From 6ada1fc0e1c4775de0e043e1bd3ae9d065491aa5 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 3 Dec 2014 19:22:48 -0500 Subject: time: settimeofday: Validate the values of tv from user An unvalidated user input is multiplied by a constant, which can result in an undefined behaviour for large values. While this is validated later, we should avoid triggering undefined behaviour. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: stable Signed-off-by: Sasha Levin [jstultz: include trivial milisecond->microsecond correction noticed by Andy] Signed-off-by: John Stultz --- include/linux/time.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 8c42cf8d2444..5989b0ead1ec 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -99,6 +99,19 @@ static inline bool timespec_valid_strict(const struct timespec *ts) return true; } +static inline bool timeval_valid(const struct timeval *tv) +{ + /* Dates before 1970 are bogus */ + if (tv->tv_sec < 0) + return false; + + /* Can't have more microseconds then a second */ + if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC) + return false; + + return true; +} + extern struct timespec timespec_trunc(struct timespec t, unsigned gran); #define CURRENT_TIME (current_kernel_time()) -- cgit v1.2.3 From ad26aa6c60974acf3228ed0ade97ba5793093dbe Mon Sep 17 00:00:00 2001 From: Jonghwa Lee Date: Thu, 8 Jan 2015 11:04:07 +0900 Subject: regulator: s2mps11: Fix wrong calculation of register offset This patch adds missing registers('BUCK7_SW' & 'LDO29_CTRL'). Since BUCK7 has 1 more register (BUCK7_SW) than others, register offset should be added one more for which has bigger address than BUCK7 registers. Fixes: 76b9840b24ae04(regulator: s2mps11: Add support S2MPS13 regulator device) Signed-off-by: Jonghwa Lee Signed-off-by: Chanwoo Choi Signed-off-by: Mark Brown Cc: --- drivers/regulator/s2mps11.c | 42 +++++++++++++++++++++++++++++++++---- include/linux/mfd/samsung/s2mps13.h | 2 ++ 2 files changed, 40 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c index c1444c3d84c2..13ca20ed33a6 100644 --- a/drivers/regulator/s2mps11.c +++ b/drivers/regulator/s2mps11.c @@ -405,6 +405,40 @@ static struct regulator_ops s2mps14_reg_ops; .enable_mask = S2MPS14_ENABLE_MASK \ } +#define regulator_desc_s2mps13_buck7(num, min, step, min_sel) { \ + .name = "BUCK"#num, \ + .id = S2MPS13_BUCK##num, \ + .ops = &s2mps14_reg_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = min, \ + .uV_step = step, \ + .linear_min_sel = min_sel, \ + .n_voltages = S2MPS14_BUCK_N_VOLTAGES, \ + .ramp_delay = S2MPS13_BUCK_RAMP_DELAY, \ + .vsel_reg = S2MPS13_REG_B1OUT + (num) * 2 - 1, \ + .vsel_mask = S2MPS14_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS13_REG_B1CTRL + (num - 1) * 2, \ + .enable_mask = S2MPS14_ENABLE_MASK \ +} + +#define regulator_desc_s2mps13_buck8_10(num, min, step, min_sel) { \ + .name = "BUCK"#num, \ + .id = S2MPS13_BUCK##num, \ + .ops = &s2mps14_reg_ops, \ + .type = REGULATOR_VOLTAGE, \ + .owner = THIS_MODULE, \ + .min_uV = min, \ + .uV_step = step, \ + .linear_min_sel = min_sel, \ + .n_voltages = S2MPS14_BUCK_N_VOLTAGES, \ + .ramp_delay = S2MPS13_BUCK_RAMP_DELAY, \ + .vsel_reg = S2MPS13_REG_B1OUT + (num) * 2 - 1, \ + .vsel_mask = S2MPS14_BUCK_VSEL_MASK, \ + .enable_reg = S2MPS13_REG_B1CTRL + (num) * 2 - 1, \ + .enable_mask = S2MPS14_ENABLE_MASK \ +} + static const struct regulator_desc s2mps13_regulators[] = { regulator_desc_s2mps13_ldo(1, MIN_800_MV, STEP_12_5_MV, 0x00), regulator_desc_s2mps13_ldo(2, MIN_1400_MV, STEP_50_MV, 0x0C), @@ -452,10 +486,10 @@ static const struct regulator_desc s2mps13_regulators[] = { regulator_desc_s2mps13_buck(4, MIN_500_MV, STEP_6_25_MV, 0x10), regulator_desc_s2mps13_buck(5, MIN_500_MV, STEP_6_25_MV, 0x10), regulator_desc_s2mps13_buck(6, MIN_500_MV, STEP_6_25_MV, 0x10), - regulator_desc_s2mps13_buck(7, MIN_500_MV, STEP_6_25_MV, 0x10), - regulator_desc_s2mps13_buck(8, MIN_1000_MV, STEP_12_5_MV, 0x20), - regulator_desc_s2mps13_buck(9, MIN_1000_MV, STEP_12_5_MV, 0x20), - regulator_desc_s2mps13_buck(10, MIN_500_MV, STEP_6_25_MV, 0x10), + regulator_desc_s2mps13_buck7(7, MIN_500_MV, STEP_6_25_MV, 0x10), + regulator_desc_s2mps13_buck8_10(8, MIN_1000_MV, STEP_12_5_MV, 0x20), + regulator_desc_s2mps13_buck8_10(9, MIN_1000_MV, STEP_12_5_MV, 