa27x_set_i2c_power_info(&palm27x_i2c_power_info); } #endif -- cgit v0.10.2 From 32c4dad8f872fadb0ae3caa15d26e73934982217 Mon Sep 17 00:00:00 2001 From: "Mark F. Brown" Date: Thu, 26 Aug 2010 05:07:29 -0400 Subject: ARM: pxa168: fix corrected reset vector Reset vector for pxa168 is 0xffff_0000 not 0x0. This fix allows reboot to work Signed-off-by: Mark F. Brown Signed-off-by: Eric Miao diff --git a/arch/arm/mach-mmp/include/mach/system.h b/arch/arm/mach-mmp/include/mach/system.h index 4f5b0e0..1a8a25e 100644 --- a/arch/arm/mach-mmp/include/mach/system.h +++ b/arch/arm/mach-mmp/include/mach/system.h @@ -9,6 +9,8 @@ #ifndef __ASM_MACH_SYSTEM_H #define __ASM_MACH_SYSTEM_H +#include + static inline void arch_idle(void) { cpu_do_idle(); @@ -16,6 +18,9 @@ static inline void arch_idle(void) static inline void arch_reset(char mode, const char *cmd) { - cpu_reset(0); + if (cpu_is_pxa168()) + cpu_reset(0xffff0000); + else + cpu_reset(0); } #endif /* __ASM_MACH_SYSTEM_H */ -- cgit v0.10.2 From cfc6a554d7a364997a43964b4b1290487f890447 Mon Sep 17 00:00:00 2001 From: Eric Miao Date: Tue, 7 Sep 2010 15:10:14 +0800 Subject: ARM: pxa: fix cpu_is_pxa*() not expanding to zero when not configured When CONFIG_PXA3xx is not selected, cpu_is_pxa3xx() doesn't expand to zero, which in some places doesn't result in correct optimization. Signed-off-by: Eric Miao Reported-and-tested-by: Marek Vasut diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h index 7f64d24..b036500 100644 --- a/arch/arm/mach-pxa/include/mach/hardware.h +++ b/arch/arm/mach-pxa/include/mach/hardware.h @@ -264,23 +264,35 @@ * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x * == 0x3 for pxa300/pxa310/pxa320 */ +#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x) #define __cpu_is_pxa2xx(id) \ ({ \ unsigned int _id = (id) >> 13 & 0x7; \ _id <= 0x2; \ }) +#else +#define __cpu_is_pxa2xx(id) (0) +#endif +#ifdef CONFIG_PXA3xx #define __cpu_is_pxa3xx(id) \ ({ \ unsigned int _id = (id) >> 13 & 0x7; \ _id == 0x3; \ }) +#else +#define __cpu_is_pxa3xx(id) (0) +#endif +#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935) #define __cpu_is_pxa93x(id) \ ({ \ unsigned int _id = (id) >> 4 & 0xfff; \ _id == 0x683 || _id == 0x693; \ }) +#else +#define __cpu_is_pxa93x(id) (0) +#endif #define cpu_is_pxa2xx() \ ({ \ -- cgit v0.10.2 From 07a5d146c80b7caa9e754b51f64d3fcbbc74e9c0 Mon Sep 17 00:00:00 2001 From: Haojian Zhuang Date: Wed, 8 Sep 2010 09:42:39 -0400 Subject: ARM: pxa168fb: clear enable bit when not active While fb isn't active, we should clear CFG_GRA_ENA bit. The existing code can't clear this bit. Signed-off-by: Haojian Zhuang Acked-by: Marek Vasut Signed-off-by: Eric Miao diff --git a/drivers/video/pxa168fb.c b/drivers/video/pxa168fb.c index 5d786bd..a31a77f 100644 --- a/drivers/video/pxa168fb.c +++ b/drivers/video/pxa168fb.c @@ -298,8 +298,8 @@ static void set_dma_control0(struct pxa168fb_info *fbi) * Set bit to enable graphics DMA. */ x = readl(fbi->reg_base + LCD_SPU_DMA_CTRL0); - x |= fbi->active ? 0x00000100 : 0; - fbi->active = 0; + x &= ~CFG_GRA_ENA_MASK; + x |= fbi->active ? CFG_GRA_ENA(1) : CFG_GRA_ENA(0); /* * If we are in a pseudo-color mode, we need to enable -- cgit v0.10.2 From d42028060dfe1b9b65a387a849e82fd5c86359fb Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Sat, 11 Sep 2010 22:10:49 -0700 Subject: ARM: pxa: remove pr_ uses of KERN_ Signed-off-by: Joe Perches Signed-off-by: Eric Miao diff --git a/arch/arm/mach-pxa/cpufreq-pxa2xx.c b/arch/arm/mach-pxa/cpufreq-pxa2xx.c index 50d5939..58093d9 100644 --- a/arch/arm/mach-pxa/cpufreq-pxa2xx.c +++ b/arch/arm/mach-pxa/cpufreq-pxa2xx.c @@ -312,8 +312,7 @@ static int pxa_set_target(struct cpufreq_policy *policy, freqs.cpu = policy->cpu; if (freq_debug) - pr_debug(KERN_INFO "Changing CPU frequency to %d Mhz, " - "(SDRAM %d Mhz)\n", + pr_debug("Changing CPU frequency to %d Mhz, (SDRAM %d Mhz)\n", freqs.new / 1000, (pxa_freq_settings[idx].div2) ? (new_freq_mem / 2000) : (new_freq_mem / 1000)); -- cgit v0.10.2 From f064af1e500a2bf4607706f0f458163bdb2a6ea5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Sep 2010 12:43:39 +0000 Subject: net: fix a lockdep splat We have for each socket : One spinlock (sk_slock.slock) One rwlock (sk_callback_lock) Possible scenarios are : (A) (this is used in net/sunrpc/xprtsock.c) read_lock(&sk->sk_callback_lock) (without blocking BH) spin_lock(&sk->sk_slock.slock); ... read_lock(&sk->sk_callback_lock); ... (B) write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) (C) spin_lock_bh(&sk->sk_slock) ... write_lock_bh(&sk->sk_callback_lock) stuff write_unlock_bh(&sk->sk_callback_lock) spin_unlock_bh(&sk->sk_slock) This (C) case conflicts with (A) : CPU1 [A] CPU2 [C] read_lock(callback_lock) spin_lock_bh(slock) We have one problematic (C) use case in inet_csk_listen_stop() : local_bh_disable(); bh_lock_sock(child); // spin_lock_bh(&sk->sk_slock) WARN_ON(sock_owned_by_user(child)); ... sock_orphan(child); // write_lock_bh(&sk->sk_callback_lock) lockdep is not happy with this, as reported by Tetsuo Handa It seems only way to deal with this is to use read_lock_bh(callbacklock) everywhere. Thanks to Jarek for pointing a bug in my first attempt and suggesting this solution. Reported-by: Tetsuo Handa Tested-by: Tetsuo Handa Signed-off-by: Eric Dumazet CC: Jarek Poplawski Tested-by: Eric Dumazet Signed-off-by: David S. Miller diff --git a/net/core/sock.c b/net/core/sock.c index b05b9b6..ef30e9d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1351,9 +1351,9 @@ int sock_i_uid(struct sock *sk) { int uid; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return uid; } EXPORT_SYMBOL(sock_i_uid); @@ -1362,9 +1362,9 @@ unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return ino; } EXPORT_SYMBOL(sock_i_ino); diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index c397524..c519939 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -43,7 +43,7 @@ void rds_tcp_state_change(struct sock *sk) struct rds_connection *conn; struct rds_tcp_connection *tc; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (conn == NULL) { state_change = sk->sk_state_change; @@ -68,7 +68,7 @@ void rds_tcp_state_change(struct sock *sk) break; } out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); state_change(sk); } diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 975183f..27844f2 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -114,7 +114,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes) rdsdebug("listen data ready sk %p\n", sk); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ready = sk->sk_user_data; if (ready == NULL) { /* check for teardown race */ ready = sk->sk_data_ready; @@ -131,7 +131,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes) queue_work(rds_wq, &rds_tcp_listen_work); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); ready(sk, bytes); } diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index 1aba687..e437974 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -324,7 +324,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes) rdsdebug("data ready sk %p bytes %d\n", sk, bytes); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (conn == NULL) { /* check for teardown race */ ready = sk->sk_data_ready; @@ -338,7 +338,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes) if (rds_tcp_read_sock(conn, GFP_ATOMIC, KM_SOFTIRQ0) == -ENOMEM) queue_delayed_work(rds_wq, &conn->c_recv_w, 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); ready(sk, bytes); } diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index a28b895..2f012a0 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -224,7 +224,7 @@ void rds_tcp_write_space(struct sock *sk) struct rds_connection *conn; struct rds_tcp_connection *tc; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); conn = sk->sk_user_data; if (conn == NULL) { write_space = sk->sk_write_space; @@ -244,7 +244,7 @@ void rds_tcp_write_space(struct sock *sk) queue_delayed_work(rds_wq, &conn->c_send_w, 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); /* * write_space is only called when data leaves tcp's send queue if diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index b6309db..fe9306b 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -800,7 +800,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) u32 _xid; __be32 *xp; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); dprintk("RPC: xs_udp_data_ready...\n"); if (!(xprt = xprt_from_sock(sk))) goto out; @@ -852,7 +852,7 @@ static void xs_udp_data_ready(struct sock *sk, int len) dropit: skb_free_datagram(sk, skb); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc) @@ -1229,7 +1229,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) dprintk("RPC: xs_tcp_data_ready...\n"); - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; if (xprt->shutdown) @@ -1248,7 +1248,7 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes) read = tcp_read_sock(sk, &rd_desc, xs_tcp_data_recv); } while (read > 0); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /* @@ -1301,7 +1301,7 @@ static void xs_tcp_state_change(struct sock *sk) { struct rpc_xprt *xprt; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: xs_tcp_state_change client %p...\n", xprt); @@ -1313,7 +1313,7 @@ static void xs_tcp_state_change(struct sock *sk) switch (sk->sk_state) { case TCP_ESTABLISHED: - spin_lock_bh(&xprt->transport_lock); + spin_lock(&xprt->transport_lock); if (!xprt_test_and_set_connected(xprt)) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); @@ -1327,7 +1327,7 @@ static void xs_tcp_state_change(struct sock *sk) xprt_wake_pending_tasks(xprt, -EAGAIN); } - spin_unlock_bh(&xprt->transport_lock); + spin_unlock(&xprt->transport_lock); break; case TCP_FIN_WAIT1: /* The client initiated a shutdown of the socket */ @@ -1365,7 +1365,7 @@ static void xs_tcp_state_change(struct sock *sk) xs_sock_mark_closed(xprt); } out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1376,7 +1376,7 @@ static void xs_error_report(struct sock *sk) { struct rpc_xprt *xprt; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; dprintk("RPC: %s client %p...