From 5d7e23a79444385d03717dc19cc58dd2d5883052 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 1 Mar 2016 17:14:22 -0800 Subject: [PATCH 001/181] ARM: dts: Add clocks for dm814x ADPLL These use the standard clock bindings and now we can make some of the fixed clocks into real clocks. Note that the clock output names may become optional as we probably want to eventually use descriptive names, or use just dynamically generated names as suggested by Tero. Acked-by: Tero Kristo Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/dm814x-clocks.dtsi | 243 +++++++++++++++++++++++---- arch/arm/boot/dts/dra62x-clocks.dtsi | 26 +++ 2 files changed, 238 insertions(+), 31 deletions(-) diff --git a/arch/arm/boot/dts/dm814x-clocks.dtsi b/arch/arm/boot/dts/dm814x-clocks.dtsi index 26001585673a..60e9b332fabb 100644 --- a/arch/arm/boot/dts/dm814x-clocks.dtsi +++ b/arch/arm/boot/dts/dm814x-clocks.dtsi @@ -4,6 +4,157 @@ * published by the Free Software Foundation. */ +&pllss { + /* + * See TRM "2.6.10 Connected outputso DPLLS" and + * "2.6.11 Connected Outputs of DPLLJ". Only clkout is + * connected except for hdmi and usb. + */ + adpll_mpu_ck: adpll@40 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-s-clock"; + reg = <0x40 0x40>; + clocks = <&devosc_ck &devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow", "clkinphif"; + clock-output-names = "481c5040.adpll.dcoclkldo", + "481c5040.adpll.clkout", + "481c5040.adpll.clkoutx2", + "481c5040.adpll.clkouthif"; + }; + + adpll_dsp_ck: adpll@80 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x80 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5080.adpll.dcoclkldo", + "481c5080.adpll.clkout", + "481c5080.adpll.clkoutldo"; + }; + + adpll_sgx_ck: adpll@b0 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0xb0 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c50b0.adpll.dcoclkldo", + "481c50b0.adpll.clkout", + "481c50b0.adpll.clkoutldo"; + }; + + adpll_hdvic_ck: adpll@e0 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0xe0 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c50e0.adpll.dcoclkldo", + "481c50e0.adpll.clkout", + "481c50e0.adpll.clkoutldo"; + }; + + adpll_l3_ck: adpll@110 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x110 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5110.adpll.dcoclkldo", + "481c5110.adpll.clkout", + "481c5110.adpll.clkoutldo"; + }; + + adpll_isp_ck: adpll@140 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x140 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5140.adpll.dcoclkldo", + "481c5140.adpll.clkout", + "481c5140.adpll.clkoutldo"; + }; + + adpll_dss_ck: adpll@170 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x170 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5170.adpll.dcoclkldo", + "481c5170.adpll.clkout", + "481c5170.adpll.clkoutldo"; + }; + + adpll_video0_ck: adpll@1a0 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x1a0 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c51a0.adpll.dcoclkldo", + "481c51a0.adpll.clkout", + "481c51a0.adpll.clkoutldo"; + }; + + adpll_video1_ck: adpll@1d0 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x1d0 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c51d0.adpll.dcoclkldo", + "481c51d0.adpll.clkout", + "481c51d0.adpll.clkoutldo"; + }; + + adpll_hdmi_ck: adpll@200 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x200 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5200.adpll.dcoclkldo", + "481c5200.adpll.clkout", + "481c5200.adpll.clkoutldo"; + }; + + adpll_audio_ck: adpll@230 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x230 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5230.adpll.dcoclkldo", + "481c5230.adpll.clkout", + "481c5230.adpll.clkoutldo"; + }; + + adpll_usb_ck: adpll@260 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x260 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5260.adpll.dcoclkldo", + "481c5260.adpll.clkout", + "481c5260.adpll.clkoutldo"; + }; + + adpll_ddr_ck: adpll@290 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x290 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5290.adpll.dcoclkldo", + "481c5290.adpll.clkout", + "481c5290.adpll.clkoutldo"; + }; +}; + &pllss_clocks { timer1_fck: timer1_fck { #clock-cells = <0>; @@ -23,6 +174,24 @@ reg = <0x2e0>; }; + /* CPTS_RFT_CLK in RMII_REFCLK_SRC, usually sourced from auiod */ + cpsw_cpts_rft_clk: cpsw_cpts_rft_clk { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&adpll_video0_ck 1 + &adpll_video1_ck 1 + &adpll_audio_ck 1>; + ti,bit-shift = <1>; + reg = <0x2e8>; + }; + + /* REVISIT: Set up with a proper mux using RMII_REFCLK_SRC */ + cpsw_125mhz_gclk: cpsw_125mhz_gclk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <125000000>; + }; + sysclk18_ck: sysclk18_ck { #clock-cells = <0>; compatible = "ti,mux-clock"; @@ -79,37 +248,6 @@ compatible = "fixed-clock"; clock-frequency = <1000000000>; }; - - sysclk4_ck: sysclk4_ck { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <222000000>; - }; - - sysclk6_ck: sysclk6_ck { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <100000000>; - }; - - sysclk10_ck: sysclk10_ck { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <48000000>; - }; - - cpsw_125mhz_gclk: cpsw_125mhz_gclk { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <125000000>; - }; - - cpsw_cpts_rft_clk: cpsw_cpts_rft_clk { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <250000000>; - }; - }; &prcm_clocks { @@ -138,6 +276,49 @@ clock-div = <78125>; }; + /* L4_HS 220 MHz*/ + sysclk4_ck: sysclk4_ck { + #clock-cells = <0>; + compatible = "ti,fixed-factor-clock"; + clocks = <&adpll_l3_ck 1>; + ti,clock-mult = <1>; + ti,clock-div = <1>; + }; + + /* L4_FWCFG */ + sysclk5_ck: sysclk5_ck { + #clock-cells = <0>; + compatible = "ti,fixed-factor-clock"; + clocks = <&adpll_l3_ck 1>; + ti,clock-mult = <1>; + ti,clock-div = <2>; + }; + + /* L4_LS 110 MHz */ + sysclk6_ck: sysclk6_ck { + #clock-cells = <0>; + compatible = "ti,fixed-factor-clock"; + clocks = <&adpll_l3_ck 1>; + ti,clock-mult = <1>; + ti,clock-div = <2>; + }; + + sysclk8_ck: sysclk8_ck { + #clock-cells = <0>; + compatible = "ti,fixed-factor-clock"; + clocks = <&adpll_usb_ck 1>; + ti,clock-mult = <1>; + ti,clock-div = <1>; + }; + + sysclk10_ck: sysclk10_ck { + compatible = "ti,divider-clock"; + reg = <0x324>; + ti,max-div = <7>; + #clock-cells = <0>; + clocks = <&adpll_usb_ck 1>; + }; + aud_clkin0_ck: aud_clkin0_ck { #clock-cells = <0>; compatible = "fixed-clock"; diff --git a/arch/arm/boot/dts/dra62x-clocks.dtsi b/arch/arm/boot/dts/dra62x-clocks.dtsi index 6f98dc8df9dd..0e49741747ef 100644 --- a/arch/arm/boot/dts/dra62x-clocks.dtsi +++ b/arch/arm/boot/dts/dra62x-clocks.dtsi @@ -6,6 +6,32 @@ #include "dm814x-clocks.dtsi" +/* Compared to dm814x, dra62x does not have hdic, l3 or dss PLLs */ +&adpll_hdvic_ck { + status = "disabled"; +}; + +&adpll_l3_ck { + status = "disabled"; +}; + +&adpll_dss_ck { + status = "disabled"; +}; + +/* Compared to dm814x, dra62x has interconnect clocks on isp PLL */ +&sysclk4_ck { + clocks = <&adpll_isp_ck 1>; +}; + +&sysclk5_ck { + clocks = <&adpll_isp_ck 1>; +}; + +&sysclk6_ck { + clocks = <&adpll_isp_ck 1>; +}; + /* * Compared to dm814x, dra62x has different shifts and more mux options. * Please add the extra options for ysclk_14 and 16 if really needed. From dd5dc001581a7cf6f563e188c302caae1be998c2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 14 Mar 2016 15:49:54 +0100 Subject: [PATCH 002/181] ASoC: cs35l32: avoid uninitialized variable access gcc warns about the possibilty of accessing a property read from devicetree in cs35l32_i2c_probe() when it has not been initialized because CONFIG_OF is disabled: sound/soc/codecs/cs35l32.c: In function 'cs35l32_i2c_probe': sound/soc/codecs/cs35l32.c:278:2: warning: 'val' may be used uninitialized in this function [-Wmaybe-uninitialized] The code is actually correct because it checks the dev->of_node variable first and we know this is NULL here when CONFIG_OF is disabled, but Russell King noticed that it's broken when we probe the device using DT, and the properties are absent. The code already has some checking for incorrect values, and I keep that checking unchanged here, but add an additional check for an error returned by the property accessor functions that now gets handled the same way as incorrect data in the properties. Signed-off-by: Arnd Bergmann Acked-by: Brian Austin Signed-off-by: Mark Brown --- sound/soc/codecs/cs35l32.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/sound/soc/codecs/cs35l32.c b/sound/soc/codecs/cs35l32.c index 44c30fe3e315..287d13740be4 100644 --- a/sound/soc/codecs/cs35l32.c +++ b/sound/soc/codecs/cs35l32.c @@ -274,7 +274,9 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, if (of_property_read_u32(np, "cirrus,sdout-share", &val) >= 0) pdata->sdout_share = val; - of_property_read_u32(np, "cirrus,boost-manager", &val); + if (of_property_read_u32(np, "cirrus,boost-manager", &val)) + val = -1u; + switch (val) { case CS35L32_BOOST_MGR_AUTO: case CS35L32_BOOST_MGR_AUTO_AUDIO: @@ -282,13 +284,15 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, case CS35L32_BOOST_MGR_FIXED: pdata->boost_mng = val; break; + case -1u: default: dev_err(&i2c_client->dev, "Wrong cirrus,boost-manager DT value %d\n", val); pdata->boost_mng = CS35L32_BOOST_MGR_BYPASS; } - of_property_read_u32(np, "cirrus,sdout-datacfg", &val); + if (of_property_read_u32(np, "cirrus,sdout-datacfg", &val)) + val = -1u; switch (val) { case CS35L32_DATA_CFG_LR_VP: case CS35L32_DATA_CFG_LR_STAT: @@ -296,13 +300,15 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, case CS35L32_DATA_CFG_LR_VPSTAT: pdata->sdout_datacfg = val; break; + case -1u: default: dev_err(&i2c_client->dev, "Wrong cirrus,sdout-datacfg DT value %d\n", val); pdata->sdout_datacfg = CS35L32_DATA_CFG_LR; } - of_property_read_u32(np, "cirrus,battery-threshold", &val); + if (of_property_read_u32(np, "cirrus,battery-threshold", &val)) + val = -1u; switch (val) { case CS35L32_BATT_THRESH_3_1V: case CS35L32_BATT_THRESH_3_2V: @@ -310,13 +316,15 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, case CS35L32_BATT_THRESH_3_4V: pdata->batt_thresh = val; break; + case -1u: default: dev_err(&i2c_client->dev, "Wrong cirrus,battery-threshold DT value %d\n", val); pdata->batt_thresh = CS35L32_BATT_THRESH_3_3V; } - of_property_read_u32(np, "cirrus,battery-recovery", &val); + if (of_property_read_u32(np, "cirrus,battery-recovery", &val)) + val = -1u; switch (val) { case CS35L32_BATT_RECOV_3_1V: case CS35L32_BATT_RECOV_3_2V: @@ -326,6 +334,7 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, case CS35L32_BATT_RECOV_3_6V: pdata->batt_recov = val; break; + case -1u: default: dev_err(&i2c_client->dev, "Wrong cirrus,battery-recovery DT value %d\n", val); From af139d5592bc812e7a1997727172ddba3e6be968 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 15 Mar 2016 22:42:50 +0100 Subject: [PATCH 003/181] ASoC: rt5616: add I2C dependency The rt5616 codec registers itself as an i2c driver, but can be enabled even when i2c is turned off, which leads to a build error: codecs/rt5616.c:1419:1: error: data definition has no type or storage class [-Werror] module_i2c_driver(rt5616_i2c_driver); This adds an explicit Kconfig dependency, like the other codec drivers. Signed-off-by: Arnd Bergmann Fixes: 288bc356a881 ("ASoC: rt5616: allow to build with CONFIG_SND_SOC_RT5616") Signed-off-by: Mark Brown --- sound/soc/codecs/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 649e92a252ae..7ef3a0c16478 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -629,6 +629,7 @@ config SND_SOC_RT5514 config SND_SOC_RT5616 tristate "Realtek RT5616 CODEC" + depends on I2C config SND_SOC_RT5631 tristate "Realtek ALC5631/RT5631 CODEC" From 4a6c5e6a8d29e4d33858227db9179e91aa8a7407 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 15 Mar 2016 16:39:23 +0530 Subject: [PATCH 004/181] ALSA: hda: use list macro for parsing on cleanup It is always better to use list_for_each_entry_safe() while doing cleanup. So use this instead of open coding this in list in snd_hdac_stream_free_all() Signed-off-by: Jeeja KP Acked-by: Takashi Iwai Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/hda/ext/hdac_ext_stream.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c index 023cc4cad5c1..626f3bb24c55 100644 --- a/sound/hda/ext/hdac_ext_stream.c +++ b/sound/hda/ext/hdac_ext_stream.c @@ -104,12 +104,11 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_init_all); */ void snd_hdac_stream_free_all(struct hdac_ext_bus *ebus) { - struct hdac_stream *s; + struct hdac_stream *s, *_s; struct hdac_ext_stream *stream; struct hdac_bus *bus = ebus_to_hbus(ebus); - while (!list_empty(&bus->stream_list)) { - s = list_first_entry(&bus->stream_list, struct hdac_stream, list); + list_for_each_entry_safe(s, _s, &bus->stream_list, list) { stream = stream_to_hdac_ext_stream(s); snd_hdac_ext_stream_decouple(ebus, stream, false); list_del(&s->list); From 7373f481dc4098a844a756201e98341bc56baaa2 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 15 Mar 2016 16:39:24 +0530 Subject: [PATCH 005/181] ASoC: Intel: Skylake: free codec objects on removal On driver removal we should ask the core to remove the device objects as well, so invoke snd_hdac_ext_bus_device_remove() in remove. Signed-off-by: Jeeja KP Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index ab5e25aaeee3..292d51db9a22 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -725,6 +725,10 @@ static void skl_remove(struct pci_dev *pci) if (pci_dev_run_wake(pci)) pm_runtime_get_noresume(&pci->dev); pci_dev_put(pci); + + /* codec removal, invoke bus_device_remove */ + snd_hdac_ext_bus_device_remove(ebus); + skl_platform_unregister(&pci->dev); skl_free_dsp(skl); skl_machine_device_unregister(skl); From 3f7f8489e25b180cf8de8a3ae3896b3f18fc4aa5 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 15 Mar 2016 16:39:25 +0530 Subject: [PATCH 006/181] ASoC: Intel: Skylake: Freeup properly on skl_dsp_free We are supposed to freeup the Code loader DMA allocation and ensure all interrupts are disabled before we disable dsp cores. So invoke these to ensure DSP shuts down properly. Signed-off-by: Jeeja KP Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl-sst-dsp.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/soc/intel/skylake/skl-sst-dsp.c b/sound/soc/intel/skylake/skl-sst-dsp.c index a5267e8a96e0..2962ef22fc84 100644 --- a/sound/soc/intel/skylake/skl-sst-dsp.c +++ b/sound/soc/intel/skylake/skl-sst-dsp.c @@ -336,6 +336,11 @@ void skl_dsp_free(struct sst_dsp *dsp) skl_ipc_int_disable(dsp); free_irq(dsp->irq, dsp); + dsp->cl_dev.ops.cl_cleanup_controller(dsp); + skl_cldma_int_disable(dsp); + skl_ipc_op_int_disable(dsp); + skl_ipc_int_disable(dsp); + skl_dsp_disable_core(dsp); } EXPORT_SYMBOL_GPL(skl_dsp_free); From 077411e5eb8872736fdc5f3e7277719160918dde Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 15 Mar 2016 16:39:26 +0530 Subject: [PATCH 007/181] ASoC: Intel: Skylake: Unmap the address last In Skylake destructor we unmap the hardware address and then free links and streams. The stream free accesses hardware to write to registers and predictably causes oops. So change the order and unmap last in destructor. Signed-off-by: Jeeja KP Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 292d51db9a22..6e916c3c3a4b 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -316,12 +316,13 @@ static int skl_free(struct hdac_ext_bus *ebus) if (bus->irq >= 0) free_irq(bus->irq, (void *)bus); - if (bus->remap_addr) - iounmap(bus->remap_addr); - snd_hdac_bus_free_stream_pages(bus); snd_hdac_stream_free_all(ebus); snd_hdac_link_free_all(ebus); + + if (bus->remap_addr) + iounmap(bus->remap_addr); + pci_release_regions(skl->pci); pci_disable_device(skl->pci); From 5b2fe89856b2d0faaaea9e4b4b2c4920de7a600c Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 15 Mar 2016 16:39:27 +0530 Subject: [PATCH 008/181] ASoC: Intel: Skylake: Call i915 exit last The Skylake driver uses i915 component APIs to talk to display. On remove we should free up by invoking snd_hdac_i915_exit() but that should be last thing in remove routine, so move it to last in skl_free() Signed-off-by: Jeeja KP Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 6e916c3c3a4b..72971dc55c52 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -328,6 +328,8 @@ static int skl_free(struct hdac_ext_bus *ebus) snd_hdac_ext_bus_exit(ebus); + if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) + snd_hdac_i915_exit(&ebus->bus); return 0; } @@ -720,9 +722,6 @@ static void skl_remove(struct pci_dev *pci) if (skl->tplg) release_firmware(skl->tplg); - if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) - snd_hdac_i915_exit(&ebus->bus); - if (pci_dev_run_wake(pci)) pm_runtime_get_noresume(&pci->dev); pci_dev_put(pci); From 36e7972c0d3f8819a5d9335c36c5dcd168cd2b72 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Wed, 16 Mar 2016 21:51:31 +0530 Subject: [PATCH 009/181] ASoC: Intel: Skylake: remove call to pci_dev_put The PCI bus takes pci_dev_get() and pci_dev_put() is also there. So no need for drivers to invoke these. In SKL driver we were calling pci_dev_put() only which is not right, so remove this Signed-off-by: Jeeja KP Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 72971dc55c52..07d9bc1cf3cb 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -724,7 +724,6 @@ static void skl_remove(struct pci_dev *pci) if (pci_dev_run_wake(pci)) pm_runtime_get_noresume(&pci->dev); - pci_dev_put(pci); /* codec removal, invoke bus_device_remove */ snd_hdac_ext_bus_device_remove(ebus); From 653aa4645244042826f105aab1be3d01b3d493ca Mon Sep 17 00:00:00 2001 From: Sugar Zhang Date: Fri, 18 Mar 2016 14:54:22 +0800 Subject: [PATCH 010/181] ASoC: rt5640: Correct the digital interface data select this patch corrects the interface adc/dac control register definition according to datasheet. Signed-off-by: Sugar Zhang Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/codecs/rt5640.c | 2 +- sound/soc/codecs/rt5640.h | 36 ++++++++++++++++++------------------ 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index e8b5ba04417a..09e8988bbb2d 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -359,7 +359,7 @@ static const DECLARE_TLV_DB_RANGE(bst_tlv, /* Interface data select */ static const char * const rt5640_data_select[] = { - "Normal", "left copy to right", "right copy to left", "Swap"}; + "Normal", "Swap", "left copy to right", "right copy to left"}; static SOC_ENUM_SINGLE_DECL(rt5640_if1_dac_enum, RT5640_DIG_INF_DATA, RT5640_IF1_DAC_SEL_SFT, rt5640_data_select); diff --git a/sound/soc/codecs/rt5640.h b/sound/soc/codecs/rt5640.h index 1761c3a98b76..58b664b06c16 100644 --- a/sound/soc/codecs/rt5640.h +++ b/sound/soc/codecs/rt5640.h @@ -443,39 +443,39 @@ #define RT5640_IF1_DAC_SEL_MASK (0x3 << 14) #define RT5640_IF1_DAC_SEL_SFT 14 #define RT5640_IF1_DAC_SEL_NOR (0x0 << 14) -#define RT5640_IF1_DAC_SEL_L2R (0x1 << 14) -#define RT5640_IF1_DAC_SEL_R2L (0x2 << 14) -#define RT5640_IF1_DAC_SEL_SWAP (0x3 << 14) +#define RT5640_IF1_DAC_SEL_SWAP (0x1 << 14) +#define RT5640_IF1_DAC_SEL_L2R (0x2 << 14) +#define RT5640_IF1_DAC_SEL_R2L (0x3 << 14) #define RT5640_IF1_ADC_SEL_MASK (0x3 << 12) #define RT5640_IF1_ADC_SEL_SFT 12 #define RT5640_IF1_ADC_SEL_NOR (0x0 << 12) -#define RT5640_IF1_ADC_SEL_L2R (0x1 << 12) -#define RT5640_IF1_ADC_SEL_R2L (0x2 << 12) -#define RT5640_IF1_ADC_SEL_SWAP (0x3 << 12) +#define RT5640_IF1_ADC_SEL_SWAP (0x1 << 12) +#define RT5640_IF1_ADC_SEL_L2R (0x2 << 12) +#define RT5640_IF1_ADC_SEL_R2L (0x3 << 12) #define RT5640_IF2_DAC_SEL_MASK (0x3 << 10) #define RT5640_IF2_DAC_SEL_SFT 10 #define RT5640_IF2_DAC_SEL_NOR (0x0 << 10) -#define RT5640_IF2_DAC_SEL_L2R (0x1 << 10) -#define RT5640_IF2_DAC_SEL_R2L (0x2 << 10) -#define RT5640_IF2_DAC_SEL_SWAP (0x3 << 10) +#define RT5640_IF2_DAC_SEL_SWAP (0x1 << 10) +#define RT5640_IF2_DAC_SEL_L2R (0x2 << 10) +#define RT5640_IF2_DAC_SEL_R2L (0x3 << 10) #define RT5640_IF2_ADC_SEL_MASK (0x3 << 8) #define RT5640_IF2_ADC_SEL_SFT 8 #define RT5640_IF2_ADC_SEL_NOR (0x0 << 8) -#define RT5640_IF2_ADC_SEL_L2R (0x1 << 8) -#define RT5640_IF2_ADC_SEL_R2L (0x2 << 8) -#define RT5640_IF2_ADC_SEL_SWAP (0x3 << 8) +#define RT5640_IF2_ADC_SEL_SWAP (0x1 << 8) +#define RT5640_IF2_ADC_SEL_L2R (0x2 << 8) +#define RT5640_IF2_ADC_SEL_R2L (0x3 << 8) #define RT5640_IF3_DAC_SEL_MASK (0x3 << 6) #define RT5640_IF3_DAC_SEL_SFT 6 #define RT5640_IF3_DAC_SEL_NOR (0x0 << 6) -#define RT5640_IF3_DAC_SEL_L2R (0x1 << 6) -#define RT5640_IF3_DAC_SEL_R2L (0x2 << 6) -#define RT5640_IF3_DAC_SEL_SWAP (0x3 << 6) +#define RT5640_IF3_DAC_SEL_SWAP (0x1 << 6) +#define RT5640_IF3_DAC_SEL_L2R (0x2 << 6) +#define RT5640_IF3_DAC_SEL_R2L (0x3 << 6) #define RT5640_IF3_ADC_SEL_MASK (0x3 << 4) #define RT5640_IF3_ADC_SEL_SFT 4 #define RT5640_IF3_ADC_SEL_NOR (0x0 << 4) -#define RT5640_IF3_ADC_SEL_L2R (0x1 << 4) -#define RT5640_IF3_ADC_SEL_R2L (0x2 << 4) -#define RT5640_IF3_ADC_SEL_SWAP (0x3 << 4) +#define RT5640_IF3_ADC_SEL_SWAP (0x1 << 4) +#define RT5640_IF3_ADC_SEL_L2R (0x2 << 4) +#define RT5640_IF3_ADC_SEL_R2L (0x3 << 4) /* REC Left Mixer Control 1 (0x3b) */ #define RT5640_G_HP_L_RM_L_MASK (0x7 << 13) From 47325078f2a3e543150e7df967e45756b2fff7ec Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 18 Mar 2016 12:04:23 +0000 Subject: [PATCH 011/181] ASoC: dapm: Make sure we have a card when displaying component widgets The dummy component is reused for all cards so we special case and don't bind it to any of them. This means that code like that displaying the component widgets that tries to look at the card will crash. In the future we will fix this by ensuring that the dummy component looks like other components but that is invasive and so not suitable for a fix. Instead add a special case check here. Reported-by: Harry Pan Suggested-by: Lars-Peter Clausen Signed-off-by: Mark Brown Cc: stable@vger.kernel.org --- sound/soc/soc-dapm.