0x20), + regulator_desc_s2mps13_buck8_10(10, MIN_500_MV, STEP_6_25_MV, 0x10), }; static int s2mps14_regulator_enable(struct regulator_dev *rdev) diff --git a/include/linux/mfd/samsung/s2mps13.h b/include/linux/mfd/samsung/s2mps13.h index ce5dda8958fe..b1fd675fa36f 100644 --- a/include/linux/mfd/samsung/s2mps13.h +++ b/include/linux/mfd/samsung/s2mps13.h @@ -59,6 +59,7 @@ enum s2mps13_reg { S2MPS13_REG_B6CTRL, S2MPS13_REG_B6OUT, S2MPS13_REG_B7CTRL, + S2MPS13_REG_B7SW, S2MPS13_REG_B7OUT, S2MPS13_REG_B8CTRL, S2MPS13_REG_B8OUT, @@ -102,6 +103,7 @@ enum s2mps13_reg { S2MPS13_REG_L26CTRL, S2MPS13_REG_L27CTRL, S2MPS13_REG_L28CTRL, + S2MPS13_REG_L29CTRL, S2MPS13_REG_L30CTRL, S2MPS13_REG_L31CTRL, S2MPS13_REG_L32CTRL, -- cgit v1.2.3 From f331a859e0ee5a898c1f47596eddad4c4f02d657 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 15 Jan 2015 18:16:04 -0600 Subject: PCI: Add flag for devices where we can't use bus reset Enable a mechanism for devices to quirk that they do not behave when doing a PCI bus reset. We require a modest level of spec compliant behavior in order to do a reset, for instance the device should come out of reset without throwing errors and PCI config space should be accessible after reset. This is too much to ask for some devices. Link: http://lkml.kernel.org/r/20140923210318.498dacbd@dualc.maya.org Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v3.14+ --- drivers/pci/pci.c | 40 ++++++++++++++++++++++++++++++++++++---- include/linux/pci.h | 2 ++ 2 files changed, 38 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index cab05f31223f..e9d4fd861ba1 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3271,7 +3271,8 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { struct pci_dev *pdev; - if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self) + if (pci_is_root_bus(dev->bus) || dev->subordinate || + !dev->bus->self || dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) @@ -3305,7 +3306,8 @@ static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe) { struct pci_dev *pdev; - if (dev->subordinate || !dev->slot) + if (dev->subordinate || !dev->slot || + dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET) return -ENOTTY; list_for_each_entry(pdev, &dev->bus->devices, bus_list) @@ -3557,6 +3559,20 @@ int pci_try_reset_function(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_try_reset_function); +/* Do any devices on or below this bus prevent a bus reset? */ +static bool pci_bus_resetable(struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || + (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + return false; + } + + return true; +} + /* Lock devices from the top of the tree down */ static void pci_bus_lock(struct pci_bus *bus) { @@ -3607,6 +3623,22 @@ unlock: return 0; } +/* Do any devices on or below this slot prevent a bus reset? */ +static bool pci_slot_resetable(struct pci_slot *slot) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &slot->bus->devices, bus_list) { + if (!dev->slot || dev->slot != slot) + continue; + if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || + (dev->subordinate && !pci_bus_resetable(dev->subordinate))) + return false; + } + + return true; +} + /* Lock devices from the top of the tree down */ static void pci_slot_lock(struct pci_slot *slot) { @@ -3728,7 +3760,7 @@ static int pci_slot_reset(struct pci_slot *slot, int probe) { int rc; - if (!slot) + if (!slot || !pci_slot_resetable(slot)) return -ENOTTY; if (!probe) @@ -3820,7 +3852,7 @@ EXPORT_SYMBOL_GPL(pci_try_reset_slot); static int pci_bus_reset(struct pci_bus *bus, int probe) { - if (!bus->self) + if (!bus->self || !pci_bus_resetable(bus)) return -ENOTTY; if (probe) diff --git a/include/linux/pci.h b/include/linux/pci.h index 360a966a97a5..44627f1df4ca 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -175,6 +175,8 @@ enum pci_dev_flags { PCI_DEV_FLAGS_DMA_ALIAS_DEVFN = (__force pci_dev_flags_t) (1 << 4), /* Use a PCIe-to-PCI bridge alias even if !pci_is_pcie */ PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5), + /* Do not use bus resets for device */ + PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6), }; enum pci_irq_reroute_variant { -- cgit v1.2.3 From 8505e729a2f6eb0803ff943a15f133dd10afff3a Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 