\n" @@ -1384,7 +1384,7 @@ static void xs_error_report(struct sock *sk) __func__, xprt, sk->sk_err); xprt_wake_pending_tasks(xprt, -EAGAIN); out: - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static void xs_write_space(struct sock *sk) @@ -1416,13 +1416,13 @@ static void xs_write_space(struct sock *sk) */ static void xs_udp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); /* from net/core/sock.c:sock_def_write_space */ if (sock_writeable(sk)) xs_write_space(sk); - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } /** @@ -1437,13 +1437,13 @@ static void xs_udp_write_space(struct sock *sk) */ static void xs_tcp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); /* from net/core/stream.c:sk_stream_write_space */ if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) xs_write_space(sk); - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); } static void xs_udp_do_set_buffer_size(struct rpc_xprt *xprt) -- cgit v0.10.2 From e0f9c4f332c99b213d4a0b7cd21dc0781ceb3d86 Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Thu, 23 Sep 2010 10:59:18 +0000 Subject: de2104x: disable autonegotiation on broken hardware At least on older 21041-AA chips (mine is rev. 11), TP duplex autonegotiation causes the card not to work at all (link is up but no packets are transmitted). de4x5 disables autonegotiation completely. But it seems to work on newer (21041-PA rev. 21) so disable it only on rev<20 chips. Signed-off-by: Ondrej Zary Acked-by: Jeff Garzik Signed-off-by: David S. Miller diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c index 5efa577..9d6b7e9 100644 --- a/drivers/net/tulip/de2104x.c +++ b/drivers/net/tulip/de2104x.c @@ -364,6 +364,8 @@ static u16 t21040_csr15[] = { 0, 0, 0x0006, 0x0000, 0x0000, }; /* 21041 transceiver register settings: TP AUTO, BNC, AUI, TP, TP FD*/ static u16 t21041_csr13[] = { 0xEF01, 0xEF09, 0xEF09, 0xEF01, 0xEF09, }; static u16 t21041_csr14[] = { 0xFFFF, 0xF7FD, 0xF7FD, 0x6F3F, 0x6F3D, }; +/* If on-chip autonegotiation is broken, use half-duplex (FF3F) instead */ +static u16 t21041_csr14_brk[] = { 0xFF3F, 0xF7FD, 0xF7FD, 0x6F3F, 0x6F3D, }; static u16 t21041_csr15[] = { 0x0008, 0x0006, 0x000E, 0x0008, 0x0008, }; @@ -1911,8 +1913,14 @@ fill_defaults: for (i = 0; i < DE_MAX_MEDIA; i++) { if (de->media[i].csr13 == 0xffff) de->media[i].csr13 = t21041_csr13[i]; - if (de->media[i].csr14 == 0xffff) - de->media[i].csr14 = t21041_csr14[i]; + if (de->media[i].csr14 == 0xffff) { + /* autonegotiation is broken at least on some chip + revisions - rev. 0x21 works, 0x11 does not */ + if (de->pdev->revision < 0x20) + de->media[i].csr14 = t21041_csr14_brk[i]; + else + de->media[i].csr14 = t21041_csr14[i]; + } if (de->media[i].csr15 == 0xffff) de->media[i].csr15 = t21041_csr15[i]; } -- cgit v0.10.2 From f1a2481c0ad3aebd94d11b317c488deaadc25002 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Fri, 24 Sep 2010 07:18:22 +0100 Subject: ARM: 6407/1: mmu: Setup MT_MEMORY and MT_MEMORY_NONCACHED L1 entries This patch populates the L1 entries for MT_MEMORY and MT_MEMORY_NONCACHED types so that at boot-up, we can map memories outside system memory at page level granularity Previously the mapping was limiting to section level, which creates unnecessary additional mapping for which physical memory may not present. On the newer ARM with speculation, this is dangerous and can result in untraceable aborts. Signed-off-by: Santosh Shilimkar Signed-off-by: Russell King diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index a486bd0..6a3a2d0 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -247,6 +247,9 @@ static struct mem_type mem_types[] = { .domain = DOMAIN_USER, }, [MT_MEMORY] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_USER | L_PTE_EXEC, + .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, @@ -255,6 +258,9 @@ static struct mem_type mem_types[] = { .domain = DOMAIN_KERNEL, }, [MT_MEMORY_NONCACHED] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_USER | L_PTE_EXEC | L_PTE_MT_BUFFERABLE, + .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, @@ -412,9 +418,12 @@ static void __init build_mem_type_table(void) * Enable CPU-specific coherency if supported. * (Only available on XSC3 at the moment.) */ - if (arch_is_coherent() && cpu_is_xsc3()) + if (arch_is_coherent() && cpu_is_xsc3()) { mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; - + mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; + } /* * ARMv6 and above have extended page tables. */ @@ -439,7 +448,9 @@ static void __init build_mem_type_table(void) mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S; mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; #endif } @@ -476,6 +487,8 @@ static void __init build_mem_type_table(void) mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd; + mem_types[MT_MEMORY].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask; mem_types[MT_ROM].prot_sect |= cp->pmd; switch (cp->pmd) { -- cgit v0.10.2 From e546f21b4b7af012d9f18edad6237339adfeb681 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Fri, 24 Sep 2010 07:19:49 +0100 Subject: ARM: 6408/1: omap: Map only available sram memory Currently we map 1 MB section while setting up SRAM on OMAPs Regardless of the actual memory. The physical OCM RAM available on OMAP SOCs is in order of KBs. This patch maps only available sram and cleans up some un-necessary cpu_is_xxx checks. Mapping un-available or non-accessible(secure) memory on the newer ARM processor is dangerous. Because ARM CPUs can now speculatively prefetch, we should avoid mapping any no-existing or secure memory. Signed-off-by: Santosh Shilimkar Acked-by: Tony Lindgren Signed-off-by: Russell King diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c index 226b2e8..10b3b4c 100644 --- a/arch/arm/plat-omap/sram.c +++ b/arch/arm/plat-omap/sram.c @@ -220,20 +220,7 @@ void __init omap_map_sram(void) if (omap_sram_size == 0) return; - if (cpu_is_omap24xx()) { - omap_sram_io_desc[0].virtual = OMAP2_SRAM_VA; - - base = OMAP2_SRAM_PA; - base = ROUND_DOWN(base, PAGE_SIZE); - omap_sram_io_desc[0].pfn = __phys_to_pfn(base); - } - if (cpu_is_omap34xx()) { - omap_sram_io_desc[0].virtual = OMAP3_SRAM_VA; - base = OMAP3_SRAM_PA; - base = ROUND_DOWN(base, PAGE_SIZE); - omap_sram_io_desc[0].pfn = __phys_to_pfn(base); - /* * SRAM must be marked as non-cached on OMAP3 since the * CORE DPLL M2 divider change code (in SRAM) runs with the @@ -244,13 +231,11 @@ void __init omap_map_sram(void) omap_sram_io_desc[0].type = MT_MEMORY_NONCACHED; } - if (cpu_is_omap44xx()) { - omap_sram_io_desc[0].virtual = OMAP4_SRAM_VA; - base = OMAP4_SRAM_PA; - base = ROUND_DOWN(base, PAGE_SIZE); - omap_sram_io_desc[0].pfn = __phys_to_pfn(base); - } - omap_sram_io_desc[0].length = 1024 * 1024; /* Use section desc */ + omap_sram_io_desc[0].virtual = omap_sram_base; + base = omap_sram_start; + base = ROUND_DOWN(base, PAGE_SIZE); + omap_sram_io_desc[0].pfn = __phys_to_pfn(base); + omap_sram_io_desc[0].length = ROUND_DOWN(omap_sram_size, PAGE_SIZE); iotable_init(omap_sram_io_desc, ARRAY_SIZE(omap_sram_io_desc)); printk(KERN_INFO "SRAM: Mapped pa 0x%08lx to va 0x%08lx size: 0x%lx\n", -- cgit v0.10.2 From 2de5c00ac06c8983ab33ad51a8341584f1cf42c3 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Fri, 24 Sep 2010 07:21:05 +0100 Subject: ARM: 6409/1: davinci: map sram using MT_MEMORY_NONCACHED instead of MT_DEVICE On Davinci SRAM is mapped as MT_DEVICE becasue of the section mapping pre-requisite instead of intended MT_MEMORY_NONCACHED Since the section mapping limitation gets fixed with first patch in this series, the MT_MEMORY_NONCACHED can be used now. Signed-off-by: Santosh Shilimkar Acked-by: Kevin Hilman Signed-off-by: Russell King diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c index 3d996b6..9be261b 100644 --- a/arch/arm/mach-davinci/dm355.c +++ b/arch/arm/mach-davinci/dm355.c @@ -769,8 +769,7 @@ static struct map_desc dm355_io_desc[] = { .virtual = SRAM_VIRT, .pfn = __phys_to_pfn(0x00010000), .length = SZ_32K, - /* MT_MEMORY_NONCACHED requires supersection alignment */ - .type = MT_DEVICE, + .type = MT_MEMORY_NONCACHED, }, }; diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c index 6b6f4c6..7781e35 100644 --- a/arch/arm/mach-davinci/dm365.c +++ b/arch/arm/mach-davinci/dm365.c @@ -969,8 +969,7 @@ static struct map_desc dm365_io_desc[] = { .virtual = SRAM_VIRT, .pfn = __phys_to_pfn(0x00010000), .length = SZ_32K, - /* MT_MEMORY_NONCACHED requires supersection alignment */ - .type = MT_DEVICE, + .type = MT_MEMORY_NONCACHED, }, }; diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c index 40fec31..5e5b0a7 100644 --- a/arch/arm/mach-davinci/dm644x.c +++ b/arch/arm/mach-davinci/dm644x.c @@ -653,8 +653,7 @@ static struct map_desc dm644x_io_desc[] = { .virtual = SRAM_VIRT, .pfn = __phys_to_pfn(0x00008000), .length = SZ_16K, - /* MT_MEMORY_NONCACHED requires supersection alignment */ - .type = MT_DEVICE, + .type = MT_MEMORY_NONCACHED, }, }; diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c index e4a3df1..26e8a9c 100644 --- a/arch/arm/mach-davinci/dm646x.c +++ b/arch/arm/mach-davinci/dm646x.c @@ -737,8 +737,7 @@ static struct map_desc dm646x_io_desc[] = { .virtual = SRAM_VIRT, .pfn = __phys_to_pfn(0x00010000), .length = SZ_32K, - /* MT_MEMORY_NONCACHED requires supersection alignment */ - .type = MT_DEVICE, + .type = MT_MEMORY_NONCACHED, }, }; -- cgit v0.10.2 From 40d24ff9b4309d37999bc0ae91a271f57651d9dd Mon Sep 17 00:00:00 2001 From: Rahul Ruikar Date: Sun, 26 Sep 2010 17:00:29 +0530 Subject: pcmcia: pd6729: Fix error path In error return path call pci_disable_device() which was enabled earlier. Signed-off-by: Rahul Ruikar Signed-off-by: Dominik Brodowski diff --git a/drivers/pcmcia/pd6729.c b/drivers/pcmcia/pd6729.c index b8a869a..deef665 100644 --- a/drivers/pcmcia/pd6729.c +++ b/drivers/pcmcia/pd6729.c @@ -646,7 +646,7 @@ static int __devinit pd6729_pci_probe(struct pci_dev *dev, if (!pci_resource_start(dev, 0)) { dev_warn(&dev->dev, "refusing to load the driver as the " "io_base is NULL.\n"); - goto err_out_free_mem; + goto err_out_disable; } dev_info(&dev->dev, "Cirrus PD6729 PCI to PCMCIA Bridge at 0x%llx " -- cgit v0.10.2 From 245feaa61dbdabffafd47b973595e06abb1288f4 Mon Sep 17 00:00:00 2001 From: Chris Ball Date: Fri, 10 Sep 2010 12:05:24 -0400 Subject: mmc: MAINTAINERS: add myself as MMC maintainer Signed-off-by: Chris Ball Cc: Pierre Ossman Cc: Signed-off-by: Andrew Morton diff --git a/MAINTAINERS b/MAINTAINERS index ceba39b..668682d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3925,8 +3925,10 @@ S: Supported F: drivers/mfd/ MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM -S: Orphan +M: Chris Ball L: linux-mmc@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc.git +S: Maintained F: drivers/mmc/ F: include/linux/mmc/ @@ -5097,8 +5099,10 @@ S: Maintained F: drivers/mmc/host/sdricoh_cs.c SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) DRIVER -S: Orphan +M: Chris Ball L: linux-mmc@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc.git +S: Maintained F: drivers/mmc/host/sdhci.