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 801ae1a81dfd..c4464858bf01 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -2188,6 +2188,13 @@ static ssize_t dapm_widget_show_component(struct snd_soc_component *cmpnt, int count = 0; char *state = "not set"; + /* card won't be set for the dummy component, as a spot fix + * we're checking for that case specifically here but in future + * we will ensure that the dummy component looks like others. + */ + if (!cmpnt->card) + return 0; + list_for_each_entry(w, &cmpnt->card->widgets, list) { if (w->dapm != dapm) continue; From c3efb42b207e22991dee86ca15861ede11a419fc Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Fri, 18 Mar 2016 20:10:23 +0530 Subject: [PATCH 012/181] ASoC: Intel: Skylake: Fix kbuild dependency The Skylake driver selects SND_HDA_I915 which causes kbuild to spew warning: warning: (SND_SOC_INTEL_SKYLAKE) selects SND_HDA_I915 which has unmet direct dependencies (SOUND && !M68K && !UML && SND && DRM_I915 && SND_HDA_CORE) The SND_HDA_I915 should not be selected so drop that. Reported-by: Takashi Iwai Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig index b3e6c2300457..1120f4f4d011 100644 --- a/sound/soc/intel/Kconfig +++ b/sound/soc/intel/Kconfig @@ -163,7 +163,6 @@ config SND_SOC_INTEL_SKYLAKE tristate select SND_HDA_EXT_CORE select SND_SOC_TOPOLOGY - select SND_HDA_I915 select SND_SOC_INTEL_SST config SND_SOC_INTEL_SKL_RT286_MACH From d643678b9a4e432a574b2ec601216afd720c69b6 Mon Sep 17 00:00:00 2001 From: Jeeja KP Date: Mon, 28 Mar 2016 22:11:30 +0530 Subject: [PATCH 013/181] ASoC: Intel: Skylake: Fix for unloading module only when it is loaded Module needs to be unloaded only when it is loaded successfully. To fix this, first correct the module state sequence and set module state to LOADED if module is loaded successfully. When unloading the module check if module state is not in UNINIT, then unload it. Signed-off-by: Jeeja KP Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl-topology.c | 5 ++++- sound/soc/intel/skylake/skl-topology.h | 8 ++++---- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index 545b4e77b8aa..3f393cbe1bfe 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -490,6 +490,8 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe) mconfig->id.module_id, mconfig->guid); if (ret < 0) return ret; + + mconfig->m_state = SKL_MODULE_LOADED; } /* update blob if blob is null for be with default value */ @@ -524,7 +526,8 @@ static int skl_tplg_unload_pipe_modules(struct skl_sst *ctx, list_for_each_entry(w_module, &pipe->w_list, node) { mconfig = w_module->w->priv; - if (mconfig->is_loadable && ctx->dsp->fw_ops.unload_mod) + if (mconfig->is_loadable && ctx->dsp->fw_ops.unload_mod && + mconfig->m_state > SKL_MODULE_UNINIT) return ctx->dsp->fw_ops.unload_mod(ctx->dsp, mconfig->id.module_id); } diff --git a/sound/soc/intel/skylake/skl-topology.h b/sound/soc/intel/skylake/skl-topology.h index de3c401284d9..d2d923002d5c 100644 --- a/sound/soc/intel/skylake/skl-topology.h +++ b/sound/soc/intel/skylake/skl-topology.h @@ -274,10 +274,10 @@ struct skl_pipe { enum skl_module_state { SKL_MODULE_UNINIT = 0, - SKL_MODULE_INIT_DONE = 1, - SKL_MODULE_LOADED = 2, - SKL_MODULE_UNLOADED = 3, - SKL_MODULE_BIND_DONE = 4 + SKL_MODULE_LOADED = 1, + SKL_MODULE_INIT_DONE = 2, + SKL_MODULE_BIND_DONE = 3, + SKL_MODULE_UNLOADED = 4, }; struct skl_module_cfg { From 4f329d9fbab630af44db2f787eb79ca52e6ba22e Mon Sep 17 00:00:00 2001 From: Jeeja KP Date: Mon, 28 Mar 2016 22:11:31 +0530 Subject: [PATCH 014/181] ASoC: Intel: Skylake: Fix DSP resource de-allocation In PRE PMD of widget handler DSP resources are allocated after the creation of DSP pipe and modules and in POST PMD DSP resources are destroyed. If there is any failure in pipe or module creation in PRE PMD, pcm trigger fails and finally POST PMD gets called and DSP resources are freed, without getting allocated. Fixes the DSP resource de-allocation by allocating the resource before creation of pipe and module in PRE PMD and in POST PMD, free the resources. Signed-off-by: Jeeja KP Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl-topology.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index 3f393cbe1bfe..5a85f3a4699b 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -485,6 +485,8 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe) if (!skl_is_pipe_mcps_avail(skl, mconfig)) return -ENOMEM; + skl_tplg_alloc_pipe_mcps(skl, mconfig); + if (mconfig->is_loadable && ctx->dsp->fw_ops.load_mod) { ret = ctx->dsp->fw_ops.load_mod(ctx->dsp, mconfig->id.module_id, mconfig->guid); @@ -511,7 +513,6 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe) ret = skl_tplg_set_module_params(w, ctx); if (ret < 0) return ret; - skl_tplg_alloc_pipe_mcps(skl, mconfig); } return 0; @@ -561,6 +562,9 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w, if (!skl_is_pipe_mem_avail(skl, mconfig)) return -ENOMEM; + skl_tplg_alloc_pipe_mem(skl, mconfig); + skl_tplg_alloc_pipe_mcps(skl, mconfig); + /* * Create a list of modules for pipe. * This list contains modules from source to sink @@ -604,9 +608,6 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w, src_module = dst_module; } - skl_tplg_alloc_pipe_mem(skl, mconfig); - skl_tplg_alloc_pipe_mcps(skl, mconfig); - return 0; } From e6cee90075c0ff261ff7eef8ad892429f028e194 Mon Sep 17 00:00:00 2001 From: Ben Zhang Date: Fri, 25 Mar 2016 16:10:39 -0700 Subject: [PATCH 015/181] ASoC: nau8825: Fix jack detection across suspend Jack plug status is rechecked at resume to handle plug/unplug in S3 when the chip has no power. Suspend/resume callbacks are moved from the i2c dev_pm_ops to snd_soc_codec_driver. soc_resume_deferred is a delayed work which may trigger nau8825_set_bias_level. The bias change races against dev_pm_ops, causing jack detection issues. soc_resume_deferred ensures bias change and snd_soc_codec_driver suspend/resume are sequenced correctly. Signed-off-by: Ben Zhang Signed-off-by: Mark Brown --- sound/soc/codecs/nau8825.c | 126 +++++++++++++++++++++---------------- 1 file changed, 71 insertions(+), 55 deletions(-) diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index 1c8729984c2b..683769f0f246 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -343,9 +343,12 @@ static const struct snd_soc_dapm_widget nau8825_dapm_widgets[] = { SND_SOC_DAPM_SUPPLY("ADC Power", NAU8825_REG_ANALOG_ADC_2, 6, 0, NULL, 0), - /* ADC for button press detection */ - SND_SOC_DAPM_ADC("SAR", NULL, NAU8825_REG_SAR_CTRL, - NAU8825_SAR_ADC_EN_SFT, 0), + /* ADC for button press detection. A dapm supply widget is used to + * prevent dapm_power_widgets keeping the codec at SND_SOC_BIAS_ON + * during suspend. + */ + SND_SOC_DAPM_SUPPLY("SAR", NAU8825_REG_SAR_CTRL, + NAU8825_SAR_ADC_EN_SFT, 0, NULL, 0), SND_SOC_DAPM_PGA_S("ADACL", 2, NAU8825_REG_RDAC, 12, 0, NULL, 0), SND_SOC_DAPM_PGA_S("ADACR", 2, NAU8825_REG_RDAC, 13, 0, NULL, 0), @@ -607,6 +610,16 @@ static bool nau8825_is_jack_inserted(struct regmap *regmap) static void nau8825_restart_jack_detection(struct regmap *regmap) { + /* Chip needs one FSCLK cycle in order to generate interrupts, + * as we cannot guarantee one will be provided by the system. Turning + * master mode on then off enables us to generate that FSCLK cycle + * with a minimum of contention on the clock bus. + */ + regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2, + NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_MASTER); + regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2, + NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_SLAVE); + /* this will restart the entire jack detection process including MIC/GND * switching and create interrupts. We have to go from 0 to 1 and back * to 0 to restart. @@ -728,7 +741,10 @@ static irqreturn_t nau8825_interrupt(int irq, void *data) struct regmap *regmap = nau8825->regmap; int active_irq, clear_irq = 0, event = 0, event_mask = 0; - regmap_read(regmap, NAU8825_REG_IRQ_STATUS, &active_irq); + if (regmap_read(regmap, NAU8825_REG_IRQ_STATUS, &active_irq)) { + dev_err(nau8825->dev, "failed to read irq status\n"); + return IRQ_NONE; + } if ((active_irq & NAU8825_JACK_EJECTION_IRQ_MASK) == NAU8825_JACK_EJECTION_DETECTED) { @@ -1141,33 +1157,74 @@ static int nau8825_set_bias_level(struct snd_soc_codec *codec, return ret; } } - - ret = regcache_sync(nau8825->regmap); - if (ret) { - dev_err(codec->dev, - "Failed to sync cache: %d\n", ret); - return ret; - } } - break; case SND_SOC_BIAS_OFF: if (nau8825->mclk_freq) clk_disable_unprepare(nau8825->mclk); - - regcache_mark_dirty(nau8825->regmap); break; } return 0; } +#ifdef CONFIG_PM +static int nau8825_suspend(struct snd_soc_codec *codec) +{ + struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); + + disable_irq(nau8825->irq); + regcache_cache_only(nau8825->regmap, true); + regcache_mark_dirty(nau8825->regmap); + + return 0; +} + +static int nau8825_resume(struct snd_soc_codec *codec) +{ + struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); + + /* The chip may lose power and reset in S3. regcache_sync restores + * register values including configurations for sysclk, irq, and + * jack/button detection. + */ + regcache_cache_only(nau8825->regmap, false); + regcache_sync(nau8825->regmap); + + /* Check the jack plug status directly. If the headset is unplugged + * during S3 when the chip has no power, there will be no jack + * detection irq even after the nau8825_restart_jack_detection below, + * because the chip just thinks no headset has ever been plugged in. + */ + if (!nau8825_is_jack_inserted(nau8825->regmap)) { + nau8825_eject_jack(nau8825); + snd_soc_jack_report(nau8825->jack, 0, SND_JACK_HEADSET); + } + + enable_irq(nau8825->irq); + + /* Run jack detection to check the type (OMTP or CTIA) of the headset + * if there is one. This handles the case where a different type of + * headset is plugged in during S3. This triggers an IRQ iff a headset + * is already plugged in. + */ + nau8825_restart_jack_detection(nau8825->regmap); + + return 0; +} +#else +#define nau8825_suspend NULL +#define nau8825_resume NULL +#endif + static struct snd_soc_codec_driver nau8825_codec_driver = { .probe = nau8825_codec_probe, .set_sysclk = nau8825_set_sysclk, .set_pll = nau8825_set_pll, .set_bias_level = nau8825_set_bias_level, .suspend_bias_off = true, + .suspend = nau8825_suspend, + .resume = nau8825_resume, .controls = nau8825_controls, .num_controls = ARRAY_SIZE(nau8825_controls), @@ -1277,16 +1334,6 @@ static int nau8825_setup_irq(struct nau8825 *nau8825) regmap_update_bits(regmap, NAU8825_REG_ENA_CTRL, NAU8825_ENABLE_DACR, NAU8825_ENABLE_DACR); - /* Chip needs one FSCLK cycle in order to generate interrupts, - * as we cannot guarantee one will be provided by the system. Turning - * master mode on then off enables us to generate that FSCLK cycle - * with a minimum of contention on the clock bus. - */ - regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2, - NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_MASTER); - regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2, - NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_SLAVE); - ret = devm_request_threaded_irq(nau8825->dev, nau8825->irq, NULL, nau8825_interrupt, IRQF_TRIGGER_LOW | IRQF_ONESHOT, "nau8825", nau8825); @@ -1354,36 +1401,6 @@ static int nau8825_i2c_remove(struct i2c_client *client) return 0; } -#ifdef CONFIG_PM_SLEEP -static int nau8825_suspend(struct device *dev) -{ - struct i2c_client *client = to_i2c_client(dev); - struct nau8825 *nau8825 = dev_get_drvdata(dev); - - disable_irq(client->irq); - regcache_cache_only(nau8825->regmap, true); - regcache_mark_dirty(nau8825->regmap); - - return 0; -} - -static int nau8825_resume(struct device *dev) -{ - struct i2c_client *client = to_i2c_client(dev); - struct nau8825 *nau8825 = dev_get_drvdata(dev); - - regcache_cache_only(nau8825->regmap, false); - regcache_sync(nau8825->regmap); - enable_irq(client->irq); - - return 0; -} -#endif - -static const struct dev_pm_ops nau8825_pm = { - SET_SYSTEM_SLEEP_PM_OPS(nau8825_suspend, nau8825_resume) -}; - static const struct i2c_device_id nau8825_i2c_ids[] = { { "nau8825", 0 }, { } @@ -1410,7 +1427,6 @@ static struct i2c_driver nau8825_driver = { .name = "nau8825", .of_match_table = of_match_ptr(nau8825_of_ids), .acpi_match_table = ACPI_PTR(nau8825_acpi_match), - .pm = &nau8825_pm, }, .probe = nau8825_i2c_probe, .remove = nau8825_i2c_remove, From 33362c69c8e68281633a7c3a1d5c840e940097b7 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Mon, 28 Mar 2016 10:47:34 +0100 Subject: [PATCH 016/181] ASoC: wm8962: Correct typo when setting DSPCLK rate The variable dspclk holds the rate of the DSPCLK, but the variable sysclk holds an identifier for the clock. Currently if read a non-sensical value from the DSPCLK_DIV register we assign sysclk to dspclk, clearly this was intended to be sysclk_rate. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- sound/soc/codecs/wm8962.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 88223608a33f..720a14e0687d 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2471,7 +2471,7 @@ static void wm8962_configure_bclk(struct snd_soc_codec *codec) break; default: dev_warn(codec->dev, "Unknown DSPCLK divisor read back\n"); - dspclk = wm8962->sysclk; + dspclk = wm8962->sysclk_rate; } dev_dbg(codec->dev, "DSPCLK is %dHz, BCLK %d\n", dspclk, wm8962->bclk); From 0fee1798af81b1428d8d5886ea48116444e635fc Mon Sep 17 00:00:00 2001 From: "Subhransu S. Prusty" Date: Fri, 1 Apr 2016 13:36:25 +0530 Subject: [PATCH 017/181] ASoC: hdac_hdmi: Fix to use dev_pm ops instead soc pm Use dev_pm ops feature instead of soc pm as core assumes system is capable of direct complete. Register with complete callback instead of resume to synchronize with Jack notification from display driver. This ensures correct Jack notification to user space. Signed-off-by: Subhransu S. Prusty Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/codecs/hdac_hdmi.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index 26f9459cb3bc..da3432c9f64d 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -1420,9 +1420,9 @@ static int hdmi_codec_remove(struct snd_soc_codec *codec) } #ifdef CONFIG_PM -static int hdmi_codec_resume(struct snd_soc_codec *codec) +static void hdmi_codec_complete(struct device *dev) { - struct hdac_ext_device *edev = snd_soc_codec_get_drvdata(codec); + struct hdac_ext_device *edev = to_hda_ext_device(dev); struct hdac_hdmi_priv *hdmi = edev->private_data; struct hdac_hdmi_pin *pin; struct hdac_device *hdac = &edev->hdac; @@ -1464,19 +1464,15 @@ static int hdmi_codec_resume(struct snd_soc_codec *codec) dev_err(bus->dev, "Cannot turn OFF display power on i915, err: %d\n", err); - return err; } - - return 0; } #else -#define hdmi_codec_resume NULL +#define hdmi_codec_complete NULL #endif static struct snd_soc_codec_driver hdmi_hda_codec = { .probe = hdmi_codec_probe, .remove = hdmi_codec_remove, - .resume = hdmi_codec_resume, .idle_bias_off = true, }; @@ -1629,6 +1625,7 @@ static int hdac_hdmi_runtime_resume(struct device *dev) static const struct dev_pm_ops hdac_hdmi_pm = { SET_RUNTIME_PM_OPS(hdac_hdmi_runtime_suspend, hdac_hdmi_runtime_resume, NULL) + .complete = hdmi_codec_complete, }; static const struct hda_device_id hdmi_list[] = { From 1b377ccddd14cd04df4b9523a426b34f928002bc Mon Sep 17 00:00:00 2001 From: "Subhransu S. Prusty" Date: Fri, 1 Apr 2016 13:36:26 +0530 Subject: [PATCH 018/181] ASoC: hdac_hdmi: Fix codec power state in S3 during playback If the system enters S3 during a playback, codec power needs to be turned OFF during suspend and restored during resume. With this patch the AFG node is set to D3 and codec power is turned OFF during controller suspend call. During resume, the codec power is left in ON state if the playback was in progress while suspending. Also setting power state for AFG node is optimized. With this the loop with timeout is removed and codec_read is used instead. Signed-off-by: Subhransu S. Prusty Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/codecs/hdac_hdmi.c | 83 +++++++++++++++++------------------- 1 file changed, 38 insertions(+), 45 deletions(-) diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index da3432c9f64d..aaa038ffc8a5 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -1420,33 +1420,40 @@ static int hdmi_codec_remove(struct snd_soc_codec *codec) } #ifdef CONFIG_PM +static int hdmi_codec_prepare(struct device *dev) +{ + struct hdac_ext_device *edev = to_hda_ext_device(dev); + struct hdac_device *hdac = &edev->hdac; + + pm_runtime_get_sync(&edev->hdac.dev); + + /* + * Power down afg. + * codec_read is preferred over codec_write to set the power state. + * This way verb is send to set the power state and response + * is received. So setting power state is ensured without using loop + * to read the state. + */ + snd_hdac_codec_read(hdac, hdac->afg, 0, AC_VERB_SET_POWER_STATE, + AC_PWRST_D3); + + return 0; +} + static void hdmi_codec_complete(struct device *dev) { struct hdac_ext_device *edev = to_hda_ext_device(dev); struct hdac_hdmi_priv *hdmi = edev->private_data; struct hdac_hdmi_pin *pin; struct hdac_device *hdac = &edev->hdac; - struct hdac_bus *bus = hdac->bus; - int err; - unsigned long timeout; + + /* Power up afg */ + snd_hdac_codec_read(hdac, hdac->afg, 0, AC_VERB_SET_POWER_STATE, + AC_PWRST_D0); hdac_hdmi_skl_enable_all_pins(&edev->hdac); hdac_hdmi_skl_enable_dp12(&edev->hdac); - /* Power up afg */ - if (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D0)) { - - snd_hdac_codec_write(hdac, hdac->afg, 0, - AC_VERB_SET_POWER_STATE, AC_PWRST_D0); - - /* Wait till power state is set to D0 */ - timeout = jiffies + msecs_to_jiffies(1000); - while (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D0) - && time_before(jiffies, timeout)) { - msleep(50); - } - } - /* * As the ELD notify callback request is not entertained while the * device is in suspend state. Need to manually check detection of @@ -1455,18 +1462,10 @@ static void hdmi_codec_complete(struct device *dev) list_for_each_entry(pin, &hdmi->pin_list, head) hdac_hdmi_present_sense(pin, 1); - /* - * Codec power is turned ON during controller resume. - * Turn it OFF here - */ - err = snd_hdac_display_power(bus, false); - if (err < 0) { - dev_err(bus->dev, - "Cannot turn OFF display power on i915, err: %d\n", - err); - } + pm_runtime_put_sync(&edev->hdac.dev); } #else +#define hdmi_codec_prepare NULL #define hdmi_codec_complete NULL #endif @@ -1557,7 +1556,6 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) struct hdac_ext_device *edev = to_hda_ext_device(dev); struct hdac_device *hdac = &edev->hdac; struct hdac_bus *bus = hdac->bus; - unsigned long timeout; int err; dev_dbg(dev, "Enter: %s\n", __func__); @@ -1566,20 +1564,15 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) if (!bus) return 0; - /* Power down afg */ - if (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D3)) { - snd_hdac_codec_write(hdac, hdac->afg, 0, - AC_VERB_SET_POWER_STATE, AC_PWRST_D3); - - /* Wait till power state is set to D3 */ - timeout = jiffies + msecs_to_jiffies(1000); - while (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D3) - && time_before(jiffies, timeout)) { - - msleep(50); - } - } - + /* + * Power down afg. + * codec_read is preferred over codec_write to set the power state. + * This way verb is send to set the power state and response + * is received. So setting power state is ensured without using loop + * to read the state. + */ + snd_hdac_codec_read(hdac, hdac->afg, 0, AC_VERB_SET_POWER_STATE, + AC_PWRST_D3); err = snd_hdac_display_power(bus, false); if (err < 0) { dev_err(bus->dev, "Cannot turn on display power on i915\n"); @@ -1612,9 +1605,8 @@ static int hdac_hdmi_runtime_resume(struct device *dev) hdac_hdmi_skl_enable_dp12(&edev->hdac); /* Power up afg */ - if (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D0)) - snd_hdac_codec_write(hdac, hdac->afg, 0, - AC_VERB_SET_POWER_STATE, AC_PWRST_D0); + snd_hdac_codec_read(hdac, hdac->afg, 0, AC_VERB_SET_POWER_STATE, + AC_PWRST_D0); return 0; } @@ -1625,6 +1617,7 @@ static int hdac_hdmi_runtime_resume(struct device *dev) static const struct dev_pm_ops hdac_hdmi_pm = { SET_RUNTIME_PM_OPS(hdac_hdmi_runtime_suspend, hdac_hdmi_runtime_resume, NULL) + .prepare = hdmi_codec_prepare, .complete = hdmi_codec_complete, }; From af037412629d8549e04039a57cf99a59b6e7a01b Mon Sep 17 00:00:00 2001 From: "Subhransu S. Prusty" Date: Fri, 1 Apr 2016 13:36:27 +0530 Subject: [PATCH 019/181] ASoC: Intel: Skylake: Fix to turn OFF codec power when entering S3 Signed-off-by: Subhransu S. Prusty Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 07d9bc1cf3cb..3982f5536f2d 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -222,6 +222,7 @@ static int skl_suspend(struct device *dev) struct hdac_ext_bus *ebus = pci_get_drvdata(pci); struct skl *skl = ebus_to_skl(ebus); struct hdac_bus *bus = ebus_to_hbus(ebus); + int ret = 0; /* * Do not suspend if streams which are marked ignore suspend are @@ -232,10 +233,20 @@ static int skl_suspend(struct device *dev) enable_irq_wake(bus->irq); pci_save_state(pci); pci_disable_device(pci); - return 0; } else { - return _skl_suspend(ebus); + ret = _skl_suspend(ebus); + if (ret < 0) + return ret; } + + if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) { + ret = snd_hdac_display_power(bus, false); + if (ret < 0) + dev_err(bus->dev, + "Cannot turn OFF display power on i915\n"); + } + + return ret; } static int skl_resume(struct device *dev) From 338d51889851cb2ac900d2ec75c8185afcde8caf Mon Sep 17 00:00:00 2001 From: Andy Gross Date: Fri, 1 Apr 2016 15:00:25 -0500 Subject: [PATCH 020/181] Revert "dts: msm8974: Add blsp2_bam dma node" Revert this commit to fix regressions on non-dragonboard MSM8974 boards. This will be put back in after the correct fixes to the bam driver are accepted that allow remote processor control of the main control registers. This reverts commit 62bc8179222372624fd8a52b88327b962614d7b2. Signed-off-by: Andy Gross --- arch/arm/boot/dts/qcom-msm8974.dtsi | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi index ef5330578431..d7eef2515deb 100644 --- a/arch/arm/boot/dts/qcom-msm8974.dtsi +++ b/arch/arm/boot/dts/qcom-msm8974.dtsi @@ -1,6 +1,6 @@ /dts-v1/; -#include +#include #include #include "skeleton.dtsi" @@ -479,16 +479,6 @@ interrupt-controller; #interrupt-cells = <4>; }; - - blsp2_dma: dma-controller@f9944000 { - compatible = "qcom,bam-v1.4.0"; - reg = <0xf9944000 0x19000>; - interrupts = ; - clocks = <&gcc GCC_BLSP2_AHB_CLK>; - clock-names = "bam_clk"; - #dma-cells = <1>; - qcom,ee = <0>; - }; }; smd { From 10c0f0e92f019ab8d0c17da3696e35b0eef4ec16 Mon Sep 17 00:00:00 2001 From: Andy Gross Date: Fri, 1 Apr 2016 15:02:06 -0500 Subject: [PATCH 021/181] Revert "dts: msm8974: Add dma channels for blsp2_i2c1 node" Revert this commit to fix regressions on non-dragonboard MSM8974 boards. This will be put back in after the correct fixes to the bam driver are accepted that allow remote processor control of the main control registers. This reverts commit 0a5d0f85bba61d8643d78869c7c4214d6c2a7ce6. Signed-off-by: Andy Gross --- arch/arm/boot/dts/qcom-msm8974.dtsi | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi index d7eef2515deb..8193139d0d87 100644 --- a/arch/arm/boot/dts/qcom-msm8974.dtsi +++ b/arch/arm/boot/dts/qcom-msm8974.dtsi @@ -460,8 +460,6 @@ clock-names = "core", "iface"; #address-cells = <1>; #size-cells = <0>; - dmas = <&blsp2_dma 20>, <&blsp2_dma 21>; - dma-names = "tx", "rx"; }; spmi_bus: spmi@fc4cf000 { From b8af8b1d80db13dd4f5e5a3698180bd9c14aee03 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 6 Apr 2016 14:36:06 +0300 Subject: [PATCH 022/181] ASoC: Intel: sst: fix a loop timeout in sst_hsw_stream_reset() In the original code we ended the loop with tries set to -1 instead of zero. Signed-off-by: Dan Carpenter Signed-off-by: Mark Brown --- sound/soc/intel/haswell/sst-haswell-ipc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/intel/haswell/sst-haswell-ipc.c b/sound/soc/intel/haswell/sst-haswell-ipc.c index ac60f1301e21..91565229d074 100644 --- a/sound/soc/intel/haswell/sst-haswell-ipc.c +++ b/sound/soc/intel/haswell/sst-haswell-ipc.c @@ -1345,7 +1345,7 @@ int sst_hsw_stream_reset(struct sst_hsw *hsw, struct sst_hsw_stream *stream) return 0; /* wait for pause to complete before we reset the stream */ - while (stream->running && tries--) + while (stream->running && --tries) msleep(1); if (!tries) { dev_err(hsw->dev, "error: reset stream %d still running\n", From c783e6fd7fe4d34f0231d0d8da36497404aa6d93 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Fri, 1 Apr 2016 17:53:05 -0500 Subject: [PATCH 023/181] ARM: OMAP: DRA7: wakeupgen: Skip SAR save for wakeupgen DRA7 has no SAR region for automated save and restore of wakeupgen, which does not make real since the SoC really does not do legacy OFF mode anymore. Further wakeupgen should never loose context in CSWR retention mode for MPU domain on DRA7 since that is the deepest state we will enter. So, just skip, instead of oopsing as follows while attemptint to enter suspend on BeagleBoard-X15. [ 55.589771] Unable to handle kernel paging request at virtual address 00002684 [ 55.589771] pgd = ec69c000 [...] [ 55.589771] [] (irq_notifier) from [] (notifier_call_chain+0x4c/0x8c) [ 55.589771] [] (notifier_call_chain) from [] (cpu_cluster_pm_enter+0x2c/0x78) [ 55.589771] [] (cpu_cluster_pm_enter) from [] (syscore_suspend+0xb8/0x31c) [ 55.589771] [] (syscore_suspend) from [] (suspend_devices_and_enter+0x308/0x9e4) [ 55.589771] [] (suspend_devices_and_enter) from [] (pm_suspend+0x640/0x75c) [ 55.589771] [] (pm_suspend) from [] (state_store+0x64/0xb8) [ 55.589771] [] (state_store) from [] (kernfs_fop_write+0xc0/0x1bc) [ 55.589771] [] (kernfs_fop_write) from [] (__vfs_write+0x1c/0xd8) [ 55.589771] [] (__vfs_write) from [] (vfs_write+0x90/0x16c) [ 55.589771] [] (vfs_write) from [] (SyS_write+0x44/0x9c) [ 55.589771] [] (SyS_write) from [] (ret_fast_syscall+0x0/0x1c) [...] Signed-off-by: Nishanth Menon Tested-by: Keerthy Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/omap-wakeupgen.