15 Jan 2015 16:21:49 -0600 Subject: PCI: Add pci_claim_bridge_resource() to clip window if necessary Add pci_claim_bridge_resource() to claim a PCI-PCI bridge window. This is like regular pci_claim_resource(), except that if we fail to claim the window, we check to see if we can reduce the size of the window and try again. This is for scenarios like this: pci_bus 0000:00: root bus resource [mem 0xc0000000-0xffffffff] pci 0000:00:01.0: bridge window [mem 0xbdf00000-0xddefffff 64bit pref] pci 0000:01:00.0: reg 0x10: [mem 0xc0000000-0xcfffffff pref] The 00:01.0 window is illegal: it starts before the host bridge window, so we have to assume the [0xbdf00000-0xbfffffff] region is inaccessible. We can make it legal by clipping it to [mem 0xc0000000-0xddefffff 64bit pref]. Previously we discarded the 00:01.0 window and tried to reassign that part of the hierarchy from scratch. That is a problem because Linux doesn't always assign things optimally. For example, in this case, BIOS put the 01:00.0 device in a prefetchable window below 4GB, but after 5b28541552ef, Linux puts the prefetchable window above 4GB where the 32-bit 01:00.0 device can't use it. Clipping the 00:01.0 window is less intrusive than completely reassigning things and is sufficient to let us use most of the BIOS configuration. Of course, it's possible that devices below 00:01.0 will no longer fit. If that's the case, we'll have to reassign things. But that's a separate problem. [bhelgaas: changelog, split into separate patch] Link: https://bugzilla.kernel.org/show_bug.cgi?id=85491 Reported-by: Marek Kordik Fixes: 5b28541552ef ("PCI: Restrict 64-bit prefetchable bridge windows to 64-bit resources") Signed-off-by: Yinghai Lu Signed-off-by: Bjorn Helgaas CC: stable@vger.kernel.org # v3.16+ --- drivers/pci/setup-bus.c | 35 +++++++++++++++++++++++++++++++++++ include/linux/pci.h | 1 + 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 802f56be2149..e3e17f3c0f0f 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -646,6 +646,41 @@ void pci_setup_bridge(struct pci_bus *bus) __pci_setup_bridge(bus, type); } + +int pci_claim_bridge_resource(struct pci_dev *bridge, int i) +{ + if (i < PCI_BRIDGE_RESOURCES || i > PCI_BRIDGE_RESOURCE_END) + return 0; + + if (pci_claim_resource(bridge, i) == 0) + return 0; /* claimed the window */ + + if ((bridge->class >> 8) != PCI_CLASS_BRIDGE_PCI) + return 0; + + if (!pci_bus_clip_resource(bridge, i)) + return -EINVAL; /* clipping didn't change anything */ + + switch (i - PCI_BRIDGE_RESOURCES) { + case 0: + pci_setup_bridge_io(bridge); + break; + case 1: + pci_setup_bridge_mmio(bridge); + break; + case 2: + pci_setup_bridge_mmio_pref(bridge); + break; + default: + return -EINVAL; + } + + if (pci_claim_resource(bridge, i) == 0) + return 0; /* claimed a smaller window */ + + return -EINVAL; +} + /* Check whether the bridge supports optional I/O and prefetchable memory ranges. If not, the respective base/limit registers must be read-only and read as 0. */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 44627f1df4ca..9603094ed59b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1067,6 +1067,7 @@ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx); void pci_bus_assign_resources(const struct pci_bus *bus); void pci_bus_size_bridges(struct pci_bus *bus); int pci_claim_resource(struct pci_dev *, int); +int pci_claim_bridge_resource(struct pci_dev *bridge, int i); void pci_assign_unassigned_resources(void); void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge); void pci_assign_unassigned_bus_resources(struct pci_bus *bus); -- cgit v1.2.3 From d453cded05ee219b77815ea194dc36efa5398bca Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 20 Jan 2015 09:07:04 +1030 Subject: module_arch_freeing_init(): new hook for archs before module->module_init freed. Archs have been abusing module_free() to clean up their arch-specific allocations. Since module_free() is also (ab)used by BPF and trace code, let's keep it to simple allocations, and provide a hook called before that. This means that avr32, ia64, parisc and s390 no longer need to implement their own module_free() at all. avr32 doesn't need module_finalize() either. Signed-off-by: Rusty Russell Cc: Chris Metcalf Cc: Haavard