* SECURE DIGITAL HOST CONTROLLER INTERFACE, OPEN FIRMWARE BINDINGS (SDHCI-OF) -- cgit v0.10.2 From 06fe577f841f383b2d4f743cfb74fac7f6468353 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 20 Sep 2010 15:03:42 +0200 Subject: mmc: sdhci-s3c: fix incorrect spinlock usage after merge In the commit f522886e202a34a2191dd5d471b3c4d46410a9a0 a merge conflict in the sdhci-s3c driver been fixed. However the fix used incorrect spinlock operation - it caused a race with sdhci interrupt service. The correct way to solve it is to use spin_lock_irqsave/irqrestore() calls. Signed-off-by: Marek Szyprowski Signed-off-by: Kyungmin Park Signed-off-by: Andrew Morton Signed-off-by: Chris Ball diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c index 71ad416..735d431 100644 --- a/drivers/mmc/host/sdhci-s3c.c +++ b/drivers/mmc/host/sdhci-s3c.c @@ -241,8 +241,10 @@ static struct sdhci_ops sdhci_s3c_ops = { static void sdhci_s3c_notify_change(struct platform_device *dev, int state) { struct sdhci_host *host = platform_get_drvdata(dev); + unsigned long flags; + if (host) { - spin_lock(&host->lock); + spin_lock_irqsave(&host->lock, flags); if (state) { dev_dbg(&dev->dev, "card inserted.\n"); host->flags &= ~SDHCI_DEVICE_DEAD; @@ -253,7 +255,7 @@ static void sdhci_s3c_notify_change(struct platform_device *dev, int state) host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION; } tasklet_schedule(&host->card_tasklet); - spin_unlock(&host->lock); + spin_unlock_irqrestore(&host->lock, flags); } } -- cgit v0.10.2 From 9320f7cbbdd5febf013b0e91db29189724057738 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 23 Sep 2010 16:22:05 +0200 Subject: mmc: sdhci-s3c: fix NULL ptr access in sdhci_s3c_remove If not all clocks have been defined in platform data, the driver will cause a null pointer dereference when it is removed. This patch fixes this issue. Signed-off-by: Marek Szyprowski Signed-off-by: Kyungmin Park Cc: Signed-off-by: Andrew Morton Signed-off-by: Chris Ball diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c index 735d431..aacb862 100644 --- a/drivers/mmc/host/sdhci-s3c.c +++ b/drivers/mmc/host/sdhci-s3c.c @@ -483,8 +483,10 @@ static int __devexit sdhci_s3c_remove(struct platform_device *pdev) sdhci_remove_host(host, 1); for (ptr = 0; ptr < 3; ptr++) { - clk_disable(sc->clk_bus[ptr]); - clk_put(sc->clk_bus[ptr]); + if (sc->clk_bus[ptr]) { + clk_disable(sc->clk_bus[ptr]); + clk_put(sc->clk_bus[ptr]); + } } clk_disable(sc->clk_io); clk_put(sc->clk_io); -- cgit v0.10.2 From b0255a02351b00ca55f4eb2588d05a5db9dd1a58 Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Fri, 24 Sep 2010 23:57:02 +0000 Subject: de2104x: fix power management At least my 21041 cards come out of suspend with bus mastering disabled so they did not work after resume(no data transferred). After adding pci_set_master(), the driver oopsed immediately on resume - because de_clean_rings() is called on suspend but de_init_rings() call was missing in resume. Also disable link (reset SIA) before sleep (de4x5 does this too). Signed-off-by: Ondrej Zary Acked-by: Jeff Garzik Signed-off-by: David S. Miller diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c index 9d6b7e9..a0be7c2 100644 --- a/drivers/net/tulip/de2104x.c +++ b/drivers/net/tulip/de2104x.c @@ -1231,6 +1231,7 @@ static void de_adapter_sleep (struct de_private *de) if (de->de21040) return; + dw32(CSR13, 0); /* Reset phy */ pci_read_config_dword(de->pdev, PCIPM, &pmctl); pmctl |= PM_Sleep; pci_write_config_dword(de->pdev, PCIPM, pmctl); @@ -2166,6 +2167,8 @@ static int de_resume (struct pci_dev *pdev) dev_err(&dev->dev, "pci_enable_device failed in resume\n"); goto out; } + pci_set_master(pdev); + de_init_rings(de); de_init_hw(de); out_attach: netif_device_attach(dev); -- cgit v0.10.2 From ca9a783575d2affed30ef27a3427a7705527ddac Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Sat, 25 Sep 2010 10:39:17 +0000 Subject: de2104x: fix TP link detection Compex FreedomLine 32 PnP-PCI2 cards have only TP and BNC connectors but the SROM contains AUI port too. When TP loses link, the driver switches to non-existing AUI port (which reports that carrier is always present). Connecting TP back generates LinkPass interrupt but de_media_interrupt() is broken - it only updates the link state of currently connected media, ignoring the fact that LinkPass and LinkFail bits of MacStatus register belong to the TP port only (the chip documentation says that). This patch changes de_media_interrupt() to switch media to TP when link goes up (and media type is not locked) and also to update the link state only when the TP port is used. Also the NonselPortActive (and also SelPortActive) bits of SIAStatus register need to be cleared (by writing 1) after reading or they're useless. Signed-off-by: Ondrej Zary Acked-by: Jeff Garzik Signed-off-by: David S. Miller diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c index a0be7c2..9124c5c 100644 --- a/drivers/net/tulip/de2104x.c +++ b/drivers/net/tulip/de2104x.c @@ -243,6 +243,7 @@ enum { NWayState = (1 << 14) | (1 << 13) | (1 << 12), NWayRestart = (1 << 12), NonselPortActive = (1 << 9), + SelPortActive = (1 << 8), LinkFailStatus = (1 << 2), NetCxnErr = (1 << 1), }; @@ -1066,6 +1067,9 @@ static void de21041_media_timer (unsigned long data) unsigned int carrier; unsigned long flags; + /* clear port active bits */ + dw32(SIAStatus, NonselPortActive | SelPortActive); + carrier = (status & NetCxnErr) ? 0 : 1; if (carrier) { @@ -1160,14 +1164,29 @@ no_link_yet: static void de_media_interrupt (struct de_private *de, u32 status) { if (status & LinkPass) { + /* Ignore if current media is AUI or BNC and we can't use TP */ + if ((de->media_type == DE_MEDIA_AUI || + de->media_type == DE_MEDIA_BNC) && + (de->media_lock || + !de_ok_to_advertise(de, DE_MEDIA_TP_AUTO))) + return; + /* If current media is not TP, change it to TP */ + if ((de->media_type == DE_MEDIA_AUI || + de->media_type == DE_MEDIA_BNC)) { + de->media_type = DE_MEDIA_TP_AUTO; + de_stop_rxtx(de); + de_set_media(de); + de_start_rxtx(de); + } de_link_up(de); mod_timer(&de->media_timer, jiffies + DE_TIMER_LINK); return; } BUG_ON(!(status & LinkFail)); - - if (netif_carrier_ok(de->dev)) { + /* Mark the link as down only if current media is TP */ + if (netif_carrier_ok(de->dev) && de->media_type != DE_MEDIA_AUI && + de->media_type != DE_MEDIA_BNC) { de_link_down(de); mod_timer(&de->media_timer, jiffies + DE_TIMER_NO_LINK); } -- cgit v0.10.2 From c8da96e87d349e9035345293093ecc74792fb96a Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sun, 26 Sep 2010 05:55:13 +0100 Subject: TOMOYO: Don't abuse sys_getpid(), sys_getppid() System call entry functions sys_*() are never to be called from general kernel code. The fact that they aren't declared in header files should have been a clue. These functions also don't exist on Alpha since it has sys_getxpid() instead. Signed-off-by: Ben Hutchings Acked-by: Tetsuo Handa Signed-off-by: James Morris diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index ef43995..c668b44 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -1416,15 +1416,19 @@ static char *tomoyo_print_header(struct tomoyo_request_info *r) const pid_t gpid = task_pid_nr(current); static const int tomoyo_buffer_len = 4096; char *buffer = kmalloc(tomoyo_buffer_len, GFP_NOFS); + pid_t ppid; if (!buffer) return NULL; do_gettimeofday(&tv); + rcu_read_lock(); + ppid = task_tgid_vnr(current->real_parent); + rcu_read_unlock(); snprintf(buffer, tomoyo_buffer_len - 1, "#timestamp=%lu profile=%u mode=%s (global-pid=%u)" " task={ pid=%u ppid=%u uid=%u gid=%u euid=%u" " egid=%u suid=%u sgid=%u fsuid=%u fsgid=%u }", tv.tv_sec, r->profile, tomoyo_mode[r->mode], gpid, - (pid_t) sys_getpid(), (pid_t) sys_getppid(), + task_tgid_vnr(current), ppid, current_uid(), current_gid(), current_euid(), current_egid(), current_suid(), current_sgid(), current_fsuid(), current_fsgid()); diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h index 04454cb..7c66bd8 100644 --- a/security/tomoyo/common.h +++ b/security/tomoyo/common.h @@ -689,9 +689,6 @@ struct tomoyo_profile { /********** Function prototypes. **********/ -extern asmlinkage long sys_getpid(void); -extern asmlinkage long sys_getppid(void); - /* Check whether the given string starts with the given keyword. */ bool tomoyo_str_starts(char **src, const char *find); /* Get tomoyo_realpath() of current process. */ -- cgit v0.10.2 From a3d6713fbd2ccb50898a6f88664da96a7857c039 Mon Sep 17 00:00:00 2001 From: Karl Hiramoto Date: Thu, 23 Sep 2010 01:50:54 +0000 Subject: br2684: fix scheduling while atomic You can't call atomic_notifier_chain_unregister() while in atomic context. Fix, call un/register_atmdevice_notifier in module __init and __exit. Bug report: http://comments.gmane.org/gmane.linux.network/172603 Reported-by: Mikko Vinni Tested-by: Mikko Vinni Signed-off-by: Karl Hiramoto Signed-off-by: David S. Miller diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 651babd..ad2b232 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -399,12 +399,6 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb) unregister_netdev(net_dev); free_netdev(net_dev); } - read_lock_irq(&devs_lock); - if (list_empty(&br2684_devs)) { - /* last br2684 device */ - unregister_atmdevice_notifier(&atm_dev_notifier); - } - read_unlock_irq(&devs_lock); return; } @@ -675,7 +669,6 @@ static int br2684_create(void __user *arg) if (list_empty(&br2684_devs)) { /* 1st br2684 device */ - register_atmdevice_notifier(&atm_dev_notifier); brdev->number = 1; } else brdev->number = BRPRIV(list_entry_brdev(br2684_devs.prev))->number + 1; @@ -815,6 +808,7 @@ static int __init br2684_init(void) return -ENOMEM; #endif register_atm_ioctl(&br2684_ioctl_ops); + register_atmdevice_notifier(&atm_dev_notifier); return 0; } @@ -830,9 +824,7 @@ static void __exit br2684_exit(void) #endif - /* if not already empty */ - if (!list_empty(&br2684_devs)) - unregister_atmdevice_notifier(&atm_dev_notifier); + unregister_atmdevice_notifier(&atm_dev_notifier); while (!list_empty(&br2684_devs)) { net_dev = list_entry_brdev(br2684_devs.next); -- cgit v0.10.2 From 693019e90ca45d881109d32c0c6d29adf03f6447 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Thu, 23 Sep 2010 11:19:54 +0000 Subject: net: reset skb queue mapping when rx'ing over tunnel Reset queue mapping when an skb is reentering the stack via a tunnel. On second pass, the queue mapping from the original device is no longer valid. Signed-off-by: Tom Herbert Acked-by: Eric Dumazet Signed-off-by: David S. Miller diff --git a/include/net/dst.h b/include/net/dst.h index 81d1413..0238650 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -242,6 +242,7 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev) dev->stats.rx_packets++; dev->stats.rx_bytes += skb->len; skb->rxhash = 0; + skb_set_queue_mapping(skb, 0); skb_dst_drop(skb); nf_reset(skb); } -- cgit v0.10.2 From 62038e4a146b97352d5911e6ede36c58d4187c3e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Vincent=20Stehl=C3=A9?