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index f397bd6bd6e3..2c04f2741476 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -274,6 +274,10 @@ static inline void omap5_irq_save_context(void) */ static void irq_save_context(void) { + /* DRA7 has no SAR to save */ + if (soc_is_dra7xx()) + return; + if (!sar_base) sar_base = omap4_get_sar_ram_base(); @@ -290,6 +294,9 @@ static void irq_sar_clear(void) { u32 val; u32 offset = SAR_BACKUP_STATUS_OFFSET; + /* DRA7 has no SAR to save */ + if (soc_is_dra7xx()) + return; if (soc_is_omap54xx()) offset = OMAP5_SAR_BACKUP_STATUS_OFFSET; From ec490f6f600f93236f1ad439b9809de563343b2c Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Fri, 1 Apr 2016 17:53:06 -0500 Subject: [PATCH 024/181] ARM: OMAP: DRA7: Provide proper class to omap2_set_globals_tap When commit 06c2d368fc36 ("ARM: OMAP: DRA7: Make use of omap_revision information for soc_is* calls") introduced SoC check using omap_revision, it missed providing DRA7 as class for initializing the omap_version variable. Without doing this, soc_is_dra7xx() will fail and as a result, omap4_pm_init_early never initializes the dra7 erratum for CPU power state. This causes the suspend path to fail on DRA7 devices. Fixes: 06c2d368fc36 ("ARM: OMAP: DRA7: Make use of omap_revision information for soc_is* calls") Signed-off-by: Nishanth Menon Tested-by: Keerthy Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/io.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 3c87e40650cf..2b86b25bcb83 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -736,7 +736,8 @@ void __init omap5_init_late(void) #ifdef CONFIG_SOC_DRA7XX void __init dra7xx_init_early(void) { - omap2_set_globals_tap(-1, OMAP2_L4_IO_ADDRESS(DRA7XX_TAP_BASE)); + omap2_set_globals_tap(DRA7XX_CLASS, + OMAP2_L4_IO_ADDRESS(DRA7XX_TAP_BASE)); omap2_set_globals_prcm_mpu(OMAP2_L4_IO_ADDRESS(OMAP54XX_PRCM_MPU_BASE)); omap2_control_base_init(); omap4_pm_init_early(); From eea08802f586acd6aef377d1b4a541821013cc0b Mon Sep 17 00:00:00 2001 From: Keerthy Date: Mon, 4 Apr 2016 11:07:15 +0530 Subject: [PATCH 025/181] ARM: dts: dra7: Correct clock tree for sys_32k_ck This is w.r.t J6/J6eco: 32clk is pseudo (erratum i856) - clock source. Errata i856 for the AM572x (DRA7xx) points out that the 32.768KHz external crystal is not enabled at power up. Instead the CPU falls back to using an emulation for the 32KHz clock which is SYSCLK1/610. SYSCLK1 is usually 20MHz on boards so far (which gives an emulated frequency of 32.786KHz) Modelling the same in device tree. Acked-by: Tero Kristo Signed-off-by: Keerthy Signed-off-by: Lokesh Vutla Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/dra7xx-clocks.dtsi | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index d0bae06b7eb7..ef2164a99d0f 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -98,12 +98,20 @@ clock-frequency = <32768>; }; - sys_32k_ck: sys_32k_ck { + sys_clk32_crystal_ck: sys_clk32_crystal_ck { #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <32768>; }; + sys_clk32_pseudo_ck: sys_clk32_pseudo_ck { + #clock-cells = <0>; + compatible = "fixed-factor-clock"; + clocks = <&sys_clkin1>; + clock-mult = <1>; + clock-div = <610>; + }; + virt_12000000_ck: virt_12000000_ck { #clock-cells = <0>; compatible = "fixed-clock"; @@ -2170,4 +2178,12 @@ ti,bit-shift = <22>; reg = <0x0558>; }; + + sys_32k_ck: sys_32k_ck { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clk32_crystal_ck>, <&sys_clk32_pseudo_ck>, <&sys_clk32_pseudo_ck>, <&sys_clk32_pseudo_ck>; + ti,bit-shift = <8>; + reg = <0x6c4>; + }; }; From 571afb4c8a4bbe88541364e7f6827340562f2736 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Fri, 1 Apr 2016 17:53:07 -0500 Subject: [PATCH 026/181] ARM: OMAP: Catch callers of revision information prior to it being populated omap_rev is used to detect various SoC types, however any misuse of the usage by invoking it earlier than it being populated will result in invalid results. Lets flag them as early as possible to prevent unintended side effects taking place. We get 0 if it is uninitialized and -1 when detection is done using device tree (as the case was for DRA7 as the case was prior to commit 06c2d368fc36 ("ARM: OMAP: DRA7: Make use of omap_revision information for soc_is* calls") Signed-off-by: Nishanth Menon Tested-by: Keerthy Signed-off-by: Tony Lindgren --- arch/arm/mach-omap1/id.c | 1 + arch/arm/mach-omap2/id.c | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/arm/mach-omap1/id.c b/arch/arm/mach-omap1/id.c index 52de382fc804..bfabc065d331 100644 --- a/arch/arm/mach-omap1/id.c +++ b/arch/arm/mach-omap1/id.c @@ -65,6 +65,7 @@ static struct omap_id omap_ids[] __initdata = { unsigned int omap_rev(void) { + WARN_ON_ONCE(!omap_revision || omap_revision == -1); return omap_revision; } EXPORT_SYMBOL(omap_rev); diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index d85c24918c17..75fb6c006e86 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -46,6 +46,7 @@ u32 omap_features; unsigned int omap_rev(void) { + WARN_ON_ONCE(!omap_revision || omap_revision == -1); return omap_revision; } EXPORT_SYMBOL(omap_rev); From 1cbabcb9807e31e87ef3a12af76ea025ceb582d3 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Tue, 5 Apr 2016 16:44:12 -0500 Subject: [PATCH 027/181] ARM: DRA7: clockdomain: Implement timer workaround for errata i874 Errata Title: i874: TIMER5/6/7/8 interrupts not propagated Description: When TIMER5, TIMER6, TIMER7, or TIMER8 clocks are enabled (CM_IPU_TIMER5/6/7/8_CLKCTRL[0:1]MODULEMODE=0x2:ENABLE) and the CD-IPU is in HW_AUTO mode (CM_IPU_CLKSTCTRL[0:1]CLKTRCTRL=0x3:HW_AUTO) the corresponding TIMER will continue counting, but enabled interrupts will not be propagated to the destinations (MPU, DSP, etc) in the SoC until the TIMER registers are accessed from the CPUs (MPU, DSP etc.). This can result in missed timer interrupts. Workaround: In order for TIMER5/6/7/8 interrupts to be propagated and serviced correctly the CD_IPU domain should be set to SW_WKUP mode (CM_IPU_CLKSTCTRL[0:1]CLKTRCTRL=0x2:SW_WKUP). The above workaround is achieved by switching the IPU clockdomain flags from HWSUP_SWSUP to SWSUP only. Signed-off-by: Keerthy Signed-off-by: Suman Anna Signed-off-by: Paul Walmsley --- arch/arm/mach-omap2/clockdomains7xx_data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/clockdomains7xx_data.c b/arch/arm/mach-omap2/clockdomains7xx_data.c index 7581e036bda6..ef9ed36e8a61 100644 --- a/arch/arm/mach-omap2/clockdomains7xx_data.c +++ b/arch/arm/mach-omap2/clockdomains7xx_data.c @@ -461,7 +461,7 @@ static struct clockdomain ipu_7xx_clkdm = { .cm_inst = DRA7XX_CM_CORE_AON_IPU_INST, .clkdm_offs = DRA7XX_CM_CORE_AON_IPU_IPU_CDOFFS, .dep_bit = DRA7XX_IPU_STATDEP_SHIFT, - .flags = CLKDM_CAN_HWSUP_SWSUP, + .flags = CLKDM_CAN_SWSUP, }; static struct clockdomain mpu1_7xx_clkdm = { From f0c8e1d9c4f473dfc771a613b602f1841afe8f8b Mon Sep 17 00:00:00 2001 From: "Subhransu S. Prusty" Date: Tue, 12 Apr 2016 10:31:23 +0530 Subject: [PATCH 028/181] ASoC: Intel: Skylake: Fix ibs/obs calc for non-integral sampling rates FW expects sampling rate rounded up to next higher integer value when calculating ibs/obs. For example for 44.1k, it should be rounded up to 45 to calculate ibs/obs. Signed-off-by: Subhransu S. Prusty Signed-off-by: Vinod Koul Signed-off-by: Mark Brown --- sound/soc/intel/skylake/skl-topology.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index 5a85f3a4699b..cdb78b7e5a14 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -239,6 +239,7 @@ static void skl_tplg_update_buffer_size(struct skl_sst *ctx, { int multiplier = 1; struct skl_module_fmt *in_fmt, *out_fmt; + int in_rate, out_rate; /* Since fixups is applied to pin 0 only, ibs, obs needs @@ -249,15 +250,24 @@ static void skl_tplg_update_buffer_size(struct skl_sst *ctx, if (mcfg->m_type == SKL_MODULE_TYPE_SRCINT) multiplier = 5; - mcfg->ibs = (in_fmt->s_freq / 1000) * - (mcfg->in_fmt->channels) * - (mcfg->in_fmt->bit_depth >> 3) * - multiplier; - mcfg->obs = (mcfg->out_fmt->s_freq / 1000) * - (mcfg->out_fmt->channels) * - (mcfg->out_fmt->bit_depth >> 3) * - multiplier; + if (in_fmt->s_freq % 1000) + in_rate = (in_fmt->s_freq / 1000) + 1; + else + in_rate = (in_fmt->s_freq / 1000); + + mcfg->ibs = in_rate * (mcfg->in_fmt->channels) * + (mcfg->in_fmt->bit_depth >> 3) * + multiplier; + + if (mcfg->out_fmt->s_freq % 1000) + out_rate = (mcfg->out_fmt->s_freq / 1000) + 1; + else + out_rate = (mcfg->out_fmt->s_freq / 1000); + + mcfg->obs = out_rate * (mcfg->out_fmt->channels) * + (mcfg->out_fmt->bit_depth >> 3) * + multiplier; } static int skl_tplg_update_be_blob(struct snd_soc_dapm_widget *w, From b0b6d123f5df189d7d3a62d450e5f5c33ad614d8 Mon Sep 17 00:00:00 2001 From: Yakir Yang Date: Mon, 14 Mar 2016 11:09:15 +0800 Subject: [PATCH 029/181] i2c: rk3x: add support for rk3228 Enable the I2C core for this SoC. Signed-off-by: Yakir Yang Reviewed-by: Heiko Stuebner Acked-by: Rob Herring Signed-off-by: Wolfram Sang --- Documentation/devicetree/bindings/i2c/i2c-rk3x.txt | 4 ++-- drivers/i2c/busses/i2c-rk3x.c | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt b/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt index f0d71bc52e64..0b4a85fe2d86 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt @@ -6,8 +6,8 @@ RK3xxx SoCs. Required properties : - reg : Offset and length of the register set for the device - - compatible : should be "rockchip,rk3066-i2c", "rockchip,rk3188-i2c" or - "rockchip,rk3288-i2c". + - compatible : should be "rockchip,rk3066-i2c", "rockchip,rk3188-i2c", + "rockchip,rk3228-i2c" or "rockchip,rk3288-i2c". - interrupts : interrupt number - clocks : parent clock diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index 9096d17beb5b..3dcc5f3f26cb 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -855,6 +855,7 @@ static struct rk3x_i2c_soc_data soc_data[3] = { static const struct of_device_id rk3x_i2c_match[] = { { .compatible = "rockchip,rk3066-i2c", .data = (void *)&soc_data[0] }, { .compatible = "rockchip,rk3188-i2c", .data = (void *)&soc_data[1] }, + { .compatible = "rockchip,rk3228-i2c", .data = (void *)&soc_data[2] }, { .compatible = "rockchip,rk3288-i2c", .data = (void *)&soc_data[2] }, {}, }; From 8574ad7800ad298dc7f184f12b454a67fa3dd839 Mon Sep 17 00:00:00 2001 From: Tanmay Jagdale Date: Mon, 11 Apr 2016 18:01:26 +0530 Subject: [PATCH 030/181] i2c: xlp9xx: add support for Broadcom Vulcan The Broadcom Vulcan ARM64 processor uses the same I2C controller present on the Broadcom XLP9xx/5xx MIPS processor family. Updated the Kconfig by adding ARCH_VULCAN option. Signed-off-by: Tanmay Jagdale Signed-off-by: Wolfram Sang --- drivers/i2c/busses/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index faa8e6821fea..0967e1a5b3a2 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -975,10 +975,10 @@ config I2C_XLR config I2C_XLP9XX tristate "XLP9XX I2C support" - depends on CPU_XLP || COMPILE_TEST + depends on CPU_XLP || ARCH_VULCAN || COMPILE_TEST help This driver enables support for the on-chip I2C interface of - the Broadcom XLP9xx/XLP5xx MIPS processors. + the Broadcom XLP9xx/XLP5xx MIPS and Vulcan ARM64 processors. This driver can also be built as a module. If so, the module will be called i2c-xlp9xx. From abaa7b0c1286ca1610a6dfa079e1d2e27dca1f25 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 8 Apr 2016 15:41:08 +0300 Subject: [PATCH 031/181] i2c: ismt: Add Intel DNV PCI ID Intel DNV has the same iSMT SMBus host controller than Intel Avoton. Add DNV PCI ID to the list of supported devices. Signed-off-by: Mika Westerberg Acked-by: Andy Shevchenko Acked-by: Neil Horman Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-ismt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index 7ba795b24e75..1c8707710098 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -75,6 +75,7 @@ /* PCI DIDs for the Intel SMBus Message Transport (SMT) Devices */ #define PCI_DEVICE_ID_INTEL_S1200_SMT0 0x0c59 #define PCI_DEVICE_ID_INTEL_S1200_SMT1 0x0c5a +#define PCI_DEVICE_ID_INTEL_DNV_SMT 0x19ac #define PCI_DEVICE_ID_INTEL_AVOTON_SMT 0x1f15 #define ISMT_DESC_ENTRIES 2 /* number of descriptor entries */ @@ -180,6 +181,7 @@ struct ismt_priv { static const struct pci_device_id ismt_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_S1200_SMT0) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_S1200_SMT1) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMT) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AVOTON_SMT) }, { 0, } }; From fc26fe9c3869f02dd9dc54ff3a45c6d9d4bbbdfa Mon Sep 17 00:00:00 2001 From: Alexander Kurz Date: Mon, 11 Apr 2016 10:20:46 +0200 Subject: [PATCH 032/181] ARM: mach-imx: sdhci-esdhc-imx: initialize DMA mask With commit 7b91369b4655 ("mmc: sdhci: Set DMA mask when adding host") DMA access got disabled for device drivers with zero DMA mask property. sdhci-esdhc-imx got blocked from DMA access by this. Hence: initialize the DMA mask to enable access again. Signed-off-by: Alexander Kurz Signed-off-by: Shawn Guo --- arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c index a5edd7d60266..3d039ef021e0 100644 --- a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c +++ b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c @@ -71,6 +71,7 @@ struct platform_device *__init imx_add_sdhci_esdhc_imx( if (!pdata) pdata = &default_esdhc_pdata; - return imx_add_platform_device(data->devid, data->id, res, - ARRAY_SIZE(res), pdata, sizeof(*pdata)); + return imx_add_platform_device_dmamask(data->devid, data->id, res, + ARRAY_SIZE(res), pdata, sizeof(*pdata), + DMA_BIT_MASK(32)); } From d9c9f3b809d2bb0356f013e88d10730eafab5346 Mon Sep 17 00:00:00 2001 From: James Liao Date: Tue, 12 Apr 2016 16:34:30 +0800 Subject: [PATCH 033/181] Revert "soc: mediatek: SCPSYS: Fix double enabling of regulators" This reverts commit cc8ed76938b5cf6a54ab3d60edabaf808dc960d1 ("soc: mediatek: SCPSYS: Fix double enabling of regulators") [1]. This patch fixes mt8173-evb failing boot issue. With commit [1], genpd state will not sync to real power domain state. So some resources such as clocks and regulators may stay in a wrong state. There is no regulator double enabling issue on mainline kernel, so we can refert commit [1] safely. Signed-off-by: James Liao Signed-off-by: Matthias Brugger --- drivers/soc/mediatek/mtk-scpsys.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/soc/mediatek/mtk-scpsys.c b/drivers/soc/mediatek/mtk-scpsys.c index 57e781c71e67..837effe19907 100644 --- a/drivers/soc/mediatek/mtk-scpsys.c +++ b/drivers/soc/mediatek/mtk-scpsys.c @@ -491,13 +491,14 @@ static int scpsys_probe(struct platform_device *pdev) genpd->dev_ops.active_wakeup = scpsys_active_wakeup; /* - * With CONFIG_PM disabled turn on all domains to make the - * hardware usable. + * Initially turn on all domains to make the domains usable + * with !CONFIG_PM and to get the hardware in sync with the + * software. The unused domains will be switched off during + * late_init time. */ - if (!IS_ENABLED(CONFIG_PM)) - genpd->power_on(genpd); + genpd->power_on(genpd); - pm_genpd_init(genpd, NULL, true); + pm_genpd_init(genpd, NULL, false); } /* From e7e0c3e26587749b62d17b9dd0532874186c77f7 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Sun, 3 Apr 2016 16:15:00 -0300 Subject: [PATCH 034/181] [media] videobuf2-core: Check user space planes array in dqbuf The number of planes in videobuf2 is specific to a buffer. In order to verify that the planes array provided by the user is long enough, a new vb2_buf_op is required. Call __verify_planes_array() when the dequeued buffer is known. Return an error to the caller if there was one, otherwise remove the buffer from the done list. Signed-off-by: Sakari Ailus Acked-by: Hans Verkuil Cc: stable@vger.kernel.org # for v4.4 and later Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/videobuf2-core.c | 10 +++++----- include/media/videobuf2-core.h | 4 ++++ 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index 5d016f496e0e..2169544883e8 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -1645,7 +1645,7 @@ static int __vb2_wait_for_done_vb(struct vb2_queue *q, int nonblocking) * Will sleep if required for nonblocking == false. */ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb, - int nonblocking) + void *pb, int nonblocking) { unsigned long flags; int ret; @@ -1666,10 +1666,10 @@ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb, /* * Only remove the buffer from done_list if v4l2_buffer can handle all * the planes. - * Verifying planes is NOT necessary since it already has been checked - * before the buffer is queued/prepared. So it can never fail. */ - list_del(&(*vb)->done_entry); + ret = call_bufop(q, verify_planes_array, *vb, pb); + if (!ret) + list_del(&(*vb)->done_entry); spin_unlock_irqrestore(&q->done_lock, flags); return ret; @@ -1748,7 +1748,7 @@ int vb2_core_dqbuf(struct vb2_queue *q, unsigned int *pindex, void *pb, struct vb2_buffer *vb = NULL; int ret; - ret = __vb2_get_done_vb(q, &vb, nonblocking); + ret = __vb2_get_done_vb(q, &vb, pb, nonblocking); if (ret < 0) return ret; diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 8a0f55b6c2ba..5342ff4d748f 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -375,6 +375,9 @@ struct vb2_ops { /** * struct vb2_ops - driver-specific callbacks * + * @verify_planes_array: Verify that a given user space structure contains + * enough planes for the buffer. This is called + * for each dequeued buffer. * @fill_user_buffer: given a vb2_buffer fill in the userspace structure. * For V4L2 this is a struct v4l2_buffer. * @fill_vb2_buffer: given a userspace structure, fill in the vb2_buffer. @@ -384,6 +387,7 @@ struct vb2_ops { * the vb2_buffer struct. */ struct vb2_buf_ops { + int (*verify_planes_array)(struct vb2_buffer *vb, const void *pb); void (*fill_user_buffer)(struct vb2_buffer *vb, void *pb); int (*fill_vb2_buffer)(struct vb2_buffer *vb, const void *pb, struct vb2_plane *planes); From 2c1f6951a8a82e6de0d82b1158b5e493fc6c54ab Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Sun, 3 Apr 2016 16:31:03 -0300 Subject: [PATCH 035/181] [media] videobuf2-v4l2: Verify planes array in buffer dequeueing When a buffer is being dequeued using VIDIOC_DQBUF IOCTL, the exact buffer which will be dequeued is not known until the buffer has been removed from the queue. The number of planes is specific to a buffer, not to the queue. This does lead to the situation where multi-plane buffers may be requested and queued with n planes, but VIDIOC_DQBUF IOCTL may be passed an argument struct with fewer planes. __fill_v4l2_buffer() however uses the number of planes from the dequeued videobuf2 buffer, overwriting kernel memory (the m.planes array allocated in video_usercopy() in v4l2-ioctl.c) if the user provided fewer planes than the dequeued buffer had. Oops! Fixes: b0e0e1f83de3 ("[media] media: videobuf2: Prepare to divide videobuf2") Signed-off-by: Sakari Ailus Acked-by: Hans Verkuil Cc: stable@vger.kernel.org # for v4.4 and later Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/videobuf2-v4l2.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/media/v4l2-core/videobuf2-v4l2.c b/drivers/media/v4l2-core/videobuf2-v4l2.c index 91f552124050..8da7470ca364 100644 --- a/drivers/media/v4l2-core/videobuf2-v4l2.c +++ b/drivers/media/v4l2-core/videobuf2-v4l2.c @@ -74,6 +74,11 @@ static int __verify_planes_array(struct vb2_buffer *vb, const struct v4l2_buffer return 0; } +static int __verify_planes_array_core(struct vb2_buffer *vb, const void *pb) +{ + return __verify_planes_array(vb, pb); +} + /** * __verify_length() - Verify that the bytesused value for each plane fits in * the plane length and that the data offset doesn't exceed the bytesused value. @@ -437,6 +442,7 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb, } static const struct vb2_buf_ops v4l2_buf_ops = { + .verify_planes_array = __verify_planes_array_core, .fill_user_buffer = __fill_v4l2_buffer, .fill_vb2_buffer = __fill_vb2_buffer, .copy_timestamp = __copy_timestamp, From a2abf904a6b594b93c0e73a36c98ecbaa7388463 Mon Sep 17 00:00:00 2001 From: Franklin S Cooper Jr Date: Thu, 10 Mar 2016 17:56:38 -0600 Subject: [PATCH 036/181] ARM: dts: am33xx: Fix GPMC dma properties This patch updates the GPMC's DT DMA property to reflect the updated eDMA bindings. Fixes: b5e509066074 ("ARM: DTS: am33xx: Use the new DT bindings for the eDMA3") Signed-off-by: Franklin S Cooper Jr Acked-by: Roger Quadros Acked-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am33xx.