Skinnemoen Cc: Hans-Christian Egtvedt Cc: Tony Luck Cc: Fenghua Yu Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: linux-kernel@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linux-s390@vger.kernel.org --- arch/avr32/kernel/module.c | 13 +------------ arch/ia64/kernel/module.c | 6 ++---- arch/parisc/kernel/module.c | 6 +----- arch/s390/kernel/module.c | 10 +++------- arch/tile/kernel/module.c | 2 +- include/linux/moduleloader.h | 2 ++ kernel/module.c | 7 +++++++ 7 files changed, 17 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 2c9412908024..164efa009e5b 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -19,12 +19,10 @@ #include #include -void module_free(struct module *mod, void *module_region) +void module_arch_freeing_init(struct module *mod) { vfree(mod->arch.syminfo); mod->arch.syminfo = NULL; - - vfree(module_region); } static inline int check_rela(Elf32_Rela *rela, struct module *module, @@ -291,12 +289,3 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, return ret; } - -int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, - struct module *module) -{ - vfree(module->arch.syminfo); - module->arch.syminfo = NULL; - - return 0; -} diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 24603be24c14..29754aae5177 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -305,14 +305,12 @@ plt_target (struct plt_entry *plt) #endif /* !USE_BRL */ void -module_free (struct module *mod, void *module_region) +module_arch_freeing_init (struct module *mod) { - if (mod && mod->arch.init_unw_table && - module_region == mod->module_init) { + if (mod->arch.init_unw_table) { unw_remove_unwind_table(mod->arch.init_unw_table); mod->arch.init_unw_table = NULL; } - vfree(module_region); } /* Have we already seen one of these relocations? */ diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 50dfafc3f2c1..5822e8e200e6 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -298,14 +298,10 @@ static inline unsigned long count_stubs(const Elf_Rela *rela, unsigned long n) } #endif - -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_arch_freeing_init(struct module *mod) { kfree(mod->arch.section); mod->arch.section = NULL; - - vfree(module_region); } /* Additional bytes needed in front of individual sections */ diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index b89b59158b95..409d152585be 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -55,14 +55,10 @@ void *module_alloc(unsigned long size) } #endif -/* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_arch_freeing_init(struct module *mod) { - if (mod) { - vfree(mod->arch.syminfo); - mod->arch.syminfo = NULL; - } - vfree(module_region); + vfree(mod->arch.syminfo); + mod->arch.syminfo = NULL; } static void check_rela(Elf_Rela *rela, struct module *me) diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c index 96447c9160a0..62a597e810d6 100644 --- a/arch/tile/kernel/module.c +++ b/arch/tile/kernel/module.c @@ -83,7 +83,7 @@ void module_free(struct module *mod, void *module_region) 0, 0, 0, NULL, NULL, 0); /* - * FIXME: If module_region == mod->module_init, trim exception + * FIXME: Add module_arch_freeing_init to trim exception * table entries. */ } diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 7eeb9bbfb816..054eac853090 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -82,4 +82,6 @@ int module_finalize(const Elf_Ehdr *hdr, /* Any cleanup needed when module leaves. */ void module_arch_cleanup(struct module *mod); +/* Any cleanup before freeing mod->module_init */ +void module_arch_freeing_init(struct module *mod); #endif diff --git a/kernel/module.c b/kernel/module.c index 3965511ae133..68be0b1f9e7f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1804,6 +1804,10 @@ void __weak module_arch_cleanup(struct module *mod) { } +void __weak module_arch_freeing_init(struct module *mod) +{ +} + /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { @@ -1841,6 +1845,7 @@ static void free_module(struct module *mod) /* This may be NULL, but that's OK */ unset_module_init_ro_nx(mod); + module_arch_freeing_init(mod); module_free(mod, mod->module_init); kfree(mod->args); percpu_modfree(mod); @@ -2930,6 +2935,7 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); + module_arch_freeing_init(mod); module_free(mod, mod->module_init); module_free(mod, mod->module_core); } @@ -3055,6 +3061,7 @@ static int do_init_module(struct module *mod) mod->strtab = mod->core_strtab; #endif unset_module_init_ro_nx(mod); + module_arch_freeing_init(mod); module_free(mod, mod->module_init); mod->module_init = NULL; mod->init_size = 0; -- cgit v1.2.3 From be1f221c0445a4157d177197c236f888d3581914 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 20 Jan 2015 09:07:05 +1030 Subject: module: remove mod arg from module_free, rename module_memfree(). Nothing needs the module pointer any more, and the next patch will call it from RCU, where the module itself might no longer exist. Removing the arg is the safest approach. This just codifies the use of the module_alloc/module_free pattern which ftrace and bpf use. Signed-off-by: Rusty Russell Acked-by: Alexei Starovoitov Cc: Mikael Starvik Cc: Jesper Nilsson Cc: Ralf Baechle Cc: Ley Foon Tan Cc: Benjamin Herrenschmidt Cc: Chris Metcalf Cc: Steven Rostedt Cc: x86@kernel.org Cc: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: Masami Hiramatsu Cc: linux-cris-kernel@axis.com Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: nios2-dev@lists.rocketboards.org Cc: linuxppc-dev@lists.ozlabs.org Cc: sparclinux@vger.kernel.org Cc: netdev@vger.kernel.org --- arch/cris/kernel/module.c | 2 +- arch/mips/net/bpf_jit.c | 2 +- arch/nios2/kernel/module.c | 2 +- arch/powerpc/net/bpf_jit_comp.c | 2 +- arch/sparc/net/bpf_jit_comp.c | 4 ++-- arch/tile/kernel/module.c | 2 +- arch/x86/kernel/ftrace.c | 2 +- include/linux/moduleloader.h | 2 +- kernel/bpf/core.c | 2 +- kernel/kprobes.c | 2 +- kernel/module.c | 14 +++++++------- 11 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/arch/cris/kernel/module.c b/arch/cris/kernel/module.c index 51123f985eb5..af04cb6b6dc9 100644 --- a/arch/cris/kernel/module.c +++ b/arch/cris/kernel/module.c @@ -36,7 +36,7 @@ void *module_alloc(unsigned long size) } /* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_memfree(void *module_region) { kfree(module_region); } diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 9fd6834a2172..5d6139390bf8 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -1388,7 +1388,7 @@ out: void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) - module_free(NULL, fp->bpf_func); + module_memfree(fp->bpf_func); bpf_prog_unlock_free(fp); } diff --git a/arch/nios2/kernel/module.c b/arch/nios2/kernel/module.c index cc924a38f22a..e2e3f13f98d5 100644 --- a/arch/nios2/kernel/module.c +++ b/arch/nios2/kernel/module.c @@ -36,7 +36,7 @@ void *module_alloc(unsigned long size) } /* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_memfree(void *module_region) { kfree(module_region); } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 1ca125b9c226..d1916b577f2c 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -699,7 +699,7 @@ out: void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) - module_free(NULL, fp->bpf_func); + module_memfree(fp->bpf_func); bpf_prog_unlock_free(fp); } diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index f33e7c7a3bf7..7931eeeb649a 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -776,7 +776,7 @@ cond_branch: f_offset = addrs[i + filter[i].jf]; if (unlikely(proglen + ilen > oldproglen)) { pr_err("bpb_jit_compile fatal error\n"); kfree(addrs); - module_free(NULL, image); + module_memfree(image); return; } memcpy(image + proglen, temp, ilen); @@ -822,7 +822,7 @@ out: void bpf_jit_free(struct bpf_prog *fp) { if (fp->jited) - module_free(NULL, fp->bpf_func); + module_memfree(fp->bpf_func); bpf_prog_unlock_free(fp); } diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c index 62a597e810d6..2305084c9b93 100644 --- a/arch/tile/kernel/module.c +++ b/arch/tile/kernel/module.c @@ -74,7 +74,7 @@ error: /* Free memory returned from module_alloc */ -void module_free(struct module *mod, void *module_region) +void module_memfree(void *module_region) { vfree(module_region); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 2142376dc8c6..8b7b0a51e742 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -674,7 +674,7 @@ static inline void *alloc_tramp(unsigned long size) } static inline void tramp_free(void *tramp) { - module_free(NULL, tramp); + module_memfree(tramp); } #else /* Trampolines can only be created if modules are supported */ diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 054eac853090..f7556261fe3c 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -26,7 +26,7 @@ unsigned int arch_mod_section_prepend(struct module *mod, unsigned int section); void *module_alloc(unsigned long size); /* Free memory returned from module_alloc. */ -void module_free(struct module *mod, void *module_region); +void module_memfree(void *module_region); /* * Apply the given relocation to the (simplified) ELF. Return -error diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d6594e457a25..a64e7a207d2b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -163,7 +163,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, void bpf_jit_binary_free(struct bpf_binary_header *hdr) { - module_free(NULL, hdr); + module_memfree(hdr); } #endif /* CONFIG_BPF_JIT */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 06f58309fed2..ee619929cf90 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -127,7 +127,7 @@ static void *alloc_insn_page(void) static void free_insn_page(void *page) { - module_free(NULL, page); + module_memfree(page); } struct kprobe_insn_cache kprobe_insn_slots = { diff --git a/kernel/module.c b/kernel/module.c index 68be0b1f9e7f..1f85fd5c89d3 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1795,7 +1795,7 @@ static void unset_module_core_ro_nx(struct module *mod) { } static void unset_module_init_ro_nx(struct module *mod) { } #endif -void __weak module_free(struct module *mod, void *module_region) +void __weak module_memfree(void *module_region) { vfree(module_region); } @@ -1846,7 +1846,7 @@ static void free_module(struct module *mod) /* This may be NULL, but that's OK */ unset_module_init_ro_nx(mod); module_arch_freeing_init(mod); - module_free(mod, mod->module_init); + module_memfree(mod->module_init); kfree(mod->args); percpu_modfree(mod); @@ -1855,7 +1855,7 @@ static void free_module(struct module *mod) /* Finally, free the core (containing the module structure) */ unset_module_core_ro_nx(mod); - module_free(mod, mod->module_core); + module_memfree(mod->module_core); #ifdef CONFIG_MPU update_protections(current->mm); @@ -2790,7 +2790,7 @@ static int move_module(struct module *mod, struct load_info *info) */ kmemleak_ignore(ptr); if (!ptr) { - module_free(mod, mod->module_core); + module_memfree(mod->module_core); return -ENOMEM; } memset(ptr, 0, mod->init_size); @@ -2936,8 +2936,8 @@ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); - module_free(mod, mod->module_init); - module_free(mod, mod->module_core); + module_memfree(mod->module_init); + module_memfree(mod->module_core); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -3062,7 +3062,7 @@ static int do_init_module(struct module *mod) #endif unset_module_init_ro_nx(mod); module_arch_freeing_init(mod); - module_free(mod, mod->module_init); + module_memfree(mod->module_init); mod->module_init = NULL; mod->init_size = 0; mod->init_ro_size = 0; -- cgit v1.2.3 From d5db139ab3764640e0882a1746e7b9fdee33fd87 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 22 Jan 2015 11:13:14 +1030 Subject: module: make module_refcount() a signed integer. James Bottomley points out that it will be -1 during unload. It's only used for diagnostics, so let's not hide that as it could be a clue as to what's gone wrong. Cc: Jason Wessel Acked-and-documention-added-by: James Bottomley Reviewed-by: Masami Hiramatsu Signed-off-by: Rusty Russell --- include/linux/module.h | 2 +- kernel/debug/kdb/kdb_main.c | 2 +- kernel/module.c | 17 +++++++++++++---- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index ebfb0e153c6a..b653d7c0a05a 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -444,7 +444,7 @@ extern void __module_put_and_exit(struct module *mod, long code) #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD -unsigned long module_refcount(struct module *mod); +int module_refcount(struct module *mod); void __symbol_put(const char *symbol); #define symbol_put(x) __symbol_put(VMLINUX_SYMBOL_STR(x)) void symbol_put_addr(void *addr); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 379650b984f8..2934889f2cce 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1979,7 +1979,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf("%-20s%8u 0x%p ", mod->name, mod->core_size, (void *)mod); #ifdef CONFIG_MODULE_UNLOAD - kdb_printf("%4ld ", module_refcount(mod)); + kdb_printf("%4d ", module_refcount(mod)); #endif if (mod->state == MODULE_STATE_GOING) kdb_printf(" (Unloading)"); diff --git a/kernel/module.c b/kernel/module.c index ed4ec9c30bd2..d856e96a3cce 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -772,9 +772,18 @@ static int try_stop_module(struct module *mod, int flags, int *forced) return 0; } -unsigned long module_refcount(struct module *mod) +/** + * module_refcount - return the refcount or -1 if unloading + * + * @mod: the module we're checking + * + * Returns: + * -1 if the module is in the process of unloading + * otherwise the number of references in the kernel to the module + */ +int module_refcount(struct module *mod) { - return (unsigned long)atomic_read(&mod->refcnt) - MODULE_REF_BASE; + return atomic_read(&mod->refcnt) - MODULE_REF_BASE; } EXPORT_SYMBOL(module_refcount); @@ -856,7 +865,7 @@ static inline void print_unload_info(struct seq_file *m, struct module *mod) struct module_use *use; int printed_something = 0; - seq_printf(m, " %lu ", module_refcount(mod)); + seq_printf(m, " %i ", module_refcount(mod)); /* * Always include a trailing , so userspace can differentiate @@ -908,7 +917,7 @@ EXPORT_SYMBOL_GPL(symbol_put_addr); static ssize_t show_refcnt(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%lu\n", module_refcount(mk->mod)); + return sprintf(buffer, "%i\n", module_refcount(mk->mod)); } static struct module_attribute modinfo_refcnt = -- cgit v1.2.3 From 9879de7373fcfb466ec198293b6ccc1ad7a42dd8 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 26 Jan 2015 12:58:32 -0800 Subject: mm: page_alloc: embed OOM killing naturally into allocation slowpath The OOM killing invocation does a lot of duplicative checks against the task's allocation context. Rework it to take advantage of the existing checks in the allocator slowpath. The OOM killer is invoked when the allocator is unable to reclaim any pages but the allocation has to keep looping. Instead of having a check for __GFP_NORETRY hidden in oom_gfp_allowed(), just move the OOM invocation to the true branch of should_alloc_retry(). The __GFP_FS check from oom_gfp_allowed() can then be moved into the OOM avoidance branch in __alloc_pages_may_oom(), along with the PF_DUMPCORE test. __alloc_pages_may_oom() can then signal to the caller whether the OOM killer was invoked, instead of requiring it to duplicate the order and high_zoneidx checks to guess this when deciding whether to continue. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 5 ---- mm/page_alloc.c | 82 +++++++++++++++++++++++------------------------------ 2 files changed, 35 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 853698c721f7..76200984d1e2 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -85,11 +85,6 @@ static inline void oom_killer_enable(void) oom_killer_disabled = false; } -static inline bool oom_gfp_allowed(gfp_t gfp_mask) -{ - return (gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY); -} - extern struct task_struct *find_lock_task_mm(struct task_struct *p); static inline bool task_will_free_mem(struct task_struct *task) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7633c503a116..8e20f9c2fa5a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2332,12 +2332,21 @@ static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int classzone_idx, int migratetype) + int classzone_idx, int migratetype, unsigned long *did_some_progress) { struct page *page; - /* Acquire the per-zone oom lock for each zone */ + *did_some_progress = 0; + + if (oom_killer_disabled) + return NULL; + + /* + * Acquire the per-zone oom lock for each zone. If that + * fails, somebody else is making progress for us. + */ if (!oom_zonelist_trylock(zonelist, gfp_mask)) { + *did_some_progress = 1; schedule_timeout_uninterruptible(1); return NULL; } @@ -2363,12 +2372,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; if (!