= Date: Sun, 26 Sep 2010 18:50:05 -0700 Subject: smsc911x: Add MODULE_ALIAS() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This enables auto loading for the smsc911x ethernet driver. Signed-off-by: Vincent Stehlé Signed-off-by: David S. Miller diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c index 0909ae9..8150ba1 100644 --- a/drivers/net/smsc911x.c +++ b/drivers/net/smsc911x.c @@ -58,6 +58,7 @@ MODULE_LICENSE("GPL"); MODULE_VERSION(SMSC_DRV_VERSION); +MODULE_ALIAS("platform:smsc911x"); #if USE_DEBUG > 0 static int debug = 16; -- cgit v0.10.2 From 52933f052186877afd218aef7a1b2dbdb010939f Mon Sep 17 00:00:00 2001 From: Kulikov Vasiliy Date: Sat, 25 Sep 2010 23:58:00 +0000 Subject: ibm_newemac: use free_netdev(netdev) instead of kfree() Freeing netdev without free_netdev() leads to net, tx leaks. I might lead to dereferencing freed pointer. The semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) @@ struct net_device* dev; @@ -kfree(dev) +free_netdev(dev) Signed-off-by: David S. Miller diff --git a/drivers/net/ibm_newemac/core.c b/drivers/net/ibm_newemac/core.c index 3506fd6..519e19e 100644 --- a/drivers/net/ibm_newemac/core.c +++ b/drivers/net/ibm_newemac/core.c @@ -2928,7 +2928,7 @@ static int __devinit emac_probe(struct platform_device *ofdev, if (dev->emac_irq != NO_IRQ) irq_dispose_mapping(dev->emac_irq); err_free: - kfree(ndev); + free_netdev(ndev); err_gone: /* if we were on the bootlist, remove us as we won't show up and * wake up all waiters to notify them in case they were waiting @@ -2971,7 +2971,7 @@ static int __devexit emac_remove(struct platform_device *ofdev) if (dev->emac_irq != NO_IRQ) irq_dispose_mapping(dev->emac_irq); - kfree(dev->ndev); + free_netdev(dev->ndev); return 0; } -- cgit v0.10.2 From 22138d307329e1968fc698821095b87c2fd5de12 Mon Sep 17 00:00:00 2001 From: Kulikov Vasiliy Date: Sat, 25 Sep 2010 23:58:03 +0000 Subject: rionet: use free_netdev(netdev) instead of kfree() Freeing netdev without free_netdev() leads to net, tx leaks. I might lead to dereferencing freed pointer. The semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) @@ struct net_device* dev; @@ -kfree(dev) +free_netdev(dev) Signed-off-by: David S. Miller diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c index 07eb884..44150f2 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -384,7 +384,7 @@ static void rionet_remove(struct rio_dev *rdev) free_pages((unsigned long)rionet_active, rdev->net->hport->sys_size ? __ilog2(sizeof(void *)) + 4 : 0); unregister_netdev(ndev); - kfree(ndev); + free_netdev(ndev); list_for_each_entry_safe(peer, tmp, &rionet_peers, node) { list_del(&peer->node); -- cgit v0.10.2 From 8d879de89807d82bc4cc3e9d73609b874fa9458c Mon Sep 17 00:00:00 2001 From: Kulikov Vasiliy Date: Sat, 25 Sep 2010 23:58:06 +0000 Subject: sgiseeq: use free_netdev(netdev) instead of kfree() Freeing netdev without free_netdev() leads to net, tx leaks. I might lead to dereferencing freed pointer. The semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) @@ struct net_device* dev; @@ -kfree(dev) +free_netdev(dev) Signed-off-by: David S. Miller diff --git a/drivers/net/sgiseeq.c b/drivers/net/sgiseeq.c index cc4bd8c..9265315 100644 --- a/drivers/net/sgiseeq.c +++ b/drivers/net/sgiseeq.c @@ -804,7 +804,7 @@ static int __devinit sgiseeq_probe(struct platform_device *pdev) err_out_free_page: free_page((unsigned long) sp->srings); err_out_free_dev: - kfree(dev); + free_netdev(dev); err_out: return err; -- cgit v0.10.2 From bc68580d41b131396054a1a04a7df4948555ed97 Mon Sep 17 00:00:00 2001 From: Vasiliy Kulikov Date: Sun, 26 Sep 2010 18:56:06 -0700 Subject: s390: use free_netdev(netdev) instead of kfree() Freeing netdev without free_netdev() leads to net, tx leaks. I might lead to dereferencing freed pointer. The semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) @@ struct net_device* dev; @@ -kfree(dev) +free_netdev(dev) Signed-off-by: David S. Miller diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 6edf20b..2c7d2d9 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -1154,7 +1154,7 @@ static struct net_device *ctcm_init_netdevice(struct ctcm_priv *priv) dev_fsm, dev_fsm_len, GFP_KERNEL); if (priv->fsm == NULL) { CTCMY_DBF_DEV(SETUP, dev, "init_fsm error"); - kfree(dev); + free_netdev(dev); return NULL; } fsm_newstate(priv->fsm, DEV_STATE_STOPPED); @@ -1165,7 +1165,7 @@ static struct net_device *ctcm_init_netdevice(struct ctcm_priv *priv) grp = ctcmpc_init_mpc_group(priv); if (grp == NULL) { MPC_DBF_DEV(SETUP, dev, "init_mpc_group error"); - kfree(dev); + free_netdev(dev); return NULL; } tasklet_init(&grp->mpc_tasklet2, -- cgit v0.10.2 From 2cc6d2bf3d6195fabcf0febc192c01f99519a8f3 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Fri, 24 Sep 2010 09:55:52 +0000 Subject: ipv6: add a missing unregister_pernet_subsys call Clean up a missing exit path in the ipv6 module init routines. In addrconf_init we call ipv6_addr_label_init which calls register_pernet_subsys for the ipv6_addr_label_ops structure. But if module loading fails, or if the ipv6 module is removed, there is no corresponding unregister_pernet_subsys call, which leaves a now-bogus address on the pernet_list, leading to oopses in subsequent registrations. This patch cleans up both the failed load path and the unload path. Tested by myself with good results. Signed-off-by: Neil Horman include/net/addrconf.h | 1 + net/ipv6/addrconf.c | 11 ++++++++--- net/ipv6/addrlabel.c | 5 +++++ 3 files changed, 14 insertions(+), 3 deletions(-) Signed-off-by: David S. Miller diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 45375b4..4d40c4d 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -121,6 +121,7 @@ static inline int addrconf_finite_timeout(unsigned long timeout) * IPv6 Address Label subsystem (addrlabel.c) */ extern int ipv6_addr_label_init(void); +extern void ipv6_addr_label_cleanup(void); extern void ipv6_addr_label_rtnl_register(void); extern u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ab70a3f..324fac3 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4637,10 +4637,12 @@ int __init addrconf_init(void) if (err < 0) { printk(KERN_CRIT "IPv6 Addrconf:" " cannot initialize default policy table: %d.\n", err); - return err; + goto out; } - register_pernet_subsys(&addrconf_ops); + err = register_pernet_subsys(&addrconf_ops); + if (err < 0) + goto out_addrlabel; /* The addrconf netdev notifier requires that loopback_dev * has it's ipv6 private information allocated and setup @@ -4692,7 +4694,9 @@ errout: unregister_netdevice_notifier(&ipv6_dev_notf); errlo: unregister_pernet_subsys(&addrconf_ops); - +out_addrlabel: + ipv6_addr_label_cleanup(); +out: return err; } @@ -4703,6 +4707,7 @@ void addrconf_cleanup(void) unregister_netdevice_notifier(&ipv6_dev_notf); unregister_pernet_subsys(&addrconf_ops); + ipv6_addr_label_cleanup(); rtnl_lock(); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index f0e774c..8175f80 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -393,6 +393,11 @@ int __init ipv6_addr_label_init(void) return register_pernet_subsys(&ipv6_addr_label_ops); } +void ipv6_addr_label_cleanup(void) +{ + unregister_pernet_subsys(&ipv6_addr_label_ops); +} + static const struct nla_policy ifal_policy[IFAL_MAX+1] = { [IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), }, [IFAL_LABEL] = { .len = sizeof(u32), }, -- cgit v0.10.2 From c9e2fbd909c20b165b2b9ffb59f8b674cf0a55b0 Mon Sep 17 00:00:00 2001 From: Alexander Chumachenko Date: Thu, 1 Apr 2010 15:34:52 +0300 Subject: x86: Avoid 'constant_test_bit()' misoptimization due to cast to non-volatile While debugging bit_spin_lock() hang, it was tracked down to gcc-4.4 misoptimization of non-inlined constant_test_bit() due to non-volatile addr when 'const volatile unsigned long *addr' cast to 'unsigned long *' with subsequent unconditional jump to pause (and not to the test) leading to hang. Compiling with gcc-4.3 or disabling CONFIG_OPTIMIZE_INLINING yields inlined constant_test_bit() and correct jump, thus working around the kernel bug. Other arches than asm-x86 may implement this slightly differently; 2.6.29 mitigates the misoptimization by changing the function prototype (commit c4295fbb6048d85f0b41c5ced5cbf63f6811c46c) but probably fixing the issue itself is better. Signed-off-by: Alexander Chumachenko Signed-off-by: Michael Shigorin Acked-by: Linus Torvalds Signed-off-by: H. Peter Anvin diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 545776e..bafd80d 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -309,7 +309,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr) static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr) { return ((1UL << (nr % BITS_PER_LONG)) & - (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0; + (addr[nr / BITS_PER_LONG])) != 0; } static inline int variable_test_bit(int nr, volatile const unsigned long *addr) -- cgit v0.10.2 From 00740c58541b6087d78418cebca1fcb86dc6077d Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sun, 26 Sep 2010 12:42:23 +0200 Subject: amd64_edac: Fix driver module removal f4347553b30ec66530bfe63c84530afea3803396 removed the edac polling mechanism in favor of using a notifier chain for conveying MCE information to edac. However, the module removal path didn't test whether the driver had setup the polling function workqueue at all and the rmmod process was hanging in the kernel at try_to_del_timer_sync() in the cancel_delayed_work() path, trying to cancel an uninitialized work struct. Fix that by adding a balancing check to the workqueue removal path. Signed-off-by: Borislav Petkov diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 3630308..6b21e25 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -339,6 +339,9 @@ static void edac_mc_workq_teardown(struct mem_ctl_info *mci) { int status; + if (mci->op_state != OP_RUNNING_POLL) + return; + status = cancel_delayed_work(&mci->work); if (status == 0) { debugf0("%s() not canceled, flush the queue\n", -- cgit v0.10.2 From 1d6400c7c9cfd38976b25d55b357200ad3ff1be9 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 13 Sep 2010 15:53:18 +0000 Subject: net/9p: fix memory handling/allocation in rdma_request() Return -ENOMEM when erroring on kmalloc and fix memory leaks when returning on error. Signed-off-by: Davidlohr Bueso Reviewed-by: Aneesh Kumar K.V Signed-off-by: Eric Van Hensbergen diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 0ea20c3..17c5ba7 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -426,8 +426,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) /* Allocate an fcall for the reply */ rpl_context = kmalloc(sizeof *rpl_context, GFP_KERNEL); - if (!rpl_context) + if (!rpl_context) { + err = -ENOMEM; goto err_close; + } /* * If the request has a buffer, steal it, otherwise @@ -445,8 +447,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) } rpl_context->rc = req->rc; if (!rpl_context->rc) { - kfree(rpl_context); - goto err_close; + err = -ENOMEM; + goto err_free2; } /* @@ -458,11 +460,8 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) */ if (atomic_inc_return(&rdma->rq_count) <= rdma->rq_depth) { err = post_recv(client, rpl_context); - if (err) { - kfree(rpl_context->rc); - kfree(rpl_context); - goto err_close; - } + if (err) + goto err_free1; } else atomic_dec(&rdma->rq_count); @@ -471,8 +470,10 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) /* Post the request */ c = kmalloc(sizeof *c, GFP_KERNEL); - if (!c) - goto err_close; + if (!c) { + err = -ENOMEM; + goto err_free1; + } c->req = req; c->busa = ib_dma_map_single(rdma->cm_id->device, @@ -499,9 +500,15 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) return ib_post_send(rdma->qp, &wr, &bad_wr); error: + kfree(c); + kfree(rpl_context->rc); + kfree(rpl_context); P9_DPRINTK(P9_DEBUG_ERROR, "EIO\n"); return -EIO; - + err_free1: + kfree(rpl_context->rc); + err_free2: + kfree(rpl_context); err_close: spin_lock_irqsave(&rdma->req_lock, flags); if (rdma->state < P9_RDMA_CLOSING) { -- cgit v0.10.2 From 2de59fea8b3095d1df4c729fda041625930aab4f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Mon, 27 Sep 2010 14:55:15 +0100 Subject: ARM: 6411/1: vexpress: set RAM latencies to 1 cycle for PL310 on ct-ca9x4 tile The PL310 on the ct-ca9x4 tile for the Versatile Express does not need to add additional latency when accessing its cache RAMs. Unfortunately, the boot monitor sets this up for an 8-cycle delay on reads and writes, resulting in greatly reduced memory performance when the L2 cache is enabled. This patch sets the L2 RAM latencies to the correct value of 1 cycle on the ct-ca9x4 tile before enabling the L2 cache. Acked-by: Catalin Marinas Signed-off-by: Will Deacon Signed-off-by: Russell King diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c index 1c9c13e..efb1270 100644 --- a/arch/arm/mach-vexpress/ct-ca9x4.c +++ b/arch/arm/mach-vexpress/ct-ca9x4.c @@ -227,7 +227,13 @@ static void ct_ca9x4_init(void) int i; #ifdef CONFIG_CACHE_L2X0 - l2x0_init(MMIO_P2V(CT_CA9X4_L2CC), 0x00400000, 0xfe0fffff); + void __iomem *l2x0_base = MMIO_P2V(CT_CA9X4_L2CC); + + /* set RAM latencies to 1 cycle for this core tile. */ + writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL); + writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL); + + l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff); #endif clkdev_add_table(lookups, ARRAY_SIZE(lookups)); -- cgit v0.10.2 From bec658ff31453a5726b1c188674d587a5d40c482 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Sat, 18 Sep 2010 19:38:21 -0500 Subject: RDMA/cxgb3: Turn off RX coalescing for iWARP connections The HW by default has RX coalescing on. For iWARP connections, this causes a 100ms delay in connection establishement due to the ingress MPA Start message being stalled in HW. So explicitly turn RX coalescing off when setting up iWARP connections. This was causing very bad performance for NP64 gather operations using Open MPI, due to the way it sets up connections on larger jobs. Signed-off-by: Steve Wise Cc: Signed-off-by: Roland Dreier diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c index d88077a..13c8887 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.c +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c @@ -463,7 +463,8 @@ static int send_connect(struct iwch_ep *ep) V_MSS_IDX(mtu_idx) | V_L2T_IDX(ep->l2t->idx) | V_TX_CHANNEL(ep->l2t->smt_idx); opt0l = V_TOS((ep->tos >> 2) & M_TOS) | V_RCV_BUFSIZ(rcv_win>>10); - opt2 = V_FLAVORS_VALID(1) | V_CONG_CONTROL_FLAVOR(cong_flavor); + opt2 = F_RX_COALESCE_VALID | V_RX_COALESCE(0) | V_FLAVORS_VALID(1) | + V_CONG_CONTROL_FLAVOR(cong_flavor); skb->priority = CPL_PRIORITY_SETUP; set_arp_failure_handler(skb, act_open_req_arp_failure); @@ -1280,7 +1281,8 @@ static void accept_cr(struct iwch_ep *ep, __be32 peer_ip, struct sk_buff *skb) V_MSS_IDX(mtu_idx) | V_L2T_IDX(ep->l2t->idx) | V_TX_CHANNEL(ep->l2t->smt_idx); opt0l = V_TOS((ep->tos >> 2) & M_TOS) | V_RCV_BUFSIZ(rcv_win>>10); - opt2 = V_FLAVORS_VALID(1) | V_CONG_CONTROL_FLAVOR(cong_flavor); + opt2 = F_RX_COALESCE_VALID | V_RX_COALESCE(0) | V_FLAVORS_VALID(1) | + V_CONG_CONTROL_FLAVOR(cong_flavor); rpl = cplhdr(skb); rpl->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD)); -- cgit v0.10.2 From 3fd6c88ef875a14740801ebfc6b6e4e064a1cdd4 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 27 Sep 2010 11:07:00 -0700 Subject: 3c59x: fix regression from patch "Add ethtool WOL support" This patch (commit 690a1f2002a3091bd18a501f46c9530f10481463) added a new call site for acpi_set_WOL() without checking that the function is actually suitable to be called via vortex_set_wol+0xcd/0xe0 [3c59x] dev_ethtool+0xa5a/0xb70 dev_ioctl+0x2e0/0x4b0 T.961+0x49/0x50 sock_ioctl+0x47/0x290 do_vfs_ioctl+0x7f/0x340 sys_ioctl+0x80/0xa0 system_call_fastpath+0x16/0x1b i.e. outside of code paths run when the device is not yet enabled or already disabled. In particular, putting the device into D3hot is a pretty bad idea when it was already brought up. Furthermore, all prior callers of the function made sure they're actually dealing with a PCI device, while the newly added one didn't. In the same spirit, the .get_wol handler shouldn't indicate support for WOL for non-PCI devices. Signed-off-by: Jan Beulich Signed-off-by: David S. Miller diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c index fa42103..179871d 100644 --- a/drivers/net/3c59x.c +++ b/drivers/net/3c59x.c @@ -2942,6 +2942,9 @@ static void vortex_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct vortex_private *vp = netdev_priv(dev); + if (!VORTEX_PCI(vp)) + return; + wol->supported = WAKE_MAGIC; wol->wolopts = 0; @@ -2952,6 +2955,10 @@ static void vortex_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static int vortex_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct vortex_private *vp = netdev_priv(dev); + + if (!VORTEX_PCI(vp)) + return -EOPNOTSUPP; + if (wol->wolopts & ~WAKE_MAGIC) return -EINVAL; @@ -3201,6 +3208,9 @@ static void acpi_set_WOL(struct net_device *dev) return; } + if (VORTEX_PCI(vp)->current_state < PCI_D3hot) + return; + /* Change the power state to D3; RxEnable doesn't take effect. */ pci_set_power_state(VORTEX_PCI(vp), PCI_D3hot); } -- cgit v0.10.2 From c52c2ddc1dfa6fe85ffd5e4c57cf91f6982639fe Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Sep 2010 19:28:12 +0100 Subject: alpha: switch osf_sigprocmask() to use of sigprocmask() get rid of a useless wrapper, while we are at it Signed-off-by: Al Viro Signed-off-by: Linus Torvalds diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index d1273c1..6d159ce 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -915,15 +915,6 @@ sys_execve: .end sys_execve .align 4 - .globl osf_sigprocmask - .ent osf_sigprocmask -osf_sigprocmask: - .prologue 0 - mov $sp, $18 - jmp $31, sys_osf_sigprocmask -.end osf_sigprocmask - - .align 4 .globl alpha_ni_syscall .ent alpha_ni_syscall alpha_ni_syscall: diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index 0f6b51a..06609aa 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -41,46 +41,20 @@ static void do_signal(struct pt_regs *, struct switch_stack *, /* * The OSF/1 sigprocmask calling sequence is different from the * C sigprocmask() sequence.. - * - * how: - * 1 - SIG_BLOCK - * 2 - SIG_UNBLOCK - * 3 - SIG_SETMASK - * - * We change the range to -1 .. 1 in order to let gcc easily - * use the conditional move instructions. - * - * Note that we don't need to acquire the kernel lock for SMP - * operation, as all of this is local to this thread. */ -SYSCALL_DEFINE3(osf_sigprocmask, int, how, unsigned long, newmask, - struct pt_regs *, regs) +SYSCALL_DEFINE2(osf_sigprocmask, int, how, unsigned long, newmask) { - unsigned long oldmask = -EINVAL; - - if ((unsigned long)how-1 <= 2) { - long sign = how-2; /* -1 .. 