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 55ca9c7dcf6a..0467846b4cc3 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -860,7 +860,7 @@ ti,no-idle-on-init; reg = <0x50000000 0x2000>; interrupts = <100>; - dmas = <&edma 52>; + dmas = <&edma 52 0>; dma-names = "rxtx"; gpmc,num-cs = <7>; gpmc,num-waitpins = <2>; From 883cbc901b570625f54250a37b008d3635f1fbda Mon Sep 17 00:00:00 2001 From: Franklin S Cooper Jr Date: Thu, 10 Mar 2016 17:56:39 -0600 Subject: [PATCH 037/181] ARM: dts: am437x: Fix GPMC dma properties This patch updates the GPMC's DT DMA property to reflect the updated eDMA bindings. Fixes: cce1ee000187 ("ARM: DTS: am437x: Use the new DT bindings for the eDMA3") Signed-off-by: Franklin S Cooper Jr Acked-by: Roger Quadros Acked-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am4372.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index 344b861a55a5..ba580a9da390 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -884,7 +884,7 @@ gpmc: gpmc@50000000 { compatible = "ti,am3352-gpmc"; ti,hwmods = "gpmc"; - dmas = <&edma 52>; + dmas = <&edma 52 0>; dma-names = "rxtx"; clocks = <&l3s_gclk>; clock-names = "fck"; From a1def45365594dd16be0d8cc52b0d5a6a79d6ae6 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Wed, 6 Apr 2016 17:32:38 +0300 Subject: [PATCH 038/181] ARM: dts: am57xx-beagle-x15: remove extcon_usb1 USB1 controller is hardwired to be used as Host only port so we don't need to check ID pin state and can get rid of extcon_usb1. This also reduces USB1 controller's and so eSATA power's dependency with EXTCON. This fixes eSATA port with multi_v7_defconfig. Cc: Franklin S Cooper Jr. Cc: Vagrant Cascadian Signed-off-by: Roger Quadros Tested-by: Franklin S Cooper Jr. [tony@atomide.com: updated to describe what it fixes] Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am57xx-beagle-x15.dts | 17 ----------------- 1 file changed, 17 deletions(-) diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts index 0a5fc5d02ce2..4168eb9dd369 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -99,13 +99,6 @@ #cooling-cells = <2>; }; - extcon_usb1: extcon_usb1 { - compatible = "linux,extcon-usb-gpio"; - id-gpio = <&gpio7 25 GPIO_ACTIVE_HIGH>; - pinctrl-names = "default"; - pinctrl-0 = <&extcon_usb1_pins>; - }; - hdmi0: connector { compatible = "hdmi-connector"; label = "hdmi"; @@ -349,12 +342,6 @@ >; }; - extcon_usb1_pins: extcon_usb1_pins { - pinctrl-single,pins = < - DRA7XX_CORE_IOPAD(0x37ec, PIN_INPUT_PULLUP | MUX_MODE14) /* uart1_rtsn.gpio7_25 */ - >; - }; - tpd12s015_pins: pinmux_tpd12s015_pins { pinctrl-single,pins = < DRA7XX_CORE_IOPAD(0x37b0, PIN_OUTPUT | MUX_MODE14) /* gpio7_10 CT_CP_HPD */ @@ -706,10 +693,6 @@ pinctrl-0 = <&usb1_pins>; }; -&omap_dwc3_1 { - extcon = <&extcon_usb1>; -}; - &omap_dwc3_2 { extcon = <&extcon_usb2>; }; From 1560d15861769c23fd981e2d60dc7fd790b21e1e Mon Sep 17 00:00:00 2001 From: Dave Gerlach Date: Wed, 13 Apr 2016 20:49:48 -0500 Subject: [PATCH 039/181] ARM: OMAP3: Fix external abort on 36xx waking from off mode idle Depending on timing during the resume path from off mode on 36xx, we may see external aborts. These seem to be caused by the following: - OMAP3 Advisory 1.62 "MPU Cannot Exit from Standby" says we need to disable intc autoidle before WFI - DM3730 Advisory 1.106 "MPU Leaves MSTANDBY State Before IDLEREQ of Interrupt Controller is Released" says we need to wait before accessing intc omap3_intc_resume_idle restores the intc autoidle for all resume paths, however in the resume path from off mode only it is also being restored by omap_intc_restore_context before this call to omap3_intc_resume_idle happens. The second restore of the intc autoidle in this path is what appears to be causing the external abort so for the off mode resume path let's rely on omap_intc_restore_context to restore intc autoidle, and for all other paths let omap3_intc_resume_idle handle it as it is now. Signed-off-by: Dave Gerlach Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/pm34xx.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 2dbd3785ee6f..d44e0e2f1106 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -198,7 +198,6 @@ void omap_sram_idle(void) int per_next_state = PWRDM_POWER_ON; int core_next_state = PWRDM_POWER_ON; int per_going_off; - int core_prev_state; u32 sdrc_pwr = 0; mpu_next_state = pwrdm_read_next_pwrst(mpu_pwrdm); @@ -278,16 +277,20 @@ void omap_sram_idle(void) sdrc_write_reg(sdrc_pwr, SDRC_POWER); /* CORE */ - if (core_next_state < PWRDM_POWER_ON) { - core_prev_state = pwrdm_read_prev_pwrst(core_pwrdm); - if (core_prev_state == PWRDM_POWER_OFF) { - omap3_core_restore_context(); - omap3_cm_restore_context(); - omap3_sram_restore_context(); - omap2_sms_restore_context(); - } + if (core_next_state < PWRDM_POWER_ON && + pwrdm_read_prev_pwrst(core_pwrdm) == PWRDM_POWER_OFF) { + omap3_core_restore_context(); + omap3_cm_restore_context(); + omap3_sram_restore_context(); + omap2_sms_restore_context(); + } else { + /* + * In off-mode resume path above, omap3_core_restore_context + * also handles the INTC autoidle restore done here so limit + * this to non-off mode resume paths so we don't do it twice. + */ + omap3_intc_resume_idle(); } - omap3_intc_resume_idle(); pwrdm_post_transition(NULL); From 54dca7015a7d6c09d34623c6ec61de30896186dd Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 15 Apr 2016 13:11:56 +0100 Subject: [PATCH 040/181] ASoC: arizona: Free speaker thermal IRQs in CODEC remove The thermal warning IRQs for the speaker are requested in CODEC probe but never freed. This patch frees them in CODEC remove. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- sound/soc/codecs/arizona.c | 12 ++++++++++++ sound/soc/codecs/arizona.h | 2 ++ sound/soc/codecs/cs47l24.c | 3 +++ sound/soc/codecs/wm5102.c | 2 ++ sound/soc/codecs/wm5110.c | 2 ++ sound/soc/codecs/wm8997.c | 2 ++ sound/soc/codecs/wm8998.c | 2 ++ 7 files changed, 25 insertions(+) diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c index 92d22a018d68..83959312f7a0 100644 --- a/sound/soc/codecs/arizona.c +++ b/sound/soc/codecs/arizona.c @@ -249,6 +249,18 @@ int arizona_init_spk(struct snd_soc_codec *codec) } EXPORT_SYMBOL_GPL(arizona_init_spk); +int arizona_free_spk(struct snd_soc_codec *codec) +{ + struct arizona_priv *priv = snd_soc_codec_get_drvdata(codec); + struct arizona *arizona = priv->arizona; + + arizona_free_irq(arizona, ARIZONA_IRQ_SPK_OVERHEAT_WARN, arizona); + arizona_free_irq(arizona, ARIZONA_IRQ_SPK_OVERHEAT, arizona); + + return 0; +} +EXPORT_SYMBOL_GPL(arizona_free_spk); + static const struct snd_soc_dapm_route arizona_mono_routes[] = { { "OUT1R", NULL, "OUT1L" }, { "OUT2R", NULL, "OUT2L" }, diff --git a/sound/soc/codecs/arizona.h b/sound/soc/codecs/arizona.h index 1ea8e4ecf8d4..ce0531b8c632 100644 --- a/sound/soc/codecs/arizona.h +++ b/sound/soc/codecs/arizona.h @@ -307,6 +307,8 @@ extern int arizona_init_spk(struct snd_soc_codec *codec); extern int arizona_init_gpio(struct snd_soc_codec *codec); extern int arizona_init_mono(struct snd_soc_codec *codec); +extern int arizona_free_spk(struct snd_soc_codec *codec); + extern int arizona_init_dai(struct arizona_priv *priv, int dai); int arizona_set_output_mode(struct snd_soc_codec *codec, int output, diff --git a/sound/soc/codecs/cs47l24.c b/sound/soc/codecs/cs47l24.c index 576087bda330..00e9b6fc1b5c 100644 --- a/sound/soc/codecs/cs47l24.c +++ b/sound/soc/codecs/cs47l24.c @@ -1108,6 +1108,9 @@ static int cs47l24_codec_remove(struct snd_soc_codec *codec) priv->core.arizona->dapm = NULL; arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, priv); + + arizona_free_spk(codec); + return 0; } diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c index a8b3e3f701f9..59fd3e8bf899 100644 --- a/sound/soc/codecs/wm5102.c +++ b/sound/soc/codecs/wm5102.c @@ -1960,6 +1960,8 @@ static int wm5102_codec_remove(struct snd_soc_codec *codec) priv->core.arizona->dapm = NULL; + arizona_free_spk(codec); + return 0; } diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c index 83ba70fe16e6..2728ac545ffe 100644 --- a/sound/soc/codecs/wm5110.c +++ b/sound/soc/codecs/wm5110.c @@ -2298,6 +2298,8 @@ static int wm5110_codec_remove(struct snd_soc_codec *codec) arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, priv); + arizona_free_spk(codec); + return 0; } diff --git a/sound/soc/codecs/wm8997.c b/sound/soc/codecs/wm8997.c index 52d766efe14f..6b0785b5a5c5 100644 --- a/sound/soc/codecs/wm8997.c +++ b/sound/soc/codecs/wm8997.c @@ -1072,6 +1072,8 @@ static int wm8997_codec_remove(struct snd_soc_codec *codec) priv->core.arizona->dapm = NULL; + arizona_free_spk(codec); + return 0; } diff --git a/sound/soc/codecs/wm8998.c b/sound/soc/codecs/wm8998.c index 012396074a8a..449f66636205 100644 --- a/sound/soc/codecs/wm8998.c +++ b/sound/soc/codecs/wm8998.c @@ -1324,6 +1324,8 @@ static int wm8998_codec_remove(struct snd_soc_codec *codec) priv->core.arizona->dapm = NULL; + arizona_free_spk(codec); + return 0; } From ab9f87c413c297cb9e7d544e0e634aaadc7fb87d Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Fri, 15 Apr 2016 13:11:57 +0100 Subject: [PATCH 041/181] ASoC: wm5102: Free compressed IRQ in CODEC remove We request one of the DSP IRQs during CODEC probe, as such we should free it during CODEC remove, this patch does so. Signed-off-by: Charles Keepax Signed-off-by: Mark Brown --- sound/soc/codecs/wm5102.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c index 59fd3e8bf899..1bae17ee8817 100644 --- a/sound/soc/codecs/wm5102.c +++ b/sound/soc/codecs/wm5102.c @@ -1955,11 +1955,14 @@ err_adsp2_codec_probe: static int wm5102_codec_remove(struct snd_soc_codec *codec) { struct wm5102_priv *priv = snd_soc_codec_get_drvdata(codec); + struct arizona *arizona = priv->core.arizona; wm_adsp2_codec_remove(&priv->core.adsp[0], codec); priv->core.arizona->dapm = NULL; + arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, priv); + arizona_free_spk(codec); return 0; From 6e1c7d6103fe7031035cec321307c6356809adf4 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 15 Apr 2016 14:06:57 +0300 Subject: [PATCH 042/181] mmc: sdhci-acpi: Reduce Baytrail eMMC/SD/SDIO hangs Baytrail eMMC/SD/SDIO host controllers have been known to hang. A change to a hardware setting has been found to reduce the occurrence of such hangs. This patch ensures the correct setting. This patch applies cleanly to v4.4+. It could go to earlier kernels also, so I will send backports to the stable list in due course. Signed-off-by: Adrian Hunter Cc: stable@vger.kernel.org # v4.4+ Signed-off-by: Ulf Hansson --- drivers/mmc/host/Kconfig | 1 + drivers/mmc/host/sdhci-acpi.c | 81 +++++++++++++++++++++++++++++++++++ 2 files changed, 82 insertions(+) diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 04feea8354cb..e657af0e95fa 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -97,6 +97,7 @@ config MMC_RICOH_MMC config MMC_SDHCI_ACPI tristate "SDHCI support for ACPI enumerated SDHCI controllers" depends on MMC_SDHCI && ACPI + select IOSF_MBI if X86 help This selects support for ACPI enumerated SDHCI controllers, identified by ACPI Compatibility ID PNP0D40 or specific diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index 6839e41c6d58..bed6a494f52c 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -41,6 +41,11 @@ #include #include +#ifdef CONFIG_X86 +#include +#include +#endif + #include "sdhci.h" enum { @@ -116,6 +121,75 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = { .ops = &sdhci_acpi_ops_int, }; +#ifdef CONFIG_X86 + +static bool sdhci_acpi_byt(void) +{ + static const struct x86_cpu_id byt[] = { + { X86_VENDOR_INTEL, 6, 0x37 }, + {} + }; + + return x86_match_cpu(byt); +} + +#define BYT_IOSF_SCCEP 0x63 +#define BYT_IOSF_OCP_NETCTRL0 0x1078 +#define BYT_IOSF_OCP_TIMEOUT_BASE GENMASK(10, 8) + +static void sdhci_acpi_byt_setting(struct device *dev) +{ + u32 val = 0; + + if (!sdhci_acpi_byt()) + return; + + if (iosf_mbi_read(BYT_IOSF_SCCEP, MBI_CR_READ, BYT_IOSF_OCP_NETCTRL0, + &val)) { + dev_err(dev, "%s read error\n", __func__); + return; + } + + if (!(val & BYT_IOSF_OCP_TIMEOUT_BASE)) + return; + + val &= ~BYT_IOSF_OCP_TIMEOUT_BASE; + + if (iosf_mbi_write(BYT_IOSF_SCCEP, MBI_CR_WRITE, BYT_IOSF_OCP_NETCTRL0, + val)) { + dev_err(dev, "%s write error\n", __func__); + return; + } + + dev_dbg(dev, "%s completed\n", __func__); +} + +static bool sdhci_acpi_byt_defer(struct device *dev) +{ + if (!sdhci_acpi_byt()) + return false; + + if (!iosf_mbi_available()) + return true; + + sdhci_acpi_byt_setting(dev); + + return false; +} + +#else + +static inline void sdhci_acpi_byt_setting(struct device *dev) +{ +} + +static inline bool sdhci_acpi_byt_defer(struct device *dev) +{ + return false; +} + +#endif + static int bxt_get_cd(struct mmc_host *mmc) { int gpio_cd = mmc_gpio_get_cd(mmc); @@ -322,6 +396,9 @@ static int sdhci_acpi_probe(struct platform_device *pdev) if (acpi_bus_get_status(device) || !device->status.present) return -ENODEV; + if (sdhci_acpi_byt_defer(dev)) + return -EPROBE_DEFER; + hid = acpi_device_hid(device); uid = device->pnp.unique_id; @@ -447,6 +524,8 @@ static int sdhci_acpi_resume(struct device *dev) { struct sdhci_acpi_host *c = dev_get_drvdata(dev); + sdhci_acpi_byt_setting(&c->pdev->dev); + return sdhci_resume_host(c->host); } @@ -470,6 +549,8 @@ static int sdhci_acpi_runtime_resume(struct device *dev) { struct sdhci_acpi_host *c = dev_get_drvdata(dev); + sdhci_acpi_byt_setting(&c->pdev->dev); + return sdhci_runtime_resume_host(c->host); } From 3d51ae172d759198b2e47e104c31a92d20d17927 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 19 Apr 2016 08:01:05 -0700 Subject: [PATCH 043/181] Revert "ARM: OMAP: Catch callers of revision information prior to it being populated" This reverts commit 571afb4c8a4bbe88541364e7f6827340562f2736. --- arch/arm/mach-omap1/id.c | 1 - arch/arm/mach-omap2/id.c | 1 - 2 files changed, 2 deletions(-) diff --git a/arch/arm/mach-omap1/id.c b/arch/arm/mach-omap1/id.c index bfabc065d331..52de382fc804 100644 --- a/arch/arm/mach-omap1/id.c +++ b/arch/arm/mach-omap1/id.c @@ -65,7 +65,6 @@ static struct omap_id omap_ids[] __initdata = { unsigned int omap_rev(void) { - WARN_ON_ONCE(!omap_revision || omap_revision == -1); return omap_revision; } EXPORT_SYMBOL(omap_rev); diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 75fb6c006e86..d85c24918c17 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -46,7 +46,6 @@ u32 omap_features; unsigned int omap_rev(void) { - WARN_ON_ONCE(!omap_revision || omap_revision == -1); return omap_revision; } EXPORT_SYMBOL(omap_rev); From ac6908b3049397b10bcfd8143d79cbdbbd266f02 Mon Sep 17 00:00:00 2001 From: Sjoerd Simons Date: Wed, 6 Apr 2016 14:52:53 +0200 Subject: [PATCH 044/181] ARM: dts: r8a7791: Don't disable referenced optional clocks clk_get on a disabled clock node will return EPROBE_DEFER, which can cause drivers to be deferred forever if such clocks are referenced in their clocks property. Update the various disabled external clock nodes to default to a frequency of 0, but don't disable them to prevent this. Signed-off-by: Sjoerd Simons Reviewed-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm/boot/dts/r8a7791-koelsch.dts | 1 + arch/arm/boot/dts/r8a7791-porter.dts | 1 + arch/arm/boot/dts/r8a7791.dtsi | 5 +---- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts index 0ad71b81d3a2..cc6e28f81fe4 100644 --- a/arch/arm/boot/dts/r8a7791-koelsch.dts +++ b/arch/arm/boot/dts/r8a7791-koelsch.dts @@ -661,6 +661,7 @@ }; &pcie_bus_clk { + clock-frequency = <100000000>; status = "okay"; }; diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts index 6c08314427d6..76c5b2ef8b7e 100644 --- a/arch/arm/boot/dts/r8a7791-porter.dts +++ b/arch/arm/boot/dts/r8a7791-porter.dts @@ -414,6 +414,7 @@ }; &pcie_bus_clk { + clock-frequency = <100000000>; status = "okay"; }; diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi index 6439f0569fe2..1cd1b6a3a72a 100644 --- a/arch/arm/boot/dts/r8a7791.dtsi +++ b/arch/arm/boot/dts/r8a7791.dtsi @@ -1083,9 +1083,8 @@ pcie_bus_clk: pcie_bus_clk { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <100000000>; + clock-frequency = <0>; clock-output-names = "pcie_bus"; - status = "disabled"; }; /* External SCIF clock */ @@ -1094,7 +1093,6 @@ #clock-cells = <0>; /* This value must be overridden by the board. */ clock-frequency = <0>; - status = "disabled"; }; /* External USB clock - can be overridden by the board */ @@ -1112,7 +1110,6 @@ /* This value must be overridden by the board. */ clock-frequency = <0>; clock-output-names = "can_clk"; - status = "disabled"; }; /* Special CPG clocks */ From 01638a7f5ef967e94e8aff455874d62e12fe32ed Mon Sep 17 00:00:00 2001 From: Sjoerd Simons Date: Wed, 6 Apr 2016 21:32:06 +0200 Subject: [PATCH 045/181] Revert "ARM: dts: porter: Enable SCIF_CLK frequency and pins" This reverts commit 19417bd9c511 ("ARM: dts: porter: Enable SCIF_CLK frequency and pins") as according to http://elinux.org/File:R-CarM2-KOELSCH_PORTER-B_PORTER_C_Comparison.pdf the external oscillator for SCIF_CLK is not mounted on the porter boards. Signed-off-by: Sjoerd Simons Acked-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm/boot/dts/r8a7791-porter.dts | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts index 76c5b2ef8b7e..a9285d9a57cd 100644 --- a/arch/arm/boot/dts/r8a7791-porter.dts +++ b/arch/arm/boot/dts/r8a7791-porter.dts @@ -143,19 +143,11 @@ }; &pfc { - pinctrl-0 = <&scif_clk_pins>; - pinctrl-names = "default"; - scif0_pins: serial0 { renesas,groups = "scif0_data_d"; renesas,function = "scif0"; }; - scif_clk_pins: scif_clk { - renesas,groups = "scif_clk"; - renesas,function = "scif_clk"; - }; - ether_pins: ether { renesas,groups = "eth_link", "eth_mdio", "eth_rmii"; renesas,function = "eth"; @@ -229,11 +221,6 @@ status = "okay"; }; -&scif_clk { - clock-frequency = <14745600>; - status = "okay"; -}; - ðer { pinctrl-0 = <ðer_pins &phy1_pins>; pinctrl-names = "default"; From c531fb27e9699eaee478ee5686a3cca5dee73602 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 11 Jan 2016 19:41:12 +0100 Subject: [PATCH 046/181] ARM: shmobile: timer: Fix preset_lpj leading to too short delays On all shmobile ARM SoCs, loop-based delays may complete early, which can be after only 1/3 (Cortex A9) or 1/2 (Cortex A7 or A15) of the minimum required time. This is caused by calculating preset_lpj based on incorrect assumptions about the number of clock cycles per loop: - All of Cortex A7, A9, and A15 run __loop_delay() at 1 loop per CPU clock cycle, - As of commit 11d4bb1bd067f9d0 ("ARM: 7907/1: lib: delay-loop: Add align directive to fix BogoMIPS calculation"), Cortex A8 runs __loop_delay() at 1 loop per 2 instead of 3 CPU clock cycles. On SoCs with Cortex A7 and/or A15 CPU cores, this went unnoticed, as delays use the ARM arch timer if available. R-Car Gen2 doesn't work if the arch timer is disabled. However, APE6 can be used without the arch timer. Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm/mach-shmobile/timer.c | 28 +++++++++++----------------- 1 file changed, 11 insertions(+), 17 deletions(-) diff --git a/arch/arm/mach-shmobile/timer.c b/arch/arm/mach-shmobile/timer.c index ad008e4b0c49..67d79f9c6bad 100644 --- a/arch/arm/mach-shmobile/timer.c +++ b/arch/arm/mach-shmobile/timer.c @@ -40,8 +40,7 @@ static void __init shmobile_setup_delay_hz(unsigned int max_cpu_core_hz, void __init shmobile_init_delay(void) { struct device_node *np, *cpus; - bool is_a7_a8_a9 = false; - bool is_a15 = false; + unsigned int div = 0; bool has_arch_timer = false; u32 max_freq = 0; @@ -55,27 +54,22 @@ void __init shmobile_init_delay(void) if (!of_property_read_u32(np, "clock-frequency", &freq)) max_freq = max(max_freq, freq); - if (of_device_is_compatible(np, "arm,cortex-a8") || - of_device_is_compatible(np, "arm,cortex-a9")) { - is_a7_a8_a9 = true; - } else if (of_device_is_compatible(np, "arm,cortex-a7")) { - is_a7_a8_a9 = true; - has_arch_timer = true; - } else if (of_device_is_compatible(np, "arm,cortex-a15")) { - is_a15 = true; + if (of_device_is_compatible(np, "arm,cortex-a8")) { + div = 2; + } else if (of_device_is_compatible(np, "arm,cortex-a9")) { + div = 1; + } else if (of_device_is_compatible(np, "arm,cortex-a7") || + of_device_is_compatible(np, "arm,cortex-a15")) { + div = 1; has_arch_timer = true; } } of_node_put(cpus); - if (!max_freq) + if (!max_freq || !div) return; - if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) { - if (is_a7_a8_a9) - shmobile_setup_delay_hz(max_freq, 1, 3); - else if (is_a15) - shmobile_setup_delay_hz(max_freq, 2, 4); - } + if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) + shmobile_setup_delay_hz(max_freq, 1, div); } From 89d124cb61b39900959e2839ac06b6339b6a54cb Mon Sep 17 00:00:00 2001 From: Jonas Eymann Date: Tue, 19 Apr 2016 20:33:47 +0300 Subject: [PATCH 047/181] crypto: talitos - fix crash in talitos_cra_init() Conversion of talitos driver to the new AEAD interface hasn't been properly tested. AEAD algorithms crash in talitos_cra_init as follows: [...] [ 1.141095] talitos ffe30000.crypto: hwrng [ 1.145381] Unable to handle kernel paging request for data at address 0x00000058 [ 1.152913] Faulting instruction address: 0xc02accc0 [ 1.157910] Oops: Kernel access of bad area, sig: 11 [#1] [ 1.163315] SMP NR_CPUS=2 P1020 RDB [ 1.166810] Modules linked in: [ 1.169875] CPU: 0 PID: 1007 Comm: cryptomgr_test Not tainted 4.4.6 #1 [ 1.176415] task: db5ec200 ti: db4d6000 task.ti: db4d6000 [ 1.181821] NIP: c02accc0 LR: c02acd18 CTR: c02acd04 [ 1.186793] REGS: db4d7d30 TRAP: 0300 Not tainted (4.4.6) [ 1.192457] MSR: 00029000 CR: 95009359 XER: e0000000 [ 1.198585] DEAR: 00000058 ESR: 00000000 GPR00: c017bdc0 db4d7de0 db5ec200 df424b48 00000000 00000000 df424bfc db75a600 GPR08: df424b48 00000000 db75a628 db4d6000 00000149 00000000 c0044cac db5acda0 GPR16: 00000000 00000000 00000000 00000000 00000000 00000000 00000400 df424940 GPR24: df424900 00003083 00000400 c0180000 db75a640 c03e9f84 df424b40 df424b48 [ 1.230978] NIP [c02accc0] talitos_cra_init+0x28/0x6c [ 1.236039] LR [c02acd18] talitos_cra_init_aead+0x14/0x28 [ 1.241443] Call Trace: [ 1.243894] [db4d7de0] [c03e9f84] 0xc03e9f84 (unreliable) [ 1.249322] [db4d7df0] [c017bdc0] crypto_create_tfm+0x5c/0xf0 [ 1.255083] [db4d7e10] [c017beec] crypto_alloc_tfm+0x98/0xf8 [ 1.260769] [db4d7e40] [c0186a20] alg_test_aead+0x28/0xc8 [ 1.266181] [db4d7e60] [c0186718] alg_test+0x260/0x2e0 [ 1.271333] [db4d7ee0] [c0183860] cryptomgr_test+0x30/0x54 [ 1.276843] [db4d7ef0] [c0044d80] kthread+0xd4/0xd8 [ 1.281741] [db4d7f40] [c000e4a4] ret_from_kernel_thread+0x5c/0x64 [ 1.287930] Instruction dump: [ 1.290902] 38600000 4e800020 81230028 7c681b78 81490010 38e9ffc0 3929ffe8 554a073e [ 1.298691] 2b8a000a 7d474f9e 812a0008 91230030 <80e90058> 39270060 7c0004ac 7cc04828 Cc: # 4.3+ Fixes: aeb4c132f33d ("crypto: talitos - Convert to new AEAD interface") Signed-off-by: Jonas Eymann Fix typo - replaced parameter of __crypto_ahash_alg(): s/tfm/alg Remove checkpatch warnings. Add commit message. Signed-off-by: Horia Geant? Signed-off-by: Herbert Xu --- drivers/crypto/talitos.c | 41 ++++++++++++++++++++++++++-------------- 1 file changed, 27 insertions(+), 14 deletions(-) diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index a0d4a08313ae..35198804d6d3 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -2629,21 +2629,11 @@ struct talitos_crypto_alg { struct talitos_alg_template algt; }; -static int talitos_cra_init(struct crypto_tfm *tfm) +static int talitos_init_common(struct talitos_ctx *ctx, + struct talitos_crypto_alg *talitos_alg) { - struct crypto_alg *alg = tfm->__crt_alg; - struct talitos_crypto_alg *talitos_alg; - struct talitos_ctx *ctx = crypto_tfm_ctx(tfm); struct talitos_private *priv; - if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH) - talitos_alg = container_of(__crypto_ahash_alg(alg), - struct talitos_crypto_alg, - algt.alg.hash); - else - talitos_alg = container_of(alg, struct talitos_crypto_alg, - algt.alg.crypto); - /* update context with ptr to dev */ ctx->dev = talitos_alg->dev; @@ -2661,10 +2651,33 @@ static int talitos_cra_init(struct crypto_tfm *tfm) return 0; } +static int talitos_cra_init(struct crypto_tfm *tfm) +{ + struct crypto_alg *alg = tfm->__crt_alg; + struct talitos_crypto_alg *talitos_alg; + struct talitos_ctx *ctx = crypto_tfm_ctx(tfm); + + if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH) + talitos_alg = container_of(__crypto_ahash_alg(alg), + struct talitos_crypto_alg, + algt.alg.hash); + else + talitos_alg = container_of(alg, struct talitos_crypto_alg, + algt.alg.crypto); + + return talitos_init_common(ctx, talitos_alg); +} + static int talitos_cra_init_aead(struct crypto_aead *tfm) { - talitos_cra_init(crypto_aead_tfm(tfm)); - return 0; + struct aead_alg *alg = crypto_aead_alg(tfm); + struct talitos_crypto_alg *talitos_alg; + struct talitos_ctx *ctx = crypto_aead_ctx(tfm); + + talitos_alg = container_of(alg, struct talitos_crypto_alg, + algt.alg.aead); + + return talitos_init_common(ctx, talitos_alg); } static int talitos_cra_init_ahash(struct crypto_tfm *tfm) From 340ff60ae93a5db2b2be6f38868df9a1293b6007 Mon Sep 17 00:00:00 2001 From: Horia Geant? Date: Tue, 19 Apr 2016 20:33:48 +0300 Subject: [PATCH 048/181] crypto: talitos - fix AEAD tcrypt tests After conversion to new AEAD interface, tcrypt tests fail as follows: [...] [ 1.145414] alg: aead: Test 1 failed on encryption for authenc-hmac-sha1-cbc-aes-talitos [ 1.153564] 00000000: 53 69 6e 67 6c 65 20 62 6c 6f 63 6b 20 6d 73 67 [ 1.160041] 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 1.166509] 00000020: 00 00 00 00 [...] Fix them by providing the correct cipher in & cipher out pointers, i.e. must skip over associated data in src and dst S/G. While here, fix a problem with the HW S/G table index usage: tbl_off must be updated after the pointer to the table entries is set. Cc: # 4.3+ Fixes: aeb4c132f33d ("crypto: talitos - Convert to new AEAD interface") Reported-by: Jonas Eymann Signed-off-by: Horia Geant? Signed-off-by: Herbert Xu --- drivers/crypto/talitos.c | 46 ++++++++++++++++++++++++++-------------- 1 file changed, 30 insertions(+), 16 deletions(-) diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index 35198804d6d3..aae05547b924 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -63,6 +63,14 @@ static void to_talitos_ptr(struct talitos_ptr *ptr, dma_addr_t dma_addr, ptr->eptr = upper_32_bits(dma_addr); } +static void copy_talitos_ptr(struct talitos_ptr *dst_ptr, + struct talitos_ptr *src_ptr, bool is_sec1) +{ + dst_ptr->ptr = src_ptr->ptr; + if (!is_sec1) + dst_ptr->eptr = src_ptr->eptr; +} + static void to_talitos_ptr_len(struct talitos_ptr *ptr, unsigned int len, bool is_sec1) { @@ -1083,21 +1091,20 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, sg_count = dma_map_sg(dev, areq->src, edesc->src_nents ?: 1, (areq->src == areq->dst) ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); - /* hmac data */ desc->ptr[1].len = cpu_to_be16(areq->assoclen); if (sg_count > 1 && (ret = sg_to_link_tbl_offset(areq->src, sg_count, 0, areq->assoclen, &edesc->link_tbl[tbl_off])) > 1) { - tbl_off += ret; - to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off * sizeof(struct talitos_ptr), 0); desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP; dma_sync_single_for_device(dev, edesc->dma_link_tbl, edesc->dma_len, DMA_BIDIRECTIONAL); + + tbl_off += ret; } else { to_talitos_ptr(&desc->ptr[1], sg_dma_address(areq->src), 0); desc->ptr[1].j_extent = 0; @@ -1126,11 +1133,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV) sg_link_tbl_len += authsize; - if (sg_count > 1 && - (ret = sg_to_link_tbl_offset(areq->src, sg_count, areq->assoclen, - sg_link_tbl_len, - &edesc->link_tbl[tbl_off])) > 1) { - tbl_off += ret; + if (sg_count == 1) { + to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src) + + areq->assoclen, 0); + } else if ((ret = sg_to_link_tbl_offset(areq->src, sg_count, + areq->assoclen, sg_link_tbl_len, + &edesc->link_tbl[tbl_off])) > + 1) { desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP; to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl + tbl_off * @@ -1138,8 +1147,10 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, dma_sync_single_for_device(dev, edesc->dma_link_tbl, edesc->dma_len, DMA_BIDIRECTIONAL); - } else - to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src), 0); + tbl_off += ret; + } else { + copy_talitos_ptr(&desc->ptr[4], &edesc->link_tbl[tbl_off], 0); + } /* cipher out */ desc->ptr[5].len = cpu_to_be16(cryptlen); @@ -1151,11 +1162,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, edesc->icv_ool = false; - if (sg_count > 1 && - (sg_count = sg_to_link_tbl_offset(areq->dst, sg_count, + if (sg_count == 1) { + to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst) + + areq->assoclen, 0); + } else if ((sg_count = + sg_to_link_tbl_offset(areq->dst, sg_count, areq->assoclen, cryptlen, - &edesc->link_tbl[tbl_off])) > - 1) { + &edesc->link_tbl[tbl_off])) > 1) { struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off]; to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl + @@ -1178,8 +1191,9 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, edesc->dma_len, DMA_BIDIRECTIONAL); edesc->icv_ool = true; - } else - to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0); + } else { + copy_talitos_ptr(&desc->ptr[5], &edesc->link_tbl[tbl_off], 0); + } /* iv out */ map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv, From d5468d7afaa9c9e961e150f0455a14a9f4872a98 Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Sun, 31 Jan 2016 14:14:52 -0200 Subject: [PATCH 049/181] [media] usbvision: revert commit 588afcc1 Commit 588afcc1c0e4 ("[media] usbvision fix overflow of interfaces array")' should be reverted, because: * "!dev->actconfig->interface[ifnum]" won't catch a case where the value is not NULL but some garbage. This way the system may crash later with GPF. * "(ifnum >= USB_MAXINTERFACES)" does not cover all the error conditions. "ifnum" should be compared to "dev->actconfig-> desc.bNumInterfaces", i.e. compared to the number of "struct usb_interface" kzalloc()-ed, not to USB_MAXINTERFACES. * There is a "struct usb_device" leak in this error path, as there is usb_get_dev(), but no usb_put_dev() on this path. * There is a bug of the same type several lines below with number of endpoints. The code is accessing hard-coded second endpoint ("interface->endpoint[1].desc") which may not exist. It would be great to handle this in the same patch too. * All the concerns above are resolved by already-accepted commit fa52bd50 ("[media] usbvision: fix crash on detecting device with invalid configuration") * Mailing list message: http://www.spinics.net/lists/linux-media/msg94832.html Signed-off-by: Vladis Dronov Signed-off-by: Hans Verkuil Cc: # for v4.5 Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/usbvision/usbvision-video.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c index 12f5ebbd0436..ad2f3d27b266 100644 --- a/drivers/media/usb/usbvision/usbvision-video.c +++ b/drivers/media/usb/usbvision/usbvision-video.c @@ -1452,13 +1452,6 @@ static int usbvision_probe(struct usb_interface *intf, printk(KERN_INFO "%s: %s found\n", __func__, usbvision_device_data[model].model_string); - /* - * this is a security check. - * an exploit using an incorrect bInterfaceNumber is known - */ - if (ifnum >= USB_MAXINTERFACES || !dev->actconfig->interface[ifnum]) - return -ENODEV; - if (usbvision_device_data[model].interface >= 0) interface = &dev->actconfig->interface[usbvision_device_data[model].interface]->altsetting[0]; else if (ifnum < dev->actconfig->desc.bNumInterfaces) From 8bbb6568428fa14c5bef120d443c20e0e7d52699 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 15 Apr 2016 08:58:10 -0300 Subject: [PATCH 050/181] [media] davinci_vpfe: Revert "staging: media: davinci_vpfe: remove,unnecessary ret variable" This reverts commit afa5d19a2b5f ("staging: media: davinci_vpfe: remove unnecessary ret variable"). This patch is completely bogus and messed up the code big time. I'm not sure what was intended, but this isn't it. Cc: Thaissa Falbo Cc: Greg Kroah-Hartman Signed-off-by: Mauro Carvalho Chehab --- .../staging/media/davinci_vpfe/vpfe_video.c | 54 ++++++++++++------- 1 file changed, 34 insertions(+), 20 deletions(-) diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c index b793c04028a3..be72a8e5f221 100644 --- a/drivers/staging/media/davinci_vpfe/vpfe_video.c +++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c @@ -172,9 +172,11 @@ static int vpfe_prepare_pipeline(struct vpfe_video_device *video) static int vpfe_update_pipe_state(struct vpfe_video_device *video) { struct vpfe_pipeline *pipe = &video->pipe; + int ret; - if (vpfe_prepare_pipeline(video)) - return vpfe_prepare_pipeline(video); + ret = vpfe_prepare_pipeline(video); + if (ret) + return ret; /* * Find out if there is any input video @@ -182,9 +184,10 @@ static int vpfe_update_pipe_state(struct vpfe_video_device *video) */ if (pipe->input_num == 0) { pipe->state = VPFE_PIPELINE_STREAM_CONTINUOUS; - if (vpfe_update_current_ext_subdev(video)) { + ret = vpfe_update_current_ext_subdev(video); + if (ret) { pr_err("Invalid external subdev\n"); - return vpfe_update_current_ext_subdev(video); + return ret; } } else { pipe->state = VPFE_PIPELINE_STREAM_SINGLESHOT; @@ -667,6 +670,7 @@ static int vpfe_enum_fmt(struct file *file, void *priv, struct v4l2_subdev *subdev; struct v4l2_format format; struct media_pad *remote; + int ret; v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_enum_fmt\n"); @@ -695,10 +699,11 @@ static int vpfe_enum_fmt(struct file *file, void *priv, sd_fmt.pad = remote->index; sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE; /* get output format of remote subdev */ - if (v4l2_subdev_call(subdev, pad, get_fmt, NULL, &sd_fmt)) { + ret = v4l2_subdev_call(subdev, pad, get_fmt, NULL, &sd_fmt); + if (ret) { v4l2_err(&vpfe_dev->v4l2_dev, "invalid remote subdev for video node\n"); - return v4l2_subdev_call(subdev, pad, get_fmt, NULL, &sd_fmt); + return ret; } /* convert to pix format */ mbus.code = sd_fmt.format.code; @@ -725,6 +730,7 @@ static int vpfe_s_fmt(struct file *file, void *priv, struct vpfe_video_device *video = video_drvdata(file); struct vpfe_device *vpfe_dev = video->vpfe_dev; struct v4l2_format format; + int ret; v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_s_fmt\n"); /* If streaming is started, return error */ @@ -733,8 +739,9 @@ static int vpfe_s_fmt(struct file *file, void *priv, return -EBUSY; } /* get adjacent subdev's output pad format */ - if (__vpfe_video_get_format(video, &format)) - return __vpfe_video_get_format(video, &format); + ret = __vpfe_video_get_format(video, &format); + if (ret) + return ret; *fmt = format; video->fmt = *fmt; return 0; @@ -757,11 +764,13 @@ static int vpfe_try_fmt(struct file *file, void *priv, struct vpfe_video_device *video = video_drvdata(file); struct vpfe_device *vpfe_dev = video->vpfe_dev; struct v4l2_format format; + int ret; v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_try_fmt\n"); /* get adjacent subdev's output pad format */ - if (__vpfe_video_get_format(video, &format)) - return __vpfe_video_get_format(video, &format); + ret = __vpfe_video_get_format(video, &format); + if (ret) + return ret; *fmt = format; return 0; @@ -838,8 +847,9 @@ static int vpfe_s_input(struct file *file, void *priv, unsigned int index) v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_s_input\n"); - if (mutex_lock_interruptible(&video->lock)) - return mutex_lock_interruptible(&video->lock); + ret = mutex_lock_interruptible(&video->lock); + if (ret) + return ret; /* * If streaming is started return device busy * error @@ -940,8 +950,9 @@ static int vpfe_s_std(struct file *file, void *priv, v4l2_std_id std_id) v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_s_std\n"); /* Call decoder driver function to set the standard */ - if (mutex_lock_interruptible(&video->lock)) - return mutex_lock_interruptible(&video->lock); + ret = mutex_lock_interruptible(&video->lock); + if (ret) + return ret; sdinfo = video->current_ext_subdev; /* If streaming is started, return device busy error */ if (video->started) { @@ -1327,8 +1338,9 @@ static int vpfe_reqbufs(struct file *file, void *priv, return -EINVAL; } - if (mutex_lock_interruptible(&video->lock)) - return mutex_lock_interruptible(&video->lock); + ret = mutex_lock_interruptible(&video->lock); + if (ret) + return ret; if (video->io_usrs != 0) { v4l2_err(&vpfe_dev->v4l2_dev, "Only one IO user allowed\n"); @@ -1354,10 +1366,11 @@ static int vpfe_reqbufs(struct file *file, void *priv, q->buf_struct_size = sizeof(struct vpfe_cap_buffer); q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; - if (vb2_queue_init(q)) { + ret = vb2_queue_init(q); + if (ret) { v4l2_err(&vpfe_dev->v4l2_dev, "vb2_queue_init() failed\n"); vb2_dma_contig_cleanup_ctx(vpfe_dev->pdev); - return vb2_queue_init(q); + return ret; } fh->io_allowed = 1; @@ -1533,8 +1546,9 @@ static int vpfe_streamoff(struct file *file, void *priv, return -EINVAL; } - if (mutex_lock_interruptible(&video->lock)) - return mutex_lock_interruptible(&video->lock); + ret = mutex_lock_interruptible(&video->lock); + if (ret) + return ret; vpfe_stop_capture(video); ret = vb2_streamoff(&video->buffer_queue, buf_type); From dba599091c191d209b1499511a524ad9657c0e5a Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Fri, 15 Apr 2016 09:41:35 +0200 Subject: [PATCH 051/181] s390/pci: fix use after free in dma_init After a failure during registration of the dma_table (because of the function being in error state) we free its memory but don't reset the associated pointer to zero. When we then receive a notification from firmware (about the function being in error state) we'll try to walk and free the dma_table again. Fix this by resetting the dma_table pointer. In addition to that make sure that we free the iommu_bitmap when appropriate. Signed-off-by: Sebastian Ott Reviewed-by: Gerald Schaefer Signed-off-by: Martin Schwidefsky --- arch/s390/pci/pci_dma.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index e595e89eac65..1ea8c07eab84 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -457,7 +457,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->dma_table = dma_alloc_cpu_table(); if (!zdev->dma_table) { rc = -ENOMEM; - goto out_clean; + goto out; } /* @@ -477,18 +477,22 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8); if (!zdev->iommu_bitmap) { rc = -ENOMEM; - goto out_reg; + goto free_dma_table; } rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, (u64) zdev->dma_table); if (rc) - goto out_reg; - return 0; + goto free_bitmap; -out_reg: + return 0; +free_bitmap: + vfree(zdev->iommu_bitmap); + zdev->iommu_bitmap = NULL; +free_dma_table: dma_free_cpu_table(zdev->dma_table); -out_clean: + zdev->dma_table = NULL; +out: return rc; } From 723cacbd9dc79582e562c123a0bacf8bfc69e72a Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Fri, 15 Apr 2016 16:38:40 +0200 Subject: [PATCH 052/181] s390/mm: fix asce_bits handling with dynamic pagetable levels There is a race with multi-threaded applications between context switch and pagetable upgrade. In switch_mm() a new user_asce is built from mm->pgd and mm->context.asce_bits, w/o holding any locks. A concurrent mmap with a pagetable upgrade on another thread in crst_table_upgrade() could already have set new asce_bits, but not yet the new mm->pgd. This would result in a corrupt user_asce in switch_mm(), and eventually in a kernel panic from a translation exception. Fix this by storing the complete asce instead of just the asce_bits, which can then be read atomically from switch_mm(), so that it either sees the old value or the new value, but no mixture. Both cases are OK. Having the old value would result in a page fault on access to the higher level memory, but the fault handler would see the new mm->pgd, if it was a valid access after the mmap on the other thread has completed. So as worst-case scenario we would have a page fault loop for the racing thread until the next time slice. Also remove dead code and simplify the upgrade/downgrade path, there are no upgrades from 2 levels, and only downgrades from 3 levels for compat tasks. There are also no concurrent upgrades, because the mmap_sem is held with down_write() in do_mmap, so the flush and table checks during upgrade can be removed. Reported-by: Michael Munday Reviewed-by: Martin Schwidefsky Signed-off-by: Gerald Schaefer Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/mmu.h | 2 +- arch/s390/include/asm/mmu_context.h | 28 ++++++++-- arch/s390/include/asm/pgalloc.h | 4 +- arch/s390/include/asm/processor.h | 2 +- arch/s390/include/asm/tlbflush.h | 9 +-- arch/s390/mm/init.c | 3 +- arch/s390/mm/mmap.c | 6 +- arch/s390/mm/pgalloc.c | 85 ++++++++++------------------- 8 files changed, 62 insertions(+), 77 deletions(-) diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index d29ad9545b41..081b2ad99d73 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -11,7 +11,7 @@ typedef struct { spinlock_t list_lock; struct list_head pgtable_list; struct list_head gmap_list; - unsigned long asce_bits; + unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; /* The mmu context allocates 4K page tables. */ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index d321469eeda7..c837b79b455d 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -26,12 +26,28 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.has_pgste = 0; mm->context.use_skey = 0; #endif - if (mm->context.asce_limit == 0) { + switch (mm->context.asce_limit) { + case 1UL << 42: + /* + * forked 3-level task, fall through to set new asce with new + * mm->pgd + */ + case 0: /* context created by exec, set asce limit to 4TB */ - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | _ASCE_TYPE_REGION3; mm->context.asce_limit = STACK_TOP_MAX; - } else if (mm->context.asce_limit == (1UL << 31)) { + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + break; + case 1UL << 53: + /* forked 4-level task, set new asce with new mm->pgd */ + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + break; + case 1UL << 31: + /* forked 2-level compat task, set new asce with new mm->pgd */ + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; + /* pgd_alloc() did not increase mm->nr_pmds */ mm_inc_nr_pmds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); @@ -42,7 +58,7 @@ static inline int init_new_context(struct task_struct *tsk, static inline void set_user_asce(struct mm_struct *mm) { - S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd); + S390_lowcore.user_asce = mm->context.asce; if (current->thread.mm_segment.ar4) __ctl_load(S390_lowcore.user_asce, 7, 7); set_cpu_flag(CIF_ASCE); @@ -71,7 +87,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, { int cpu = smp_processor_id(); - S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd); + S390_lowcore.user_asce = next->context.asce; if (prev == next) return; if (MACHINE_HAS_TLB_LC) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 9b3d9b6099f2..da34cb6b1f3b 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -52,8 +52,8 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm) return _REGION2_ENTRY_EMPTY; } -int crst_table_upgrade(struct mm_struct *, unsigned long limit); -void crst_table_downgrade(struct mm_struct *, unsigned long limit); +int crst_table_upgrade(struct mm_struct *); +void crst_table_downgrade(struct mm_struct *); static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index d6fd22ea270d..18cdede1aeda 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -175,7 +175,7 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS]; regs->psw.mask = PSW_USER_BITS | PSW_MASK_BA; \ regs->psw.addr = new_psw; \ regs->gprs[15] = new_stackp; \ - crst_table_downgrade(current->mm, 1UL << 31); \ + crst_table_downgrade(current->mm); \ execve_tail(); \ } while (0) diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index ca148f7c3eaa..a2e6ef32e054 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -110,8 +110,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) static inline void __tlb_flush_kernel(void) { if (MACHINE_HAS_IDTE) - __tlb_flush_idte((unsigned long) init_mm.pgd | - init_mm.context.asce_bits); + __tlb_flush_idte(init_mm.context.asce); else __tlb_flush_global(); } @@ -133,8 +132,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) static inline void __tlb_flush_kernel(void) { if (MACHINE_HAS_TLB_LC) - __tlb_flush_idte_local((unsigned long) init_mm.pgd | - init_mm.context.asce_bits); + __tlb_flush_idte_local(init_mm.context.asce); else __tlb_flush_local(); } @@ -148,8 +146,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm) * only ran on the local cpu. */ if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list)) - __tlb_flush_asce(mm, (unsigned long) mm->pgd | - mm->context.asce_bits); + __tlb_flush_asce(mm, mm->context.asce); else __tlb_flush_full(mm); } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c7b0451397d6..2489b2e917c8 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -89,7 +89,8 @@ void __init paging_init(void) asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH; pgd_type = _REGION3_ENTRY_EMPTY; } - S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits; + init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits; + S390_lowcore.kernel_asce = init_mm.context.asce; clear_table((unsigned long *) init_mm.pgd, pgd_type, sizeof(unsigned long)*2048); vmem_map_init(); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 45c4daa49930..89cf09e5f168 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -174,7 +174,7 @@ int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags) if (!