(gfp_mask & __GFP_NOFAIL)) { + /* Coredumps can quickly deplete all memory reserves */ + if (current->flags & PF_DUMPCORE) + goto out; /* The OOM killer will not help higher order allocs */ if (order > PAGE_ALLOC_COSTLY_ORDER) goto out; /* The OOM killer does not needlessly kill tasks for lowmem */ if (high_zoneidx < ZONE_NORMAL) goto out; + /* The OOM killer does not compensate for light reclaim */ + if (!(gfp_mask & __GFP_FS)) + goto out; /* * GFP_THISNODE contains __GFP_NORETRY and we never hit this. * Sanity check for bare calls of __GFP_THISNODE, not real OOM. @@ -2381,7 +2396,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, } /* Exhausted what can be done so it's blamo time */ out_of_memory(zonelist, gfp_mask, order, nodemask, false); - + *did_some_progress = 1; out: oom_zonelist_unlock(zonelist, gfp_mask); return page; @@ -2658,7 +2673,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; -restart: +retry: if (!(gfp_mask & __GFP_NO_KSWAPD)) wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone, nodemask); @@ -2681,7 +2696,6 @@ restart: classzone_idx = zonelist_zone_idx(preferred_zoneref); } -rebalance: /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, @@ -2788,54 +2802,28 @@ rebalance: if (page) goto got_pg; - /* - * If we failed to make any progress reclaiming, then we are - * running out of options and have to consider going OOM - */ - if (!did_some_progress) { - if (oom_gfp_allowed(gfp_mask)) { - if (oom_killer_disabled) - goto nopage; - /* Coredumps can quickly deplete all memory reserves */ - if ((current->flags & PF_DUMPCORE) && - !(gfp_mask & __GFP_NOFAIL)) - goto nopage; - page = __alloc_pages_may_oom(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, preferred_zone, - classzone_idx, migratetype); - if (page) - goto got_pg; - - if (!(gfp_mask & __GFP_NOFAIL)) { - /* - * The oom killer is not called for high-order - * allocations that may fail, so if no progress - * is being made, there are no other options and - * retrying is unlikely to help. - */ - if (order > PAGE_ALLOC_COSTLY_ORDER) - goto nopage; - /* - * The oom killer is not called for lowmem - * allocations to prevent needlessly killing - * innocent tasks. - */ - if (high_zoneidx < ZONE_NORMAL) - goto nopage; - } - - goto restart; - } - } - /* Check if we should retry the allocation */ pages_reclaimed += did_some_progress; if (should_alloc_retry(gfp_mask, order, did_some_progress, pages_reclaimed)) { + /* + * If we fail to make progress by freeing individual + * pages, but the allocation wants us to keep going, + * start OOM killing tasks. + */ + if (!did_some_progress) { + page = __alloc_pages_may_oom(gfp_mask, order, zonelist, + high_zoneidx, nodemask, + preferred_zone, classzone_idx, + migratetype,&did_some_progress); + if (page) + goto got_pg; + if (!did_some_progress) + goto nopage; + } /* Wait for some write requests to complete then retry */ wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); - goto rebalance; + goto retry; } else { /* * High-order allocations do not necessarily loop after -- cgit v1.2.3 From 07261edb971492c6b41b44d7b1b51f76807d30ad Mon Sep 17 00:00:00 2001 From: Pranith Kumar Date: Mon, 26 Jan 2015 12:58:43 -0800 Subject: printk: add dummy routine for when CONFIG_PRINTK=n There are missing dummy routines for log_buf_addr_get() and log_buf_len_get() for when CONFIG_PRINTK is not set causing build failures. This patch adds these dummy routines at the appropriate location. Signed-off-by: Pranith Kumar Cc: Michael Ellerman Reviewed-by: Petr Mladek Acked-by: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index c8f170324e64..4d5bf5726578 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -10,9 +10,6 @@ extern const char linux_banner[]; extern const char linux_proc_banner[]; -extern char *log_buf_addr_get(void); -extern u32 log_buf_len_get(void); - static inline int printk_get_level(const char *buffer) { if (buffer[0] == KERN_SOH_ASCII && buffer[1]) { @@ -163,6 +160,8 @@ extern int kptr_restrict; extern void wake_up_klogd(void); +char *log_buf_addr_get(void); +u32 log_buf_len_get(void); void log_buf_kexec_setup(void); void __init setup_log_buf(int early); void dump_stack_set_arch_desc(const char *fmt, ...); @@ -198,6 +197,16 @@ static inline void wake_up_klogd(void) { } +static inline char *log_buf_addr_get(void) +{ + return NULL; +} + +static inline u32 log_buf_len_get(void) +{ + return 0; +} + static inline void log_buf_kexec_setup(void) { } -- cgit v1.2.3