1 */ - unsigned long block, unblock; - - newmask &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); - oldmask = current->blocked.sig[0]; - - unblock = oldmask & ~newmask; - block = oldmask | newmask; - if (!sign) - block = unblock; - if (sign <= 0) - newmask = block; - if (_NSIG_WORDS > 1 && sign > 0) - sigemptyset(¤t->blocked); - current->blocked.sig[0] = newmask; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - regs->r0 = 0; /* special no error return */ + sigset_t oldmask; + sigset_t mask; + unsigned long res; + + siginitset(&mask, newmask & ~_BLOCKABLE); + res = siprocmask(how, &mask, &oldmask); + if (!res) { + force_successful_syscall_return(); + res = oldmask->sig[0]; } - return oldmask; + return res; } SYSCALL_DEFINE3(osf_sigaction, int, sig, diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S index ce594ef..a6a1de9 100644 --- a/arch/alpha/kernel/systbls.S +++ b/arch/alpha/kernel/systbls.S @@ -58,7 +58,7 @@ sys_call_table: .quad sys_open /* 45 */ .quad alpha_ni_syscall .quad sys_getxgid - .quad osf_sigprocmask + .quad sys_osf_sigprocmask .quad alpha_ni_syscall .quad alpha_ni_syscall /* 50 */ .quad sys_acct -- cgit v0.10.2 From 18e6bfa96d4d810ad9a69e17f08e0d0089379f22 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Sep 2010 19:28:22 +0100 Subject: alpha: __get_user/__put_user results need to be checked... Signed-off-by: Al Viro Signed-off-by: Linus Torvalds diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index 06609aa..779780a 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -68,9 +68,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig, old_sigset_t mask; if (!access_ok(VERIFY_READ, act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_flags, &act->sa_flags)) + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) return -EFAULT; - __get_user(mask, &act->sa_mask); siginitset(&new_ka.sa.sa_mask, mask); new_ka.ka_restorer = NULL; } @@ -80,9 +80,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig, if (!ret && oact) { if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || - __put_user(old_ka.sa.sa_flags, &oact->sa_flags)) + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); } return ret; -- cgit v0.10.2 From e46924d246e028c94689087db0699438343a344e Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Sep 2010 19:28:32 +0100 Subject: mn10300: avoid SIGSEGV delivery loop force_sigsegv() is there for purpose... Signed-off-by: Al Viro Signed-off-by: Linus Torvalds diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c index 717db14..57178a8 100644 --- a/arch/mn10300/kernel/signal.c +++ b/arch/mn10300/kernel/signal.c @@ -345,7 +345,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, return 0; give_sigsegv: - force_sig(SIGSEGV, current); + force_sigsegv(sig, current); return -EFAULT; } @@ -428,7 +428,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, return 0; give_sigsegv: - force_sig(SIGSEGV, current); + force_sigsegv(sig, current); return -EFAULT; } -- cgit v0.10.2 From 00cbf6080c7d60b999864afcd9010e0bbc7c5db6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Sep 2010 19:28:42 +0100 Subject: mn10300: prevent double syscall restarts set ->orig_d0 to -1, same as what sigreturn does Signed-off-by: Al Viro Signed-off-by: Linus Torvalds diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c index 57178a8..4ef9925 100644 --- a/arch/mn10300/kernel/signal.c +++ b/arch/mn10300/kernel/signal.c @@ -432,6 +432,12 @@ give_sigsegv: return -EFAULT; } +static inline void stepback(struct pt_regs *regs) +{ + regs->pc -= 2; + regs->orig_d0 = -1; +} + /* * handle the actual delivery of a signal to userspace */ @@ -459,7 +465,7 @@ static int handle_signal(int sig, /* fallthrough */ case -ERESTARTNOINTR: regs->d0 = regs->orig_d0; - regs->pc -= 2; + stepback(regs); } } @@ -527,12 +533,12 @@ static void do_signal(struct pt_regs *regs) case -ERESTARTSYS: case -ERESTARTNOINTR: regs->d0 = regs->orig_d0; - regs->pc -= 2; + stepback(regs); break; case -ERESTART_RESTARTBLOCK: regs->d0 = __NR_restart_syscall; - regs->pc -= 2; + stepback(regs); break; } } -- cgit v0.10.2 From c05628b49b19187841d635dddd3e47caab33242b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Sep 2010 19:28:52 +0100 Subject: mn10300: ->restart_block.fn needs to be reset on sigreturn Signed-off-by: Al Viro Signed-off-by: Linus Torvalds diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c index 4ef9925..5a2c004 100644 --- a/arch/mn10300/kernel/signal.c +++ b/arch/mn10300/kernel/signal.c @@ -102,6 +102,9 @@ static int restore_sigcontext(struct pt_regs *regs, { unsigned int err = 0; + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + if (is_using_fpu(current)) fpu_kill_state(current); -- cgit v0.10.2 From 8e87354d01b3046aa5e1080419178191f3dce8f0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Sep 2010 19:29:02 +0100 Subject: mn10300: get rid of set_fs(USER_DS) in sigframe setup It really has no business being there; short of a serious kernel bug we should already have USER_DS at that point. It shouldn't have been done on x86 either... Signed-off-by: Al Viro Signed-off-by: Linus Torvalds diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c index 5a2c004..ae36480 100644 --- a/arch/mn10300/kernel/signal.c +++ b/arch/mn10300/kernel/signal.c @@ -333,8 +333,6 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, regs->d0 = sig; regs->d1 = (unsigned long) &frame->sc; - set_fs(USER_DS); - /* the tracer may want to single-step inside the handler */ if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); @@ -416,8 +414,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->d0 = sig; regs->d1 = (long) &frame->info; - set_fs(USER_DS); - /* the tracer may want to single-step inside the handler */ if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); -- cgit v0.10.2 From 60bdb72e3c2e808228612f672bd8d18e82872de3 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Sep 2010 19:29:12 +0100 Subject: mn10300: check __get_user/__put_user results... Signed-off-by: Al Viro Signed-off-by: Linus Torvalds diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c index ae36480..d4de05a 100644 --- a/arch/mn10300/kernel/signal.c +++ b/arch/mn10300/kernel/signal.c @@ -65,10 +65,10 @@ asmlinkage long sys_sigaction(int sig, old_sigset_t mask; if (verify_area(VERIFY_READ, act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_restorer, &act->sa_restorer)) + __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) return -EFAULT; - __get_user(new_ka.sa.sa_flags, &act->sa_flags); - __get_user(mask, &act->sa_mask); siginitset(&new_ka.sa.sa_mask, mask); } @@ -77,10 +77,10 @@ asmlinkage long sys_sigaction(int sig, if (!ret && oact) { if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) || __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || - __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer)) + __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; - __put_user(old_ka.sa.sa_flags, &oact->sa_flags); - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); } return ret; -- cgit v0.10.2 From b3de7559afbb7a8a35b4be975a6adf6c5e3cdca0 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 24 Sep 2010 13:22:06 +0000 Subject: tcp: fix TSO FACK loss marking in tcp_mark_head_lost MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When TCP uses FACK algorithm to mark lost packets in tcp_mark_head_lost(), if the number of packets in the (TSO) skb is greater than the number of packets that should be marked lost, TCP incorrectly exits the loop and marks no packets lost in the skb. This underestimates tp->lost_out and affects the recovery/retransmission. This patch fargments the skb and marks the correct amount of packets lost. Signed-off-by: Yuchung Cheng Acked-by: Ilpo Järvinen Signed-off-by: David S. Miller diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 149e79a..b55f60f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2545,7 +2545,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) cnt += tcp_skb_pcount(skb); if (cnt > packets) { - if (tcp_is_sack(tp) || (oldcnt >= packets)) + if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || + (oldcnt >= packets)) break; mss = skb_shinfo(skb)->gso_size; -- cgit v0.10.2 From 7e1b33e5ea392dfc984fc63b76ca75acbf249dcd Mon Sep 17 00:00:00 2001 From: Ulrich Weber Date: Mon, 27 Sep 2010 15:02:18 -0700 Subject: ipv6: add IPv6 to neighbour table overflow warning IPv4 and IPv6 have separate neighbour tables, so the warning messages should be distinguishable. [ Add a suitable message prefix on the ipv4 side as well -DaveM ] Signed-off-by: Ulrich Weber Signed-off-by: David S. Miller diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6298f75..ac6559c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1231,7 +1231,7 @@ restart: } if (net_ratelimit()) - printk(KERN_WARNING "Neighbour table overflow.\n"); + printk(KERN_WARNING "ipv4: Neighbour table overflow.\n"); rt_drop(rt); return -ENOBUFS; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d126365..8323136 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -670,7 +670,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad if (net_ratelimit()) printk(KERN_WARNING - "Neighbour table overflow.\n"); + "ipv6: Neighbour table overflow.\n"); dst_free(&rt->dst); return NULL; } -- cgit v0.10.2 From fb0c5f0bc8b69b40549449ee7fc65f3706f12062 Mon Sep 17 00:00:00 2001 From: Ulrich Weber Date: Mon, 27 Sep 2010 03:31:00 +0000 Subject: tproxy: check for transparent flag in ip_route_newports as done in ip_route_connect() Signed-off-by: Ulrich Weber Signed-off-by: David S. Miller diff --git a/include/net/route.h b/include/net/route.h index bd732d6..7e5e73b 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -199,6 +199,8 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol, fl.fl_ip_sport = sport; fl.fl_ip_dport = dport; fl.proto = protocol; + if (inet_sk(sk)->transparent) + fl.flags |= FLOWI_FLAG_ANYSRC; ip_rt_put(*rp); *rp = NULL; security_sk_classify_flow(sk, &fl); -- cgit v0.10.2 From 387a85628782690b56492dae4bbf544639f5d4a9 Mon Sep 17 00:00:00 2001 From: Ondrej Zary Date: Mon, 27 Sep 2010 11:41:45 +0000 Subject: de2104x: fix ethtool When the interface is up, using ethtool breaks it because: a) link is put down but media_timer interval is not shortened to NO_LINK b) rxtx is stopped but not restarted Also manual 10baseT-HD (and probably FD too - untested) mode does not work - the link is forced up, packets are transmitted but nothing is received. Changing CSR14 value to match documentation (not disabling link check) fixes this. Signed-off-by: Ondrej Zary Acked-by: Jeff Garzik Signed-off-by: David S. Miller diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c index 9124c5c..6888e3d 100644 --- a/drivers/net/tulip/de2104x.c +++ b/drivers/net/tulip/de2104x.c @@ -364,9 +364,9 @@ static u16 t21040_csr15[] = { 0, 0, 0x0006, 0x0000, 0x0000, }; /* 21041 transceiver register settings: TP AUTO, BNC, AUI, TP, TP FD*/ static u16 t21041_csr13[] = { 0xEF01, 0xEF09, 0xEF09, 0xEF01, 0xEF09, }; -static u16 t21041_csr14[] = { 0xFFFF, 0xF7FD, 0xF7FD, 0x6F3F, 0x6F3D, }; +static u16 t21041_csr14[] = { 0xFFFF, 0xF7FD, 0xF7FD, 0x7F3F, 0x7F3D, }; /* If on-chip autonegotiation is broken, use half-duplex (FF3F) instead */ -static u16 t21041_csr14_brk[] = { 0xFF3F, 0xF7FD, 0xF7FD, 0x6F3F, 0x6F3D, }; +static u16 t21041_csr14_brk[] = { 0xFF3F, 0xF7FD, 0xF7FD, 0x7F3F, 0x7F3D, }; static u16 t21041_csr15[] = { 0x0008, 0x0006, 0x000E, 0x0008, 0x0008, }; @@ -1596,12 +1596,15 @@ static int __de_set_settings(struct de_private *de, struct ethtool_cmd *ecmd) return 0; /* nothing to change */ de_link_down(de); + mod_timer(&de->media_timer, jiffies + DE_TIMER_NO_LINK); de_stop_rxtx(de); de->media_type = new_media; de->media_lock = media_lock; de->media_advertise = ecmd->advertising; de_set_media(de); + if (netif_running(de->dev)) + de_start_rxtx(de); return 0; } -- cgit v0.10.2 From 0b20406cda621c2495d10baab1e87127ceb43337 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Mon, 27 Sep 2010 15:54:44 -0700 Subject: net/9p: Mount only matching virtio channels p9_virtio_create will only compare the the channel's tag characters against the device name till the end of the channel's tag but not till the end of the device name. This means that if a user defines channels with the tags foo and foobar then he would mount foo when he requested foonot and may mount foo when he requested foobar. Thus it is necessary to check both string lengths against each other in case of a successful partial string match. Signed-off-by: Sven Eckelmann Signed-off-by: David S. Miller diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index dcfbe99..b885159 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -329,7 +329,8 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args) mutex_lock(&virtio_9p_lock); list_for_each_entry(chan, &virtio_chan_list, chan_list) { - if (!strncmp(devname, chan->tag, chan->tag_len)) { + if (!strncmp(devname, chan->tag, chan->tag_len) && + strlen(devname) == chan->tag_len) { if (!chan->inuse) { chan->inuse = true; found = 1; -- cgit v0.10.2 From 95929eff2cb01e9858779283795f4e3943ee020d Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 27 Sep 2010 13:12:33 +0100 Subject: MN10300: Default config choice GDBSTUB_TTYSM0 should be GDBSTUB_ON_TTYSM0 The configuration choice for the port on which the GDB stub listens has a default of GDBSTUB_TTYSM0, but this should be GDBSTUB_ON_TTYSM0 to match the option. Signed-off-by: David Howells Signed-off-by: Linus Torvalds diff --git a/arch/mn10300/Kconfig.debug b/arch/mn10300/Kconfig.debug index ff80e86..ce83c74 100644 --- a/arch/mn10300/Kconfig.debug +++ b/arch/mn10300/Kconfig.debug @@ -101,7 +101,7 @@ config GDBSTUB_DEBUG_BREAKPOINT choice prompt "GDB stub port" - default GDBSTUB_TTYSM0 + default GDBSTUB_ON_TTYSM0 depends on GDBSTUB help Select the serial port used for GDB-stub. -- cgit v0.10.2 From 252a52aa4fa22a668f019e55b3aac3ff71ec1c29 Mon Sep 17 00:00:00 2001 From: Dan Rosenberg Date: Mon, 27 Sep 2010 12:30:28 -0400 Subject: Fix pktcdvd ioctl dev_minor range check The PKT_CTRL_CMD_STATUS device ioctl retrieves a pointer to a pktcdvd_device from the global pkt_devs array. The index into this array is provided directly by the user and is a signed integer, so the comparison to ensure that it falls within the bounds of this array will fail when provided with a negative index. This can be used to read arbitrary kernel memory or cause a crash due to an invalid pointer dereference. This can be exploited by users with permission to open /dev/pktcdvd/control (on many distributions, this is readable by group "cdrom"). Signed-off-by: Dan Rosenberg [ Rather than add a cast, just make the function take the right type -Linus ] Signed-off-by: Linus Torvalds diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index b1cbeb5..37a2bb5 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2369,7 +2369,7 @@ static void pkt_release_dev(struct pktcdvd_device *pd, int flush) pkt_shrink_pktlist(pd); } -static struct pktcdvd_device *pkt_find_dev_from_minor(int dev_minor) +static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor) { if (dev_minor >= MAX_WRITERS) return NULL; -- cgit v0.10.2 From 01db403cf99f739f86903314a489fb420e0e254f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 27 Sep 2010 20:24:54 -0700 Subject: tcp: Fix >4GB writes on 64-bit. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes kernel bugzilla #16603 tcp_sendmsg() truncates iov_len to an 'int' which a 4GB write to write zero bytes, for example. There is also the problem higher up of how verify_iovec() works. It wants to prevent the total length from looking like an error return value. However it does this using 'int', but syscalls return 'long' (and thus signed 64-bit on 64-bit machines). So it could trigger false-positives on 64-bit as written. So fix it to use 'long'. Reported-by: Olaf Bonorden Reported-by: Daniel Büse Reported-by: Andrew Morton Signed-off-by: David S. Miller diff --git a/include/linux/socket.h b/include/linux/socket.h index a2fada9..a8f56e1 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -322,7 +322,7 @@ extern int csum_partial_copy_fromiovecend(unsigned char *kdata, int offset, unsigned int len, __wsum *csump); -extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode); +extern long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode); extern int memcpy_toiovec(struct iovec *v, unsigned char *kdata, int len); extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, int offset, int len); diff --git a/net/core/iovec.c b/net/core/iovec.c index 1cd98df..e6b133b 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -35,9 +35,10 @@ * in any case. */ -int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) +long verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) { - int size, err, ct; + int size, ct; + long err; if (m->msg_namelen) { if (mode == VERIFY_READ) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 95d75d4..f115ea6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -943,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sg = sk->sk_route_caps & NETIF_F_SG; while (--iovlen >= 0) { - int seglen = iov->iov_len; + size_t seglen = iov->iov_len; unsigned char __user *from = iov->iov_base; iov++; -- cgit v0.10.2 From fff2017354a3a9906862aabbf2a1cae5b4330e40 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Mon, 27 Sep 2010 18:01:49 -0700 Subject: hwmon (coretemp): Fix build breakage if SMP is undefined Commit e40cc4bdfd4b89813f072f72bd9c7055814d3f0f introduced a build breakage if CONFIG_SMP is undefined. This commit fixes the problem. This fix is only a workaround. For a real fix, cpu_sibling_mask() should be defined in UP include code, eg in linux/smp.h, and asm/smp.h should not be included directly. This fix is currently not possible because asm/smp.h defines cpu_sibling_mask() unconditionally and is included directly from many source files. Reported-by: Ingo Molnar Tested-by: Ingo Molnar Signed-off-by: Guenter Roeck Cc: Fenghua Yu diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index baa842a..a23b17a 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -36,6 +36,7 @@ #include #include #include +#include #define DRVNAME "coretemp" -- cgit v0.10.2 From fad16e7a7f67eef8d33f8ad58850db89382b09ce Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 21 Sep 2010 09:25:48 +0200 Subject: ahci: fix module refcount breakage introduced by libahci split libata depends on scsi_host_template for module reference counting and sht's should be owned by each low level driver. During libahci split, the sht was left with libahci.ko leaving the actual low level drivers not reference counted. This made ahci and ahci_platform always unloadable even while they're being actively used. Fix it by defining AHCI_SHT() macro in ahci.h and defining a sht for each low level ahci driver. stable: only applicable to 2.6.35. Signed-off-by: Tejun Heo Reported-by: Pedro Francisco Tested-by: Michael Tokarev Cc: stable@kernel.org Signed-off-by: Jeff Garzik diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index ff1c945..99d0e5a 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -90,6 +90,10 @@ static int ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg); static int ahci_pci_device_resume(struct pci_dev *pdev); #endif +static struct scsi_host_template ahci_sht = { + AHCI_SHT("ahci"), +}; + static struct ata_port_operations ahci_vt8251_ops = { .inherits = &ahci_ops, .hardreset = ahci_vt8251_hardreset, diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 474427b..e5fdeeb 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -298,7 +298,17 @@ struct ahci_host_priv { extern int ahci_ignore_sss; -extern struct scsi_host_template ahci_sht; +extern struct device_attribute *ahci_shost_attrs[]; +extern struct device_attribute *ahci_sdev_attrs[]; + +#define AHCI_SHT(drv_name) \ + ATA_NCQ_SHT(drv_name), \ + .can_queue = AHCI_MAX_CMDS - 1, \ + .sg_tablesize = AHCI_MAX_SG, \ + .dma_boundary = AHCI_DMA_BOUNDARY, \ + .shost_attrs = ahci_shost_attrs, \ + .sdev_attrs = ahci_sdev_attrs + extern struct ata_port_operations ahci_ops; void ahci_save_initial_config(struct device *dev, diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 4e97f33..84b6432 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -23,6 +23,10 @@ #include #include "ahci.h" +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT("ahci_platform"), +}; + static int __init ahci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -145,7 +149,7 @@ static int __init ahci_probe(struct platform_device *pdev) ahci_print_info(host, "platform"); rc = ata_host_activate(host, irq, ahci_interrupt, IRQF_SHARED, - &ahci_sht); + &ahci_platform_sht); if (rc) goto err0; diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 68dc678..8eea309 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -121,7 +121,7 @@ static DEVICE_ATTR(ahci_port_cmd, S_IRUGO, ahci_show_port_cmd, NULL); static DEVICE_ATTR(em_buffer, S_IWUSR | S_IRUGO, ahci_read_em_buffer, ahci_store_em_buffer); -static struct device_attribute *ahci_shost_attrs[] = { +struct device_attribute *ahci_shost_attrs[] = { &dev_attr_link_power_management_policy, &dev_attr_em_message_type, &dev_attr_em_message, @@ -132,22 +132,14 @@ static struct device_attribute *ahci_shost_attrs[] = { &dev_attr_em_buffer, NULL }; +EXPORT_SYMBOL_GPL(ahci_shost_attrs); -static struct device_attribute *ahci_sdev_attrs[] = { +struct device_attribute *ahci_sdev_attrs[] = { &dev_attr_sw_activity, &dev_attr_unload_heads, NULL }; - -struct scsi_host_template ahci_sht = { - ATA_NCQ_SHT("ahci"), - .can_queue = AHCI_MAX_CMDS - 1, - .sg_tablesize = AHCI_MAX_SG, - .dma_boundary = AHCI_DMA_BOUNDARY, - .shost_attrs = ahci_shost_attrs, - .sdev_attrs = ahci_sdev_attrs, -}; -EXPORT_SYMBOL_GPL(ahci_sht); +EXPORT_SYMBOL_GPL(ahci_sdev_attrs); struct ata_port_operations ahci_ops = { .inherits = &sata_pmp_port_ops, -- cgit v0.10.2 From 0f44fbd297e1cda5d9ecc9f5321a86fe647c7d4a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 28 Sep 2010 13:26:57 -0700 Subject: alpha: fix compile problem in arch/alpha/kernel/signal.c Tssk. Apparently Al hadn't checked