(flags & MAP_FIXED)) addr = 0; if ((addr + len) >= TASK_SIZE) - return crst_table_upgrade(current->mm, TASK_MAX_SIZE); + return crst_table_upgrade(current->mm); return 0; } @@ -191,7 +191,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr, return area; if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, TASK_MAX_SIZE); + rc = crst_table_upgrade(mm); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); @@ -213,7 +213,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, return area; if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, TASK_MAX_SIZE); + rc = crst_table_upgrade(mm); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area_topdown(filp, addr, len, diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index f6c3de26cda8..e8b5962ac12a 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -76,81 +76,52 @@ static void __crst_table_upgrade(void *arg) __tlb_flush_local(); } -int crst_table_upgrade(struct mm_struct *mm, unsigned long limit) +int crst_table_upgrade(struct mm_struct *mm) { unsigned long *table, *pgd; - unsigned long entry; - int flush; - BUG_ON(limit > TASK_MAX_SIZE); - flush = 0; -repeat: + /* upgrade should only happen from 3 to 4 levels */ + BUG_ON(mm->context.asce_limit != (1UL << 42)); + table = crst_table_alloc(mm); if (!table) return -ENOMEM; + spin_lock_bh(&mm->page_table_lock); - if (mm->context.asce_limit < limit) { - pgd = (unsigned long *) mm->pgd; - if (mm->context.asce_limit <= (1UL << 31)) { - entry = _REGION3_ENTRY_EMPTY; - mm->context.asce_limit = 1UL << 42; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION3; - } else { - entry = _REGION2_ENTRY_EMPTY; - mm->context.asce_limit = 1UL << 53; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION2; - } - crst_table_init(table, entry); - pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); - mm->pgd = (pgd_t *) table; - mm->task_size = mm->context.asce_limit; - table = NULL; - flush = 1; - } + pgd = (unsigned long *) mm->pgd; + crst_table_init(table, _REGION2_ENTRY_EMPTY); + pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); + mm->pgd = (pgd_t *) table; + mm->context.asce_limit = 1UL << 53; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm->task_size = mm->context.asce_limit; spin_unlock_bh(&mm->page_table_lock); - if (table) - crst_table_free(mm, table); - if (mm->context.asce_limit < limit) - goto repeat; - if (flush) - on_each_cpu(__crst_table_upgrade, mm, 0); + + on_each_cpu(__crst_table_upgrade, mm, 0); return 0; } -void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) +void crst_table_downgrade(struct mm_struct *mm) { pgd_t *pgd; + /* downgrade should only happen from 3 to 2 levels (compat only) */ + BUG_ON(mm->context.asce_limit != (1UL << 42)); + if (current->active_mm == mm) { clear_user_asce(); __tlb_flush_mm(mm); } - while (mm->context.asce_limit > limit) { - pgd = mm->pgd; - switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) { - case _REGION_ENTRY_TYPE_R2: - mm->context.asce_limit = 1UL << 42; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION3; - break; - case _REGION_ENTRY_TYPE_R3: - mm->context.asce_limit = 1UL << 31; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_SEGMENT; - break; - default: - BUG(); - } - mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN); - mm->task_size = mm->context.asce_limit; - crst_table_free(mm, (unsigned long *) pgd); - } + + pgd = mm->pgd; + mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN); + mm->context.asce_limit = 1UL << 31; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; + mm->task_size = mm->context.asce_limit; + crst_table_free(mm, (unsigned long *) pgd); + if (current->active_mm == mm) set_user_asce(mm); } From 2144fff7df8e76654fa72b0a9d2324ce2e0c8a5c Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Thu, 21 Apr 2016 13:52:38 +0200 Subject: [PATCH 053/181] drm/etnaviv: don't move linear memory window on 3D cores without MC2.0 On cores with MC1.0 the memory window offset is not properly respected by all engines in the core, leading to different views of the memory if the offset in non-zero. This causes relocs for those engines to be wrong and might lead to other subtile problems. Rather than trying to work around this, just disable the linear memory window offset for those cores. Suggested-by: Russell King Signed-off-by: Lucas Stach --- drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 31 ++++++++++++++++----------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 09198d0b5814..306dde18a94a 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -572,6 +572,24 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) goto fail; } + /* + * Set the GPU linear window to be at the end of the DMA window, where + * the CMA area is likely to reside. This ensures that we are able to + * map the command buffers while having the linear window overlap as + * much RAM as possible, so we can optimize mappings for other buffers. + * + * For 3D cores only do this if MC2.0 is present, as with MC1.0 it leads + * to different views of the memory on the individual engines. + */ + if (!(gpu->identity.features & chipFeatures_PIPE_3D) || + (gpu->identity.minor_features0 & chipMinorFeatures0_MC20)) { + u32 dma_mask = (u32)dma_get_required_mask(gpu->dev); + if (dma_mask < PHYS_OFFSET + SZ_2G) + gpu->memory_base = PHYS_OFFSET; + else + gpu->memory_base = dma_mask - SZ_2G + 1; + } + ret = etnaviv_hw_reset(gpu); if (ret) goto fail; @@ -1566,7 +1584,6 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct etnaviv_gpu *gpu; - u32 dma_mask; int err = 0; gpu = devm_kzalloc(dev, sizeof(*gpu), GFP_KERNEL); @@ -1576,18 +1593,6 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev) gpu->dev = &pdev->dev; mutex_init(&gpu->lock); - /* - * Set the GPU linear window to be at the end of the DMA window, where - * the CMA area is likely to reside. This ensures that we are able to - * map the command buffers while having the linear window overlap as - * much RAM as possible, so we can optimize mappings for other buffers. - */ - dma_mask = (u32)dma_get_required_mask(dev); - if (dma_mask < PHYS_OFFSET + SZ_2G) - gpu->memory_base = PHYS_OFFSET; - else - gpu->memory_base = dma_mask - SZ_2G + 1; - /* Map registers: */ gpu->mmio = etnaviv_ioremap(pdev, NULL, dev_name(gpu->dev)); if (IS_ERR(gpu->mmio)) From d9676fa152c83b82137af950b1d4f629045d90c9 Mon Sep 17 00:00:00 2001 From: Evgeny Voevodin Date: Wed, 23 Mar 2016 12:26:52 +0300 Subject: [PATCH 054/181] ARCv2: Enable LOCKDEP - The asm helpers for calling into irq tracer were missing - Add calls to above helpers in low level assembly entry code for ARCv2 - irq_save() uses CLRI to disable interrupts and returns the prev interrupt state (in STATUS32) in a specific encoding (and not the raw value of STATUS32). This is usable with SETI in irq_restore(). However save_flags() reads the raw value of STATUS32 which doesn't pair with irq_save/restore() and thus needs fixing. Signed-off-by: Evgeny Voevodin [vgupta: updated changelog and also added some comments] Signed-off-by: Vineet Gupta --- arch/arc/include/asm/irqflags-arcv2.h | 36 ++++++++++++++++++++++++++- arch/arc/kernel/entry-arcv2.S | 10 +++++++- arch/arc/kernel/entry-compact.S | 3 +++ 3 files changed, 47 insertions(+), 2 deletions(-) diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index 37c2f751eebf..d1ec7f6b31e0 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -18,6 +18,12 @@ #define STATUS_AD_MASK (1< Date: Wed, 13 Apr 2016 13:59:14 +1000 Subject: [PATCH 055/181] i2c: cpm: Fix build break due to incompatible pointer types Since commit ea8daa7b9784 ("kbuild: Add option to turn incompatible pointer check into error"), assignments from an incompatible pointer types have become a hard error, eg: drivers/i2c/busses/i2c-cpm.c:545:91: error: passing argument 3 of 'dma_alloc_coherent' from incompatible pointer type Fix the build break by converting txdma & rxdma to dma_addr_t. Signed-off-by: Michael Ellerman Signed-off-by: Wolfram Sang Cc: stable@kernel.org Fixes: ea8daa7b9784 --- drivers/i2c/busses/i2c-cpm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c index 714bdc837769..b167ab25310a 100644 --- a/drivers/i2c/busses/i2c-cpm.c +++ b/drivers/i2c/busses/i2c-cpm.c @@ -116,8 +116,8 @@ struct cpm_i2c { cbd_t __iomem *rbase; u_char *txbuf[CPM_MAXBD]; u_char *rxbuf[CPM_MAXBD]; - u32 txdma[CPM_MAXBD]; - u32 rxdma[CPM_MAXBD]; + dma_addr_t txdma[CPM_MAXBD]; + dma_addr_t rxdma[CPM_MAXBD]; }; static irqreturn_t cpm_i2c_interrupt(int irq, void *dev_id) From 10ff4c5239a137abfc896ec73ef3d15a0f86a16a Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Sat, 16 Apr 2016 21:14:52 -0400 Subject: [PATCH 056/181] i2c: exynos5: Fix possible ABBA deadlock by keeping I2C clock prepared The exynos5 I2C controller driver always prepares and enables a clock before using it and then disables unprepares it when the clock is not used anymore. But this can cause a possible ABBA deadlock in some scenarios since a driver that uses regmap to access its I2C registers, will first grab the regmap lock and then the I2C xfer function will grab the prepare lock when preparing the I2C clock. But since the clock driver also uses regmap for I2C accesses, preparing a clock will first grab the prepare lock and then the regmap lock when using the regmap API. An example of this happens on the Exynos5422 Odroid XU4 board where a s2mps11 PMIC is used and both the s2mps11 regulators and clk drivers share the same I2C regmap. The possible deadlock is reported by the kernel lockdep: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(sec_core:428:(regmap)->lock); lock(prepare_lock); lock(sec_core:428:(regmap)->lock); lock(prepare_lock); *** DEADLOCK *** Fix it by leaving the code prepared on probe and use {en,dis}able in the I2C transfer function. This patch is similar to commit 34e81ad5f0b6 ("i2c: s3c2410: fix ABBA deadlock by keeping clock prepared") that fixes the same bug in other driver for an I2C controller found in Samsung SoCs. Reported-by: Anand Moon Signed-off-by: Javier Martinez Canillas Reviewed-by: Anand Moon Reviewed-by: Krzysztof Kozlowski Signed-off-by: Wolfram Sang Cc: stable@kernel.org --- drivers/i2c/busses/i2c-exynos5.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c index b29c7500461a..f54ece8fce78 100644 --- a/drivers/i2c/busses/i2c-exynos5.c +++ b/drivers/i2c/busses/i2c-exynos5.c @@ -671,7 +671,9 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap, return -EIO; } - clk_prepare_enable(i2c->clk); + ret = clk_enable(i2c->clk); + if (ret) + return ret; for (i = 0; i < num; i++, msgs++) { stop = (i == num - 1); @@ -695,7 +697,7 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap, } out: - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); return ret; } @@ -747,7 +749,9 @@ static int exynos5_i2c_probe(struct platform_device *pdev) return -ENOENT; } - clk_prepare_enable(i2c->clk); + ret = clk_prepare_enable(i2c->clk); + if (ret) + return ret; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); i2c->regs = devm_ioremap_resource(&pdev->dev, mem); @@ -799,6 +803,10 @@ static int exynos5_i2c_probe(struct platform_device *pdev) platform_set_drvdata(pdev, i2c); + clk_disable(i2c->clk); + + return 0; + err_clk: clk_disable_unprepare(i2c->clk); return ret; @@ -810,6 +818,8 @@ static int exynos5_i2c_remove(struct platform_device *pdev) i2c_del_adapter(&i2c->adap); + clk_unprepare(i2c->clk); + return 0; } @@ -821,6 +831,8 @@ static int exynos5_i2c_suspend_noirq(struct device *dev) i2c->suspended = 1; + clk_unprepare(i2c->clk); + return 0; } @@ -830,7 +842,9 @@ static int exynos5_i2c_resume_noirq(struct device *dev) struct exynos5_i2c *i2c = platform_get_drvdata(pdev); int ret = 0; - clk_prepare_enable(i2c->clk); + ret = clk_prepare_enable(i2c->clk); + if (ret) + return ret; ret = exynos5_hsi2c_clock_setup(i2c); if (ret) { @@ -839,7 +853,7 @@ static int exynos5_i2c_resume_noirq(struct device *dev) } exynos5_i2c_init(i2c); - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); i2c->suspended = 0; return 0; From 630ba0cc7a6dbafbdee43795617c872b35cde1b4 Mon Sep 17 00:00:00 2001 From: Laszlo Ersek Date: Thu, 21 Apr 2016 18:21:11 +0200 Subject: [PATCH 057/181] efi: Fix out-of-bounds read in variable_matches() The variable_matches() function can currently read "var_name[len]", for example when: - var_name[0] == 'a', - len == 1 - match_name points to the NUL-terminated string "ab". This function is supposed to accept "var_name" inputs that are not NUL-terminated (hence the "len" parameter"). Document the function, and access "var_name[*match]" only if "*match" is smaller than "len". Reported-by: Chris Wilson Signed-off-by: Laszlo Ersek Cc: Peter Jones Cc: Matthew Garrett Cc: Jason Andryuk Cc: Jani Nikula Cc: # v3.10+ Link: http://thread.gmane.org/gmane.comp.freedesktop.xorg.drivers.intel/86906 Signed-off-by: Matt Fleming --- drivers/firmware/efi/vars.c | 37 ++++++++++++++++++++++++++----------- 1 file changed, 26 insertions(+), 11 deletions(-) diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 0ac594c0a234..34b741940494 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -202,29 +202,44 @@ static const struct variable_validate variable_validate[] = { { NULL_GUID, "", NULL }, }; +/* + * Check if @var_name matches the pattern given in @match_name. + * + * @var_name: an array of @len non-NUL characters. + * @match_name: a NUL-terminated pattern string, optionally ending in "*". A + * final "*" character matches any trailing characters @var_name, + * including the case when there are none left in @var_name. + * @match: on output, the number of non-wildcard characters in @match_name + * that @var_name matches, regardless of the return value. + * @return: whether @var_name fully matches @match_name. + */ static bool variable_matches(const char *var_name, size_t len, const char *match_name, int *match) { for (*match = 0; ; (*match)++) { char c = match_name[*match]; - char u = var_name[*match]; - /* Wildcard in the matching name means we've matched */ - if (c == '*') + switch (c) { + case '*': + /* Wildcard in @match_name means we've matched. */ return true; - /* Case sensitive match */ - if (!c && *match == len) - return true; + case '\0': + /* @match_name has ended. Has @var_name too? */ + return (*match == len); - if (c != u) + default: + /* + * We've reached a non-wildcard char in @match_name. + * Continue only if there's an identical character in + * @var_name. + */ + if (*match < len && c == var_name[*match]) + continue; return false; - - if (!c) - return true; + } } - return true; } bool From f4e7de63ab273b6a5e35c82eb4fc6363c855ddd4 Mon Sep 17 00:00:00 2001 From: Doug Ledford Date: Fri, 22 Apr 2016 20:14:58 -0400 Subject: [PATCH 058/181] IB/core: Fix oops in ib_cache_gid_set_default_gid When we fail to find the default gid index, we can't continue processing in this routine or else we will pass a negative index to later routines resulting in invalid memory access attempts and a kernel oops. Fixes: 03db3a2d81e6 (IB/core: Add RoCE GID table management) Signed-off-by: Doug Ledford --- drivers/infiniband/core/cache.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index cb00d59da456..c2e257d97eff 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -691,7 +691,8 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port, NULL); /* Coudn't find default GID location */ - WARN_ON(ix < 0); + if (WARN_ON(ix < 0)) + goto release; zattr_type.gid_type = gid_type; From 707e59ba494372a90d245f18b0c78982caa88e48 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Fri, 22 Apr 2016 13:05:31 +0100 Subject: [PATCH 059/181] xen/qspinlock: Don't kick CPU if IRQ is not initialized The following commit: 1fb3a8b2cfb2 ("xen/spinlock: Fix locking path engaging too soon under PVHVM.") ... moved the initalization of the kicker interrupt until after native_cpu_up() is called. However, when using qspinlocks, a CPU may try to kick another CPU that is spinning (because it has not yet initialized its kicker interrupt), resulting in the following crash during boot: kernel BUG at /build/linux-Ay7j_C/linux-4.4.0/drivers/xen/events/events_base.c:1210! invalid opcode: 0000 [#1] SMP ... RIP: 0010:[] [] xen_send_IPI_one+0x59/0x60 ... Call Trace: [] xen_qlock_kick+0xe/0x10 [] __pv_queued_spin_unlock+0xb2/0xf0 [] ? __raw_callee_save___pv_queued_spin_unlock+0x11/0x20 [] ? check_tsc_warp+0x76/0x150 [] check_tsc_sync_source+0x96/0x160 [] native_cpu_up+0x3d8/0x9f0 [] xen_hvm_cpu_up+0x35/0x80 [] _cpu_up+0x13c/0x180 [] cpu_up+0x7a/0xa0 [] smp_init+0x7f/0x81 [] kernel_init_freeable+0xef/0x212 [] ? rest_init+0x80/0x80 [] kernel_init+0xe/0xe0 [] ret_from_fork+0x3f/0x70 [] ? rest_init+0x80/0x80 To fix this, only send the kick if the target CPU's interrupt has been initialized. This check isn't racy, because the target is waiting for the spinlock, so it won't have initialized the interrupt in the meantime. Signed-off-by: Ross Lagerwall Reviewed-by: Boris Ostrovsky Cc: David Vrabel Cc: Juergen Gross Cc: Konrad Rzeszutek Wilk Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Cc: xen-devel@lists.xenproject.org Signed-off-by: Ingo Molnar --- arch/x86/xen/spinlock.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 9e2ba5c6e1dd..f42e78de1e10 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -27,6 +27,12 @@ static bool xen_pvspin = true; static void xen_qlock_kick(int cpu) { + int irq = per_cpu(lock_kicker_irq, cpu); + + /* Don't kick if the target's kicker interrupt is not initialized. */ + if (irq == -1) + return; + xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); } From b89c173788c3a8ed571652c203bf59a0e9d700aa Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 15 Apr 2016 13:25:33 -0700 Subject: [PATCH 060/181] perf/x86/intel: Add model number for Skylake Server to perf Everything the same as base Skylake, just a new model number. Signed-off-by: Andi Kleen Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/1460751933-2264-1-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 68fa55b4d42e..aff79884e17d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3639,6 +3639,7 @@ __init int intel_pmu_init(void) case 78: /* 14nm Skylake Mobile */ case 94: /* 14nm Skylake Desktop */ + case 85: /* 14nm Skylake Server */ x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); From e1089602a3bf3efd13d0ffc575f3e22213f009da Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Sun, 17 Apr 2016 08:43:29 -0700 Subject: [PATCH 061/181] perf/x86/intel/rapl: Add missing Haswell model Added one missing Haswell model. Signed-off-by: Srinivas Pandruvada Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: bp@alien8.de Cc: hpa@zytor.com Link: http://lkml.kernel.org/r/1460907809-11897-1-git-send-email-srinivas.pandruvada@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/rapl.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 70c93f9b03ac..1705c9d75e44 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -718,6 +718,7 @@ static int __init rapl_pmu_init(void) break; case 60: /* Haswell */ case 69: /* Haswell-Celeron */ + case 70: /* Haswell GT3e */ case 61: /* Broadwell */ case 71: /* Broadwell-H */ rapl_cntr_mask = RAPL_IDX_HSW; From b303e7c15d53cd8ef6b349b702e07eee3f102792 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 4 Apr 2016 09:57:40 +0200 Subject: [PATCH 062/181] perf/core: Make sysctl_perf_cpu_time_max_percent conform to documentation Markus reported that 0 should also disable the throttling we per Documentation/sysctl/kernel.txt. Reported-by: Markus Trippelsdorf Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: 91a612eea9a3 ("perf/core: Fix dynamic interrupt throttle") Signed-off-by: Ingo Molnar --- kernel/events/core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 52bedc5a5aaa..2c78b6f47339 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -412,7 +412,8 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, if (ret || !write) return ret; - if (sysctl_perf_cpu_time_max_percent == 100) { + if (sysctl_perf_cpu_time_max_percent == 100 || + sysctl_perf_cpu_time_max_percent == 0) { printk(KERN_WARNING "perf: Dynamic interrupt throttling disabled, can hang your system!\n"); WRITE_ONCE(perf_sample_allowed_ns, 0); From c24697566298df04cac9913e0601501b5ee2b3f5 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 16 Feb 2016 13:57:40 +0800 Subject: [PATCH 063/181] locking/lockdep: Fix ->irq_context calculation task_irq_context() returns the encoded irq_context of the task, the return value is encoded in the same as ->irq_context of held_lock. Always return 0 if !