commit c52c2ddc1dfa ("alpha: switch osf_sigprocmask() to use of sigprocmask()") at all. It doesn't compile. Fixed as per suggestions from Michael Cree. Reported-by: Michael Cree Cc: Al Viro Signed-off-by: Linus Torvalds diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index 779780a..d290845 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -49,10 +49,10 @@ SYSCALL_DEFINE2(osf_sigprocmask, int, how, unsigned long, newmask) unsigned long res; siginitset(&mask, newmask & ~_BLOCKABLE); - res = siprocmask(how, &mask, &oldmask); + res = sigprocmask(how, &mask, &oldmask); if (!res) { force_successful_syscall_return(); - res = oldmask->sig[0]; + res = oldmask.sig[0]; } return res; } -- cgit v0.10.2 From 62bdb288bf464862a2801b2e53aadc6c4d100fab Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 29 Sep 2010 01:57:02 +0100 Subject: MN10300: Handle missing sys_cacheflush() when caching disabled When caching is disabled on the MN10300 arch, the sys_cacheflush() function is removed by conditional stuff in the makefiles, but is still referred to by the syscall table. Provide a null version that just returns 0 when caching is disabled (or -EINVAL if the arguments are silly). Signed-off-by: David Howells Signed-off-by: Linus Torvalds diff --git a/arch/mn10300/mm/Makefile b/arch/mn10300/mm/Makefile index 28b9d98..1557277 100644 --- a/arch/mn10300/mm/Makefile +++ b/arch/mn10300/mm/Makefile @@ -2,13 +2,11 @@ # Makefile for the MN10300-specific memory management code # +cacheflush-y := cache.o cache-mn10300.o +cacheflush-$(CONFIG_MN10300_CACHE_WBACK) += cache-flush-mn10300.o + +cacheflush-$(CONFIG_MN10300_CACHE_DISABLED) := cache-disabled.o + obj-y := \ init.o fault.o pgtable.o extable.o tlb-mn10300.o mmu-context.o \ - misalignment.o dma-alloc.o - -ifneq ($(CONFIG_MN10300_CACHE_DISABLED),y) -obj-y += cache.o cache-mn10300.o -ifeq ($(CONFIG_MN10300_CACHE_WBACK),y) -obj-y += cache-flush-mn10300.o -endif -endif + misalignment.o dma-alloc.o $(cacheflush-y) diff --git a/arch/mn10300/mm/cache-disabled.c b/arch/mn10300/mm/cache-disabled.c new file mode 100644 index 0000000..f669ea4 --- /dev/null +++ b/arch/mn10300/mm/cache-disabled.c @@ -0,0 +1,21 @@ +/* Handle the cache being disabled + * + * Copyright (C) 2010 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ +#include + +/* + * allow userspace to flush the instruction cache + */ +asmlinkage long sys_cacheflush(unsigned long start, unsigned long end) +{ + if (end < start) + return -EINVAL; + return 0; +} -- cgit v0.10.2 From 899611ee7d373e5eeda08e9a8632684e1ebbbf00 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 28 Sep 2010 18:01:22 -0700 Subject: Linux 2.6.36-rc6 diff --git a/Makefile b/Makefile index 3133a57..471c49f 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 36 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Sheep on Meth # *DOCUMENTATION* -- cgit v0.10.2 From 35ed16740c564ff092fe45804dfbbb1449f2bd7e Mon Sep 17 00:00:00 2001 From: Rahul Ruikar Date: Fri, 1 Oct 2010 13:32:45 -0700 Subject: [IA64] ioc3_serial: release resources in error return path In ioc3uart_probe() resources were not released during error return path - ports[phys_port] Signed-off-by: Rahul Ruikar Signed-off-by: Tony Luck diff --git a/drivers/serial/ioc3_serial.c b/drivers/serial/ioc3_serial.c index 93de907..08d77b0 100644 --- a/drivers/serial/ioc3_serial.c +++ b/drivers/serial/ioc3_serial.c @@ -2017,6 +2017,7 @@ ioc3uart_probe(struct ioc3_submodule *is, struct ioc3_driver_data *idd) struct ioc3_port *port; struct ioc3_port *ports[PORTS_PER_CARD]; int phys_port; + int cnt; DPRINT_CONFIG(("%s (0x%p, 0x%p)\n", __func__, is, idd)); @@ -2146,6 +2147,9 @@ ioc3uart_probe(struct ioc3_submodule *is, struct ioc3_driver_data *idd) /* error exits that give back resources */ out4: + for (cnt = 0; cnt < phys_port; cnt++) + kfree(ports[cnt]); + kfree(card_ptr); return ret; } -- cgit v0.10.2 From e33621a2e3f2b7b73259f6740776b3983ec5bab9 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Fri, 1 Oct 2010 14:15:27 -0700 Subject: [IA64] enable ARCH_DMA_ADDR_T_64BIT Signed-off-by: FUJITA Tomonori Signed-off-by: Andrew Morton Signed-off-by: Tony Luck diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index ba22849..5d5e32e 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -53,6 +53,9 @@ config MMU bool default y +config ARCH_DMA_ADDR_T_64BIT + def_bool y + config NEED_DMA_MAP_STATE def_bool y -- cgit v0.10.2 From 4de0a7594823d04361281e34e59f2c1108899f3e Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 5 Oct 2010 15:41:25 -0700 Subject: [IA64] Initialize interrupts later (from init_IRQ()) Thomas Gleixner is cleaning up the generic irq code, and ia64 ran into problems because it calls register_intr() before early_irq_init() is called. Move the call to acpi_boot_init() from setup_arch() to init_IRQ(). As a bonus - moving the call later means we no longer need the hacks in iosapic.c to switch between the bootmem and regular allocator - we can just used kzalloc() for allocation. Signed-off-by: Tony Luck diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index 7ded766..66ec078 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -108,10 +108,6 @@ #define DBG(fmt...) #endif -#define NR_PREALLOCATE_RTE_ENTRIES \ - (PAGE_SIZE / sizeof(struct iosapic_rte_info)) -#define RTE_PREALLOCATED (1) - static DEFINE_SPINLOCK(iosapic_lock); /* @@ -136,7 +132,6 @@ struct iosapic_rte_info { struct list_head rte_list; /* RTEs sharing the same vector */ char rte_index; /* IOSAPIC RTE index */ int refcnt; /* reference counter */ - unsigned int flags; /* flags */ struct iosapic *iosapic; } ____cacheline_aligned; @@ -155,9 +150,6 @@ static struct iosapic_intr_info { static unsigned char pcat_compat __devinitdata; /* 8259 compatibility flag */ -static int iosapic_kmalloc_ok; -static LIST_HEAD(free_rte_list); - static inline void iosapic_write(struct iosapic *iosapic, unsigned int reg, u32 val) { @@ -552,37 +544,6 @@ iosapic_reassign_vector (int irq) } } -static struct iosapic_rte_info * __init_refok iosapic_alloc_rte (void) -{ - int i; - struct iosapic_rte_info *rte; - int preallocated = 0; - - if (!iosapic_kmalloc_ok && list_empty(&free_rte_list)) { - rte = alloc_bootmem(sizeof(struct iosapic_rte_info) * - NR_PREALLOCATE_RTE_ENTRIES); - for (i = 0; i < NR_PREALLOCATE_RTE_ENTRIES; i++, rte++) - list_add(&rte->rte_list, &free_rte_list); - } - - if (!list_empty(&free_rte_list)) { - rte = list_entry(free_rte_list.next, struct iosapic_rte_info, - rte_list); - list_del(&rte->rte_list); - preallocated++; - } else { - rte = kmalloc(sizeof(struct iosapic_rte_info), GFP_ATOMIC); - if (!rte) - return NULL; - } - - memset(rte, 0, sizeof(struct iosapic_rte_info)); - if (preallocated) - rte->flags |= RTE_PREALLOCATED; - - return rte; -} - static inline int irq_is_shared (int irq) { return (iosapic_intr_info[irq].count > 1); @@ -615,7 +576,7 @@ register_intr (unsigned int gsi, int irq, unsigned char delivery, rte = find_rte(irq, gsi); if (!rte) { - rte = iosapic_alloc_rte(); + rte = kzalloc(sizeof (*rte), GFP_ATOMIC); if (!rte) { printk(KERN_WARNING "%s: cannot allocate memory\n", __func__); @@ -1161,10 +1122,3 @@ map_iosapic_to_node(unsigned int gsi_base, int node) return; } #endif - -static int __init iosapic_enable_kmalloc (void) -{ - iosapic_kmalloc_ok = 1; - return 0; -} -core_initcall (iosapic_enable_kmalloc); diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c index f14c35f..07d4f94 100644 --- a/arch/ia64/kernel/irq_ia64.c +++ b/arch/ia64/kernel/irq_ia64.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -650,6 +651,9 @@ ia64_native_register_ipi(void) void __init init_IRQ (void) { +#ifdef CONFIG_ACPI + acpi_boot_init(); +#endif ia64_register_ipi(); register_percpu_irq(IA64_SPURIOUS_INT_VECTOR, NULL); #ifdef CONFIG_SMP diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 8fb958a..911cf97 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -594,10 +594,6 @@ setup_arch (char **cmdline_p) cpu_init(); /* initialize the bootstrap CPU */ mmu_context_init(); /* initialize context_id bitmap */ -#ifdef CONFIG_ACPI - acpi_boot_init(); -#endif - paravirt_banner(); paravirt_arch_setup_console(cmdline_p); -- cgit v0.10.2 From c75f2aa13f5b268aba369b5dc566088b5194377c Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Thu, 7 Oct 2010 16:23:34 -0700 Subject: [IA64] Cannot use register_percpu_irq() from ia64_mca_init() This is called before early_irq_init() which will clobber any registrations made too early. Move the calls to ia64_mca_late_init(). Signed-off-by: Tony Luck diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index a0220dc..1753f6a 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -2055,25 +2055,6 @@ ia64_mca_init(void) IA64_MCA_DEBUG("%s: registered OS INIT handler with SAL\n", __func__); - /* - * Configure the CMCI/P vector and handler. Interrupts for CMC are - * per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c). - */ - register_percpu_irq(IA64_CMC_VECTOR, &cmci_irqaction); - register_percpu_irq(IA64_CMCP_VECTOR, &cmcp_irqaction); - ia64_mca_cmc_vector_setup(); /* Setup vector on BSP */ - - /* Setup the MCA rendezvous interrupt vector */ - register_percpu_irq(IA64_MCA_RENDEZ_VECTOR, &mca_rdzv_irqaction); - - /* Setup the MCA wakeup interrupt vector */ - register_percpu_irq(IA64_MCA_WAKEUP_VECTOR, &mca_wkup_irqaction); - -#ifdef CONFIG_ACPI - /* Setup the CPEI/P handler */ - register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction); -#endif - /* Initialize the areas set aside by the OS to buffer the * platform/processor error states for MCA/INIT/CMC * handling. @@ -2103,6 +2084,25 @@ ia64_mca_late_init(void) if (!mca_init) return 0; + /* + * Configure the CMCI/P vector and handler. Interrupts for CMC are + * per-processor, so AP CMC interrupts are setup in smp_callin() (smpboot.c). + */ + register_percpu_irq(IA64_CMC_VECTOR, &cmci_irqaction); + register_percpu_irq(IA64_CMCP_VECTOR, &cmcp_irqaction); + ia64_mca_cmc_vector_setup(); /* Setup vector on BSP */ + + /* Setup the MCA rendezvous interrupt vector */ + register_percpu_irq(IA64_MCA_RENDEZ_VECTOR, &mca_rdzv_irqaction); + + /* Setup the MCA wakeup interrupt vector */ + register_percpu_irq(IA64_MCA_WAKEUP_VECTOR, &mca_wkup_irqaction); + +#ifdef CONFIG_ACPI + /* Setup the CPEI/P handler */ + register_percpu_irq(IA64_CPEP_VECTOR, &mca_cpep_irqaction); +#endif + register_hotcpu_notifier(&mca_cpu_notifier); /* Setup the CMCI/P vector and handler */ -- cgit v0.10.2