(CONFIG_TRACE_IRQFLAGS && CONFIG_PROVE_LOCKING) Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Josh Triplett Cc: Lai Jiangshan Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Cc: sasha.levin@oracle.com Link: http://lkml.kernel.org/r/1455602265-16490-2-git-send-email-boqun.feng@gmail.com Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index ed9410936a22..beb06f604420 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2932,6 +2932,11 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock) return 1; } +static inline unsigned int task_irq_context(struct task_struct *task) +{ + return 2 * !!task->hardirq_context + !!task->softirq_context; +} + static int separate_irq_context(struct task_struct *curr, struct held_lock *hlock) { @@ -2940,8 +2945,6 @@ static int separate_irq_context(struct task_struct *curr, /* * Keep track of points where we cross into an interrupt context: */ - hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) + - curr->softirq_context; if (depth) { struct held_lock *prev_hlock; @@ -2973,6 +2976,11 @@ static inline int mark_irqflags(struct task_struct *curr, return 1; } +static inline unsigned int task_irq_context(struct task_struct *task) +{ + return 0; +} + static inline int separate_irq_context(struct task_struct *curr, struct held_lock *hlock) { @@ -3241,6 +3249,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, hlock->acquire_ip = ip; hlock->instance = lock; hlock->nest_lock = nest_lock; + hlock->irq_context = task_irq_context(curr); hlock->trylock = trylock; hlock->read = read; hlock->check = check; From 75dd602a5198a6e5f75534db52b6e6fbaabb33d1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 30 Mar 2016 11:36:59 +0200 Subject: [PATCH 064/181] lockdep: Fix lock_chain::base size lock_chain::base is used to store an index into the chain_hlocks[] array, however that array contains more elements than can be indexed using the u16. Change the lock_chain structure to use a bitfield to encode the data it needs and add BUILD_BUG_ON() assertions to check the fields are wide enough. Also, for DEBUG_LOCKDEP, assert that we don't run out of elements of that array; as that would wreck the collision detectoring. Signed-off-by: Peter Zijlstra (Intel) Cc: Alfredo Alvarez Fernandez Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Sedat Dilek Cc: Theodore Ts'o Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160330093659.GS3408@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 8 +++++--- kernel/locking/lockdep.c | 24 +++++++++++++++++++++++- kernel/locking/lockdep_proc.c | 2 ++ 3 files changed, 30 insertions(+), 4 deletions(-) diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index d026b190c530..d10ef06971b5 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -196,9 +196,11 @@ struct lock_list { * We record lock dependency chains, so that we can cache them: */ struct lock_chain { - u8 irq_context; - u8 depth; - u16 base; + /* see BUILD_BUG_ON()s in lookup_chain_cache() */ + unsigned int irq_context : 2, + depth : 6, + base : 24; + /* 4 byte hole */ struct hlist_node entry; u64 chain_key; }; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index beb06f604420..78c1c0ee6dc1 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2176,15 +2176,37 @@ cache_hit: chain->irq_context = hlock->irq_context; i = get_first_held_lock(curr, hlock); chain->depth = curr->lockdep_depth + 1 - i; + + BUILD_BUG_ON((1UL << 24) <= ARRAY_SIZE(chain_hlocks)); + BUILD_BUG_ON((1UL << 6) <= ARRAY_SIZE(curr->held_locks)); + BUILD_BUG_ON((1UL << 8*sizeof(chain_hlocks[0])) <= ARRAY_SIZE(lock_classes)); + if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { chain->base = nr_chain_hlocks; - nr_chain_hlocks += chain->depth; for (j = 0; j < chain->depth - 1; j++, i++) { int lock_id = curr->held_locks[i].class_idx - 1; chain_hlocks[chain->base + j] = lock_id; } chain_hlocks[chain->base + j] = class - lock_classes; } + + if (nr_chain_hlocks < MAX_LOCKDEP_CHAIN_HLOCKS) + nr_chain_hlocks += chain->depth; + +#ifdef CONFIG_DEBUG_LOCKDEP + /* + * Important for check_no_collision(). + */ + if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) { + if (debug_locks_off_graph_unlock()) + return 0; + + print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!"); + dump_stack(); + return 0; + } +#endif + hlist_add_head_rcu(&chain->entry, hash_head); debug_atomic_inc(chain_lookup_misses); inc_chains(); diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index dbb61a302548..a0f61effad25 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -141,6 +141,8 @@ static int lc_show(struct seq_file *m, void *v) int i; if (v == SEQ_START_TOKEN) { + if (nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS) + seq_printf(m, "(buggered) "); seq_printf(m, "all lock chains:\n"); return 0; } From 56896ef5b990a3822da45f92e548c4c8ac301bb4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 15 Apr 2016 19:30:46 +0900 Subject: [PATCH 065/181] arm64: dts: uniphier: fix I2C nodes of PH1-LD20 The I2C hardware blocks on this SoC are connected as follows: I2C0: external connection I2C1: external connection I2C2: internal connection I2C3: external connection I2C4: external connection I2C5: internal connection I2C6: no connection (not accessible) Delete pinctrl from Ch2, add pinctrl to Ch4, and remove the Ch6 node. Signed-off-by: Masahiro Yamada Signed-off-by: Arnd Bergmann --- .../dts/socionext/uniphier-ph1-ld20-ref.dts | 1 - .../boot/dts/socionext/uniphier-ph1-ld20.dtsi | 20 +++++-------------- 2 files changed, 5 insertions(+), 16 deletions(-) diff --git a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20-ref.dts index 727ae5f8c4e7..b0ed44313a5b 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20-ref.dts +++ b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20-ref.dts @@ -70,7 +70,6 @@ i2c3 = &i2c3; i2c4 = &i2c4; i2c5 = &i2c5; - i2c6 = &i2c6; }; }; diff --git a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi index e682a3f52791..651c9d9d2d54 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi +++ b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi @@ -201,15 +201,12 @@ i2c2: i2c@58782000 { compatible = "socionext,uniphier-fi2c"; - status = "disabled"; reg = <0x58782000 0x80>; #address-cells = <1>; #size-cells = <0>; interrupts = <0 43 4>; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_i2c2>; clocks = <&i2c_clk>; - clock-frequency = <100000>; + clock-frequency = <400000>; }; i2c3: i2c@58783000 { @@ -227,12 +224,15 @@ i2c4: i2c@58784000 { compatible = "socionext,uniphier-fi2c"; + status = "disabled"; reg = <0x58784000 0x80>; #address-cells = <1>; #size-cells = <0>; interrupts = <0 45 4>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c4>; clocks = <&i2c_clk>; - clock-frequency = <400000>; + clock-frequency = <100000>; }; i2c5: i2c@58785000 { @@ -245,16 +245,6 @@ clock-frequency = <400000>; }; - i2c6: i2c@58786000 { - compatible = "socionext,uniphier-fi2c"; - reg = <0x58786000 0x80>; - #address-cells = <1>; - #size-cells = <0>; - interrupts = <0 26 4>; - clocks = <&i2c_clk>; - clock-frequency = <400000>; - }; - system_bus: system-bus@58c00000 { compatible = "socionext,uniphier-system-bus"; status = "disabled"; From f75cfbaddeef943aed479b80415c3dcc63ff4247 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 21 Apr 2016 13:13:56 +0300 Subject: [PATCH 066/181] MAINTAINERS: net: add entry for TI Ethernet Switch drivers Add record for TI Ethernet Switch Driver CPSW/CPDMA/MDIO HW (am33/am43/am57/dr7/davinci) to ensure that related patches will go through dedicated linux-omap list. Also add Mugunthan as maintainer and myself as the reviewer. Cc: "David S. Miller" Cc: Tony Lindgren Cc: Mugunthan V N Cc: Richard Cochran Signed-off-by: Grygorii Strashko Acked-by: Mugunthan V N Acked-by: Tony Lindgren Signed-off-by: David S. Miller --- MAINTAINERS | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 1d5b4becab6f..849133608da7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11071,6 +11071,15 @@ S: Maintained F: drivers/clk/ti/ F: include/linux/clk/ti.h +TI ETHERNET SWITCH DRIVER (CPSW) +M: Mugunthan V N +R: Grygorii Strashko +L: linux-omap@vger.kernel.org +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/ti/cpsw* +F: drivers/net/ethernet/ti/davinci* + TI FLASH MEDIA INTERFACE DRIVER M: Alex Dubov S: Maintained From 7ceb2afbd6aee4643056b47156baad6841db8e78 Mon Sep 17 00:00:00 2001 From: Elad Raz Date: Thu, 21 Apr 2016 12:52:43 +0200 Subject: [PATCH 067/181] switchdev: Adding complete operation to deferred switchdev ops When using switchdev deferred operation (SWITCHDEV_F_DEFER), the operation is executed in different context and the application doesn't have any way to get the operation real status. Adding a completion callback fixes that. This patch adds fields to switchdev_attr and switchdev_obj "complete_priv" field which is used by the "complete" callback. Application can set a complete function which will be called once the operation executed. Signed-off-by: Elad Raz Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/switchdev.h | 4 ++++ net/switchdev/switchdev.c | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d451122e8404..51d77b2ce2b2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -54,6 +54,8 @@ struct switchdev_attr { struct net_device *orig_dev; enum switchdev_attr_id id; u32 flags; + void *complete_priv; + void (*complete)(struct net_device *dev, int err, void *priv); union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ @@ -75,6 +77,8 @@ struct switchdev_obj { struct net_device *orig_dev; enum switchdev_obj_id id; u32 flags; + void *complete_priv; + void (*complete)(struct net_device *dev, int err, void *priv); }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 2b9b98f1c2ff..b7e01d88bdc5 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -305,6 +305,8 @@ static void switchdev_port_attr_set_deferred(struct net_device *dev, if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n", err, attr->id); + if (attr->complete) + attr->complete(dev, err, attr->complete_priv); } static int switchdev_port_attr_set_defer(struct net_device *dev, @@ -434,6 +436,8 @@ static void switchdev_port_obj_add_deferred(struct net_device *dev, if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to add object (id=%d)\n", err, obj->id); + if (obj->complete) + obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_add_defer(struct net_device *dev, @@ -502,6 +506,8 @@ static void switchdev_port_obj_del_deferred(struct net_device *dev, if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to del object (id=%d)\n", err, obj->id); + if (obj->complete) + obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_del_defer(struct net_device *dev, From 6dd684c0feb207f30180570bad24264b922d9476 Mon Sep 17 00:00:00 2001 From: Elad Raz Date: Thu, 21 Apr 2016 12:52:44 +0200 Subject: [PATCH 068/181] bridge: mdb: Common function for mdb entry translation There is duplicate code that translates br_mdb_entry to br_ip let's wrap it in a common function. Signed-off-by: Elad Raz Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_mdb.c | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 253bc77eda3b..b258120e1145 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -61,6 +61,19 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags) e->flags |= MDB_FLAGS_OFFLOAD; } +static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip) +{ + memset(ip, 0, sizeof(struct br_ip)); + ip->vid = entry->vid; + ip->proto = entry->addr.proto; + if (ip->proto == htons(ETH_P_IP)) + ip->u.ip4 = entry->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + else + ip->u.ip6 = entry->addr.u.ip6; +#endif +} + static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { @@ -509,15 +522,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; - memset(&ip, 0, sizeof(ip)); - ip.vid = entry->vid; - ip.proto = entry->addr.proto; - if (ip.proto == htons(ETH_P_IP)) - ip.u.ip4 = entry->addr.u.ip4; -#if IS_ENABLED(CONFIG_IPV6) - else - ip.u.ip6 = entry->addr.u.ip6; -#endif + __mdb_entry_to_br_ip(entry, &ip); spin_lock_bh(&br->multicast_lock); ret = br_mdb_add_group(br, p, &ip, entry->state, pg); @@ -584,15 +589,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (!netif_running(br->dev) || br->multicast_disabled) return -EINVAL; - memset(&ip, 0, sizeof(ip)); - ip.vid = entry->vid; - ip.proto = entry->addr.proto; - if (ip.proto == htons(ETH_P_IP)) - ip.u.ip4 = entry->addr.u.ip4; -#if IS_ENABLED(CONFIG_IPV6) - else - ip.u.ip6 = entry->addr.u.ip6; -#endif + __mdb_entry_to_br_ip(entry, &ip); spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); From 45ebcce56823d14d196dbdecd26783b3d5f464a6 Mon Sep 17 00:00:00 2001 From: Elad Raz Date: Thu, 21 Apr 2016 12:52:45 +0200 Subject: [PATCH 069/181] bridge: mdb: Marking port-group as offloaded There is a race-condition when updating the mdb offload flag without using the mulicast_lock. This reverts commit 9e8430f8d60d98 ("bridge: mdb: Passing the port-group pointer to br_mdb module"). This patch marks offloaded MDB entry as "offload" by changing the port- group flags and marks it as MDB_PG_FLAGS_OFFLOAD. When switchdev PORT_MDB succeeded and adds a multicast group, a completion callback is been invoked "br_mdb_complete". The completion function locks the multicast_lock and finds the right net_bridge_port_group and marks it as offloaded. Fixes: 9e8430f8d60d98 ("bridge: mdb: Passing the port-group pointer to br_mdb module") Reported-by: Nikolay Aleksandrov Signed-off-by: Elad Raz Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_mdb.c | 91 +++++++++++++++++++++++++++------------ net/bridge/br_multicast.c | 8 ++-- net/bridge/br_private.h | 4 +- 3 files changed, 71 insertions(+), 32 deletions(-) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index b258120e1145..7dbc80d01eb0 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -256,9 +256,45 @@ static inline size_t rtnl_mdb_nlmsg_size(void) + nla_total_size(sizeof(struct br_mdb_entry)); } -static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, - int type, struct net_bridge_port_group *pg) +struct br_mdb_complete_info { + struct net_bridge_port *port; + struct br_ip ip; +}; + +static void br_mdb_complete(struct net_device *dev, int err, void *priv) { + struct br_mdb_complete_info *data = priv; + struct net_bridge_port_group __rcu **pp; + struct net_bridge_port_group *p; + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port *port = data->port; + struct net_bridge *br = port->br; + + if (err) + goto err; + + spin_lock_bh(&br->multicast_lock); + mdb = mlock_dereference(br->mdb, br); + mp = br_mdb_ip_get(mdb, &data->ip); + if (!mp) + goto out; + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port != port) + continue; + p->flags |= MDB_PG_FLAGS_OFFLOAD; + } +out: + spin_unlock_bh(&br->multicast_lock); +err: + kfree(priv); +} + +static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, + struct br_mdb_entry *entry, int type) +{ + struct br_mdb_complete_info *complete_info; struct switchdev_obj_port_mdb mdb = { .obj = { .id = SWITCHDEV_OBJ_ID_PORT_MDB, @@ -281,9 +317,14 @@ static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, mdb.obj.orig_dev = port_dev; if (port_dev && type == RTM_NEWMDB) { - err = switchdev_port_obj_add(port_dev, &mdb.obj); - if (!err && pg) - pg->flags |= MDB_PG_FLAGS_OFFLOAD; + complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); + if (complete_info) { + complete_info->port = p; + __mdb_entry_to_br_ip(entry, &complete_info->ip); + mdb.obj.complete_priv = complete_info; + mdb.obj.complete = br_mdb_complete; + switchdev_port_obj_add(port_dev, &mdb.obj); + } } else if (port_dev && type == RTM_DELMDB) { switchdev_port_obj_del(port_dev, &mdb.obj); } @@ -304,21 +345,21 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } -void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg, - int type) +void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type, u8 flags) { struct br_mdb_entry entry; memset(&entry, 0, sizeof(entry)); - entry.ifindex = pg->port->dev->ifindex; - entry.addr.proto = pg->addr.proto; - entry.addr.u.ip4 = pg->addr.u.ip4; + entry.ifindex = port->dev->ifindex; + entry.addr.proto = group->proto; + entry.addr.u.ip4 = group->u.ip4; #if IS_ENABLED(CONFIG_IPV6) - entry.addr.u.ip6 = pg->addr.u.ip6; + entry.addr.u.ip6 = group->u.ip6; #endif - entry.vid = pg->addr.vid; - __mdb_entry_fill_flags(&entry, pg->flags); - __br_mdb_notify(dev, &entry, type, pg); + entry.vid = group->vid; + __mdb_entry_fill_flags(&entry, flags); + __br_mdb_notify(dev, port, &entry, type); } static int nlmsg_populate_rtr_fill(struct sk_buff *skb, @@ -463,8 +504,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, } static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, - struct br_ip *group, unsigned char state, - struct net_bridge_port_group **pg) + struct br_ip *group, unsigned char state) { struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; @@ -495,7 +535,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); - *pg = p; if (state == MDB_TEMPORARY) mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -503,8 +542,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, } static int __br_mdb_add(struct net *net, struct net_bridge *br, - struct br_mdb_entry *entry, - struct net_bridge_port_group **pg) + struct br_mdb_entry *entry) { struct br_ip ip; struct net_device *dev; @@ -525,7 +563,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, __mdb_entry_to_br_ip(entry, &ip); spin_lock_bh(&br->multicast_lock); - ret = br_mdb_add_group(br, p, &ip, entry->state, pg); + ret = br_mdb_add_group(br, p, &ip, entry->state); spin_unlock_bh(&br->multicast_lock); return ret; } @@ -533,7 +571,6 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - struct net_bridge_port_group *pg; struct net_bridge_vlan_group *vg; struct net_device *dev, *pdev; struct br_mdb_entry *entry; @@ -563,15 +600,15 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) if (br_vlan_enabled(br) && vg && entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; - err = __br_mdb_add(net, br, entry, &pg); + err = __br_mdb_add(net, br, entry); if (err) break; - __br_mdb_notify(dev, entry, RTM_NEWMDB, pg); + __br_mdb_notify(dev, p, entry, RTM_NEWMDB); } } else { - err = __br_mdb_add(net, br, entry, &pg); + err = __br_mdb_add(net, br, entry); if (!err) - __br_mdb_notify(dev, entry, RTM_NEWMDB, pg); + __br_mdb_notify(dev, p, entry, RTM_NEWMDB); } return err; @@ -659,12 +696,12 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) entry->vid = v->vid; err = __br_mdb_del(br, entry); if (!err) - __br_mdb_notify(dev, entry, RTM_DELMDB, NULL); + __br_mdb_notify(dev, p, entry, RTM_DELMDB); } } else { err = __br_mdb_del(br, entry); if (!err) - __br_mdb_notify(dev, entry, RTM_DELMDB, NULL); + __br_mdb_notify(dev, p, entry, RTM_DELMDB); } return err; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index a4c15df2b792..191ea66e4d92 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -283,7 +283,8 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); - br_mdb_notify(br->dev, p, RTM_DELMDB); + br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB, + p->flags); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && @@ -705,7 +706,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); - br_mdb_notify(br->dev, p, RTM_NEWMDB); + br_mdb_notify(br->dev, port, group, RTM_NEWMDB, 0); found: mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -1461,7 +1462,8 @@ br_multicast_leave_group(struct net_bridge *br, hlist_del_init(&p->mglist); del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - br_mdb_notify(br->dev, p, RTM_DELMDB); + br_mdb_notify(br->dev, port, group, RTM_DELMDB, + p->flags); if (!mp->ports && !mp->mglist && netif_running(br->dev)) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1b5d145dfcbf..d9da857182ef 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -560,8 +560,8 @@ br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, unsigned char flags); void br_mdb_init(void); void br_mdb_uninit(void); -void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg, - int type); +void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type, u8 flags); void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, int type); From 72f2a05b8f367ee0d75584a6fbec7dbe7c144f27 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:01 +0200 Subject: [PATCH 070/181] macsec: add missing NULL check after kmalloc Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: Dan Carpenter Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/macsec.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 84d3e5ca8817..f691030ee3df 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1622,8 +1622,8 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) } rx_sa = kmalloc(sizeof(*rx_sa), GFP_KERNEL); - if (init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, - secy->icv_len)) { + if (!rx_sa || init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), + secy->key_len, secy->icv_len)) { rtnl_unlock(); return -ENOMEM; } From c10c63ea739bce3b8a6ab85c7bb472d900c9b070 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:02 +0200 Subject: [PATCH 071/181] macsec: take rtnl lock before for_each_netdev Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: Johannes Berg Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/macsec.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index f691030ee3df..5f3ea8026074 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2268,8 +2268,6 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, if (!hdr) return -EMSGSIZE; - rtnl_lock(); - if (nla_put_u32(skb, MACSEC_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -2429,14 +2427,11 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, nla_nest_end(skb, rxsc_list); - rtnl_unlock(); - genlmsg_end(skb, hdr); return 0; nla_put_failure: - rtnl_unlock(); genlmsg_cancel(skb, hdr); return -EMSGSIZE; } @@ -2450,6 +2445,7 @@ static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) dev_idx = cb->args[0]; d = 0; + rtnl_lock(); for_each_netdev(net, dev) { struct macsec_secy *secy; @@ -2467,6 +2463,7 @@ next: } done: + rtnl_unlock(); cb->args[0] = d; return skb->len; } From 497f358aa4c0d99b75ec204407389920d5e33ec5 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:03 +0200 Subject: [PATCH 072/181] macsec: don't put a NULL rxsa The "deliver:" path of macsec_handle_frame can be called with rx_sa == NULL. Check rx_sa != NULL before calling macsec_rxsa_put(). Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/macsec.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 5f3ea8026074..2a2136b7d324 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1161,7 +1161,8 @@ deliver: macsec_extra_len(macsec_skb_cb(skb)->has_sci)); macsec_reset_skb(skb, secy->netdev); - macsec_rxsa_put(rx_sa); + if (rx_sa) + macsec_rxsa_put(rx_sa); count_rx(dev, skb->len); rcu_read_unlock(); From c3b7d0bd7ac2c501d4806db71ddd383c184968e8 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:04 +0200 Subject: [PATCH 073/181] macsec: fix rx_sa refcounting with decrypt callback The decrypt callback macsec_decrypt_done needs a reference on the rx_sa and releases it before returning, but macsec_handle_frame already put that reference after macsec_decrypt returned NULL. Set rx_sa to NULL when the decrypt callback runs so that macsec_handle_frame knows it must not release the reference. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/macsec.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 2a2136b7d324..1fd2b147fda1 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -880,12 +880,12 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, macsec_skb_cb(skb)->valid = false; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) - return NULL; + return ERR_PTR(-ENOMEM); req = aead_request_alloc(rx_sa->key.tfm, GFP_ATOMIC); if (!req) { kfree_skb(skb); - return NULL; + return ERR_PTR(-ENOMEM); } hdr = (struct macsec_eth_header *)skb->data; @@ -905,7 +905,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) { aead_request_free(req); - return NULL; + return ERR_PTR(-ENOMEM); } } else { /* integrity only: all headers + data authenticated */ @@ -921,14 +921,14 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, dev_hold(dev); ret = crypto_aead_decrypt(req); if (ret == -EINPROGRESS) { - return NULL; + return ERR_PTR(ret); } else if (ret != 0) { /* decryption/authentication failed * 10.6 if validateFrames is disabled, deliver anyway */ if (ret != -EBADMSG) { kfree_skb(skb); - skb = NULL; + skb = ERR_PTR(ret); } } else { macsec_skb_cb(skb)->valid = true; @@ -1146,8 +1146,10 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) secy->validate_frames != MACSEC_VALIDATE_DISABLED) skb = macsec_decrypt(skb, dev, rx_sa, sci, secy); - if (!skb) { - macsec_rxsa_put(rx_sa); + if (IS_ERR(skb)) { + /* the decrypt callback needs the reference */ + if (PTR_ERR(skb) != -EINPROGRESS) + macsec_rxsa_put(rx_sa); rcu_read_unlock(); *pskb = NULL; return RX_HANDLER_CONSUMED; From 96cfc5052c5d434563873caa7707b32b9e389b16 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:05 +0200 Subject: [PATCH 074/181] macsec: add consistency check to netlink dumps Use genl_dump_check_consistent in dump_secy. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Suggested-by: Johannes Berg Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/macsec.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 1fd2b147fda1..41fbe556ba6d 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2271,6 +2271,8 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, if (!hdr) return -EMSGSIZE; + genl_dump_check_consistent(cb, hdr, &macsec_fam); + if (nla_put_u32(skb, MACSEC_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -2439,6 +2441,8 @@ nla_put_failure: return -EMSGSIZE; } +static int macsec_generation = 1; /* protected by RTNL */ + static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -2449,6 +2453,9 @@ static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) d = 0; rtnl_lock(); + + cb->seq = macsec_generation; + for_each_netdev(net, dev) { struct macsec_secy *secy; @@ -2920,6 +2927,8 @@ static void macsec_dellink(struct net_device *dev, struct list_head *head) struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); + macsec_generation++; + unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); if (list_empty(&rxd->secys)) @@ -3066,6 +3075,8 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (err < 0) goto del_dev; + macsec_generation++; + dev_hold(real_dev); return 0; From 960d5848dbf1245cc3a310109897937207411c0c Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:06 +0200 Subject: [PATCH 075/181] macsec: fix memory leaks around rx_handler (un)registration We leak a struct macsec_rxh_data when we unregister the rx_handler in macsec_dellink. We also leak a struct macsec_rxh_data in register_macsec_dev if we fail to register the rx_handler. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/macsec.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 41fbe556ba6d..826c6c9ce7fd 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2931,8 +2931,10 @@ static void macsec_dellink(struct net_device *dev, struct list_head *head) unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); - if (list_empty(&rxd->secys)) + if (list_empty(&rxd->secys)) { netdev_rx_handler_unregister(real_dev); + kfree(rxd); + } macsec_del_dev(macsec); } @@ -2954,8 +2956,10 @@ static int register_macsec_dev(struct net_device *real_dev, err = netdev_rx_handler_register(real_dev, macsec_handle_frame, rxd); - if (err < 0) + if (err < 0) { + kfree(rxd); return err; + } } list_add_tail_rcu(&macsec->secys, &rxd->secys); From 38787fc209580f9b5918e93e71da7c960dbb5d8d Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:07 +0200 Subject: [PATCH 076/181] macsec: fix SA leak if initialization fails Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: Lance Richardson Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/macsec.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 826c6c9ce7fd..b37d348b8ea0 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1627,6 +1627,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) rx_sa = kmalloc(sizeof(*rx_sa), GFP_KERNEL); if (!rx_sa || init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len)) { + kfree(rx_sa); rtnl_unlock(); return -ENOMEM; } @@ -1771,6 +1772,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) tx_sa = kmalloc(sizeof(*tx_sa), GFP_KERNEL); if (!tx_sa || init_tx_sa(tx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len)) { + kfree(tx_sa); rtnl_unlock(); return -ENOMEM; } From 748164802c1bd2c52937d20782b07d8c68dd9a4f Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:08 +0200 Subject: [PATCH 077/181] macsec: add missing macsec prefix in uapi I accidentally forgot some MACSEC_ prefixes in if_macsec.h. Fixes: dece8d2b78d1 ("uapi: add MACsec bits") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/macsec.c | 12 +++++++----- include/uapi/linux/if_macsec.h | 4 ++-- 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index b37d348b8ea0..9f63cc7b0a73 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2232,7 +2232,8 @@ static int nla_put_secy(struct macsec_secy *secy, struct sk_buff *skb) return 1; if (nla_put_sci(skb, MACSEC_SECY_ATTR_SCI, secy->sci) || - nla_put_u64(skb, MACSEC_SECY_ATTR_CIPHER_SUITE, DEFAULT_CIPHER_ID) || + nla_put_u64(skb, MACSEC_SECY_ATTR_CIPHER_SUITE, + MACSEC_DEFAULT_CIPHER_ID) || nla_put_u8(skb, MACSEC_SECY_ATTR_ICV_LEN, secy->icv_len) || nla_put_u8(skb, MACSEC_SECY_ATTR_OPER, secy->operational) || nla_put_u8(skb, MACSEC_SECY_ATTR_PROTECT, secy->protect_frames) || @@ -3096,7 +3097,7 @@ unregister: static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) { - u64 csid = DEFAULT_CIPHER_ID; + u64 csid = MACSEC_DEFAULT_CIPHER_ID; u8 icv_len = DEFAULT_ICV_LEN; int flag; bool es, scb, sci; @@ -3111,8 +3112,8 @@ static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); switch (csid) { - case DEFAULT_CIPHER_ID: - case DEFAULT_CIPHER_ALT: + case MACSEC_DEFAULT_CIPHER_ID: + case MACSEC_DEFAULT_CIPHER_ALT: if (icv_len < MACSEC_MIN_ICV_LEN || icv_len > MACSEC_MAX_ICV_LEN) return -EINVAL; @@ -3185,7 +3186,8 @@ static int macsec_fill_info(struct sk_buff *skb, if (nla_put_sci(skb, IFLA_MACSEC_SCI, secy->sci) || nla_put_u8(skb, IFLA_MACSEC_ICV_LEN, secy->icv_len) || - nla_put_u64(skb, IFLA_MACSEC_CIPHER_SUITE, DEFAULT_CIPHER_ID) || + nla_put_u64(skb, IFLA_MACSEC_CIPHER_SUITE, + MACSEC_DEFAULT_CIPHER_ID) || nla_put_u8(skb, IFLA_MACSEC_ENCODING_SA, tx_sc->encoding_sa) || nla_put_u8(skb, IFLA_MACSEC_ENCRYPT, tx_sc->encrypt) || nla_put_u8(skb, IFLA_MACSEC_PROTECT, secy->protect_frames) || diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h index 26b0d1e3e3e7..4c58d9917aa4 100644 --- a/include/uapi/linux/if_macsec.h +++ b/include/uapi/linux/if_macsec.h @@ -19,8 +19,8 @@ #define MACSEC_MAX_KEY_LEN 128 -#define DEFAULT_CIPHER_ID 0x0080020001000001ULL -#define DEFAULT_CIPHER_ALT 0x0080C20001000001ULL +#define MACSEC_DEFAULT_CIPHER_ID 0x0080020001000001ULL +#define MACSEC_DEFAULT_CIPHER_ALT 0x0080C20001000001ULL #define MACSEC_MIN_ICV_LEN 8 #define MACSEC_MAX_ICV_LEN 32 From 4b1fb9352f351faa067a914907d58a6fe38ac048 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:09 +0200 Subject: [PATCH 078/181] macsec: fix netlink attribute validation macsec_validate_attr should check IFLA_MACSEC_REPLAY_PROTECT (not IFLA_MACSEC_PROTECT) to verify that the replay protection and replay window arguments are correct. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- drivers/net/macsec.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 9f63cc7b0a73..c6385617bfb2 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3147,8 +3147,8 @@ static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) nla_get_u8(data[IFLA_MACSEC_VALIDATION]) > MACSEC_VALIDATE_MAX) return -EINVAL; - if ((data[IFLA_MACSEC_PROTECT] && - nla_get_u8(data[IFLA_MACSEC_PROTECT])) && + if ((data[IFLA_MACSEC_REPLAY_PROTECT] && + nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT])) && !data[IFLA_MACSEC_WINDOW]) return -EINVAL; From 3c201b5a84edd6ee2f9a8548efaa813980839b46 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 21 Apr 2016 14:11:50 +0200 Subject: [PATCH 079/181] net: stmmac: socfpga: Remove re-registration of reset controller Both socfpga_dwmac_parse_data() in dwmac-socfpga.c and stmmac_dvr_probe() in stmmac_main.c functions call devm_reset_control_get() to register an reset controller for the stmmac. This results in an attempt to register two reset controllers for the same non-shared reset line. The first attempt to register the reset controller works fine. The second attempt fails with warning from the reset controller core, see below. The warning is produced because the reset line is non-shared and thus it is allowed to have only up-to one reset controller associated with that reset line, not two or more. The solution has multiple parts. First, the original socfpga_dwmac_init() is tweaked to use reset controller pointer from the stmmac_priv (private data of the stmmac core) instead of the local instance, which was used before. The local re-registration of the reset controller is removed. Next, the socfpga_dwmac_init() is moved after stmmac_dvr_probe() in the probe function. This order is legal according to Altera and it makes the code much easier, since there is no need to temporarily register and unregister the reset controller ; the reset controller is already registered by the stmmac_dvr_probe(). Finally, plat_dat->exit and socfpga_dwmac_exit() is no longer necessary, since the functionality is already performed by the stmmac core. ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at drivers/reset/core.c:187 __of_reset_control_get+0x218/0x270 Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.6.0-rc4-next-20160419-00015-gabb2477-dirty #4 Hardware name: Altera SOCFPGA [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [] (show_stack) from [] (dump_stack+0x94/0xa8) [] (dump_stack) from [] (__warn+0xec/0x104) [] (__warn) from [] (warn_slowpath_null+0x20/0x28) [] (warn_slowpath_null) from [] (__of_reset_control_get+0x218/0x270) [] (__of_reset_control_get) from [] (__devm_reset_control_get+0x54/0x90) [] (__devm_reset_control_get) from [] (stmmac_dvr_probe+0x1b4/0x8e8) [] (stmmac_dvr_probe) from [] (socfpga_dwmac_probe+0x1b8/0x28c) [] (socfpga_dwmac_probe) from [] (platform_drv_probe+0x4c/0xb0) [] (platform_drv_probe) from [] (driver_probe_device+0x224/0x2bc) [] (driver_probe_device) from [] (__driver_attach+0xac/0xb0) [] (__driver_attach) from [] (bus_for_each_dev+0x6c/0xa0) [] (bus_for_each_dev) from [] (bus_add_driver+0x1a4/0x21c) [] (bus_add_driver) from [] (driver_register+0x78/0xf8) [] (driver_register) from [] (do_one_initcall+0x40/0x170) [] (do_one_initcall) from [] (kernel_init_freeable+0x1dc/0x27c) [] (kernel_init_freeable) from [] (kernel_init+0x8/0x114) [] (kernel_init) from [] (ret_from_fork+0x14/0x3c) ---[ end trace 059d2fbe87608fa9 ]--- Signed-off-by: Marek Vasut Cc: Matthew Gerlach Cc: Dinh Nguyen Cc: David S. Miller Tested-by: Dinh Nguyen Signed-off-by: David S. Miller --- .../ethernet/stmicro/stmmac/dwmac-socfpga.c | 50 ++++++------------- 1 file changed, 16 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 44022b1845ce..afb90d129cb6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -49,7 +49,6 @@ struct socfpga_dwmac { u32 reg_shift; struct device *dev; struct regmap *sys_mgr_base_addr; - struct reset_control *stmmac_rst; void __iomem *splitter_base; bool f2h_ptp_ref_clk; }; @@ -92,15 +91,6 @@ static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device * struct device_node *np_splitter; struct resource res_splitter; - dwmac->stmmac_rst = devm_reset_control_get(dev, - STMMAC_RESOURCE_NAME); - if (IS_ERR(dwmac->stmmac_rst)) { - dev_info(dev, "Could not get reset control!\n"); - if (PTR_ERR(dwmac->stmmac_rst) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dwmac->stmmac_rst = NULL; - } - dwmac->interface = of_get_phy_mode(np); sys_mgr_base_addr = syscon_regmap_lookup_by_phandle(np, "altr,sysmgr-syscon"); @@ -194,30 +184,23 @@ static int socfpga_dwmac_setup(struct socfpga_dwmac *dwmac) return 0; } -static void socfpga_dwmac_exit(struct platform_device *pdev, void *priv) -{ - struct socfpga_dwmac *dwmac = priv; - - /* On socfpga platform exit, assert and hold reset to the - * enet controller - the default state after a hard reset. - */ - if (dwmac->stmmac_rst) - reset_control_assert(dwmac->stmmac_rst); -} - static int socfpga_dwmac_init(struct platform_device *pdev, void *priv) { - struct socfpga_dwmac *dwmac = priv; + struct socfpga_dwmac *dwmac = priv; struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *stpriv = NULL; int ret = 0; - if (ndev) - stpriv = netdev_priv(ndev); + if (!ndev) + return -EINVAL; + + stpriv = netdev_priv(ndev); + if (!stpriv) + return -EINVAL; /* Assert reset to the enet controller before changing the phy mode */ - if (dwmac->stmmac_rst) - reset_control_assert(dwmac->stmmac_rst); + if (stpriv->stmmac_rst) + reset_control_assert(stpriv->stmmac_rst); /* Setup the phy mode in the system manager registers according to * devicetree configuration @@ -227,8 +210,8 @@ static int socfpga_dwmac_init(struct platform_device *pdev, void *priv) /* Deassert reset for the phy configuration to be sampled by * the enet controller, and operation to start in requested mode */ - if (dwmac->stmmac_rst) - reset_control_deassert(dwmac->stmmac_rst); + if (stpriv->stmmac_rst) + reset_control_deassert(stpriv->stmmac_rst); /* Before the enet controller is suspended, the phy is suspended. * This causes the phy clock to be gated. The enet controller is @@ -245,7 +228,7 @@ static int socfpga_dwmac_init(struct platform_device *pdev, void *priv) * control register 0, and can be modified by the phy driver * framework. */ - if (stpriv && stpriv->phydev) + if (stpriv->phydev) phy_resume(stpriv->phydev); return ret; @@ -285,14 +268,13 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) plat_dat->bsp_priv = dwmac; plat_dat->init = socfpga_dwmac_init; - plat_dat->exit = socfpga_dwmac_exit; plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed; - ret = socfpga_dwmac_init(pdev, plat_dat->bsp_priv); - if (ret) - return ret; + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (!ret) + ret = socfpga_dwmac_init(pdev, dwmac); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + return ret; } static const struct of_device_id socfpga_dwmac_match[] = { From 45c78e0219405af1b0f31b06952dfd9bcf7ad1f6 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Thu, 21 Apr 2016 13:25:20 -0400 Subject: [PATCH 080/181] qlcnic: Update version to 5.3.64 Just updating the version as many fixes got accumulated over 5.3.63 Signed-off-by: Manish Chopra Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qlcnic/qlcnic.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 55007f1e6bbc..caf6ddb7ea76 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -37,8 +37,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 3 -#define _QLCNIC_LINUX_SUBVERSION 63 -#define QLCNIC_LINUX_VERSIONID "5.3.63" +#define _QLCNIC_LINUX_SUBVERSION 64 +#define QLCNIC_LINUX_VERSIONID "5.3.64" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) From c3f9bf628bc7edda298897d952f5e761137229c9 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Fri, 22 Apr 2016 00:33:00 +0300 Subject: [PATCH 081/181] net/mlx5_core: Fix soft lockup in steering error flow In the error flow of adding flow rule to auto-grouped flow table, we call to tree_remove_node. tree_remove_node locks the node's parent, however the node's parent is already locked by mlx5_add_flow_rule and this causes a deadlock. After this patch, if we failed to add the flow rule, we unlock the flow table before calling to tree_remove_node. fixes: f0d22d187473 ('net/mlx5_core: Introduce flow steering autogrouped flow table') Signed-off-by: Maor Gottlieb Reported-by: Amir Vadai Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 46 +++++++------------ 1 file changed, 17 insertions(+), 29 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5121be4675d1..3c7e3e581835 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1065,33 +1065,6 @@ unlock_fg: return rule; } -static struct mlx5_flow_rule *add_rule_to_auto_fg(struct mlx5_flow_table *ft, - u8 match_criteria_enable, - u32 *match_criteria, - u32 *match_value, - u8 action, - u32 flow_tag, - struct mlx5_flow_destination *dest) -{ - struct mlx5_flow_rule *rule; - struct mlx5_flow_group *g; - - g = create_autogroup(ft, match_criteria_enable, match_criteria); - if (IS_ERR(g)) - return (void *)g; - - rule = add_rule_fg(g, match_value, - action, flow_tag, dest); - if (IS_ERR(rule)) { - /* Remove assumes refcount > 0 and autogroup creates a group - * with a refcount = 0. - */ - tree_get_node(&g->node); - tree_remove_node(&g->node); - } - return rule; -} - static struct mlx5_flow_rule * _mlx5_add_flow_rule(struct mlx5_flow_table *ft, u8 match_criteria_enable, @@ -1119,8 +1092,23 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft, goto unlock; } - rule = add_rule_to_auto_fg(ft, match_criteria_enable, match_criteria, - match_value, action, flow_tag, dest); + g = create_autogroup(ft, match_criteria_enable, match_criteria); + if (IS_ERR(g)) { + rule = (void *)g; + goto unlock; + } + + rule = add_rule_fg(g, match_value, + action, flow_tag, dest); + if (IS_ERR(rule)) { + /* Remove assumes refcount > 0 and autogroup creates a group + * with a refcount = 0. + */ + unlock_ref_node(&ft->node); + tree_get_node(&g->node); + tree_remove_node(&g->node); + return rule; + } unlock: unlock_ref_node(&ft->node); return rule; From 6e4c21894673baabdbef03c3ac2458a28246128b Mon Sep 17 00:00:00 2001 From: Rana Shahout Date: Fri, 22 Apr 2016 00:33:01 +0300 Subject: [PATCH 082/181] net/mlx5e: Fix MLX5E_100BASE_T define Bit 25 of eth_proto_capability in PTYS register is 1000Base-TT and not 100Base-T. Fixes: f62b8bb8f2d3 ('net/mlx5: Extend mlx5_core to support ConnectX-4 Ethernet functionality') Signed-off-by: Rana Shahout Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 879e6276c473..e80ce94b5dcf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -609,7 +609,7 @@ enum mlx5e_link_mode { MLX5E_100GBASE_KR4 = 22, MLX5E_100GBASE_LR4 = 23, MLX5E_100BASE_TX = 24, - MLX5E_100BASE_T = 25, + MLX5E_1000BASE_T = 25, MLX5E_10GBASE_T = 26, MLX5E_25GBASE_CR = 27, MLX5E_25GBASE_KR = 28, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 68834b715f6c..3476ab844634 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -138,10 +138,10 @@ static const struct { [MLX5E_100BASE_TX] = { .speed = 100, }, - [MLX5E_100BASE_T] = { - .supported = SUPPORTED_100baseT_Full, - .advertised = ADVERTISED_100baseT_Full, - .speed = 100, + [MLX5E_1000BASE_T] = { + .supported = SUPPORTED_1000baseT_Full, + .advertised = ADVERTISED_1000baseT_Full, + .speed = 1000, }, [MLX5E_10GBASE_T] = { .supported = SUPPORTED_10000baseT_Full, From 64dbbdfef245f67504ec403a5aebfcc7b92bd8c1 Mon Sep 17 00:00:00 2001 From: Majd Dibbiny Date: Fri, 22 Apr 2016 00:33:02 +0300 Subject: [PATCH 083/181] net/mlx5_core: Add ConnectX-5 to list of supported devices Add the upcoming ConnectX-5 devices (PF and VF) to the list of supported devices by the mlx5 driver. Signed-off-by: Majd Dibbiny Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 3f3b2fae4991..ddd352ae3dbd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1459,6 +1459,8 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1014), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4 VF */ { PCI_VDEVICE(MELLANOX, 0x1015) }, /* ConnectX-4LX */ { PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4LX VF */ + { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5 */ + { PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */ { 0, } }; From 046339eaab26804f52f6604877f5674f70815b26 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 22 Apr 2016 00:33:03 +0300 Subject: [PATCH 084/181] net/mlx5e: Device's mtu field is u16 and not int For set/query MTU port firmware commands the MTU field is 16 bits, here I changed all the "int mtu" parameters of the functions wrapping those firmware commands to be u16. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx5/main.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/port.c | 10 +++++----- include/linux/mlx5/port.h | 6 +++--- 4 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5acf346e048e..99eb1c1a3b7b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -671,8 +671,8 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port, struct mlx5_ib_dev *dev = to_mdev(ibdev); struct mlx5_core_dev *mdev = dev->mdev; struct mlx5_hca_vport_context *rep; - int max_mtu; - int oper_mtu; + u16 max_mtu; + u16 oper_mtu; int err; u8 ib_link_width_oper; u8 vl_hw_cap; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e0adb604f461..2fbbc625f106 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1408,7 +1408,7 @@ static int mlx5e_set_dev_port_mtu(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; - int hw_mtu; + u16 hw_mtu; int err; err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1); @@ -2004,7 +2004,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; bool was_opened; - int max_mtu; + u16 max_mtu; int err = 0; mlx5_query_port_max_mtu(mdev, &max_mtu, 1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index ae378c575deb..53cc1e2c693b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -247,8 +247,8 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, } EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status); -static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu, - int *max_mtu, int *oper_mtu, u8 port) +static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, u16 *admin_mtu, + u16 *max_mtu, u16 *oper_mtu, u8 port) { u32 in[MLX5_ST_SZ_DW(pmtu_reg)]; u32 out[MLX5_ST_SZ_DW(pmtu_reg)]; @@ -268,7 +268,7 @@ static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu, *admin_mtu = MLX5_GET(pmtu_reg, out, admin_mtu); } -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port) +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port) { u32 in[MLX5_ST_SZ_DW(pmtu_reg)]; u32 out[MLX5_ST_SZ_DW(pmtu_reg)]; @@ -283,14 +283,14 @@ int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port) } EXPORT_SYMBOL_GPL(mlx5_set_port_mtu); -void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port) { mlx5_query_port_mtu(dev, NULL, max_mtu, NULL, port); } EXPORT_SYMBOL_GPL(mlx5_query_port_max_mtu); -void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, u8 port) { mlx5_query_port_mtu(dev, NULL, NULL, oper_mtu, port); diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index a1d145abd4eb..b30250ab7604 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -54,9 +54,9 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status *status); -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); -void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); -void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port); +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port); +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, u8 port); int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, From d8edd2469ace550db707798180d1c84d81f93bca Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 22 Apr 2016 00:33:04 +0300 Subject: [PATCH 085/181] net/mlx5e: Fix minimum MTU Minimum MTU that can be set in Connectx4 device is 68. This fixes the case where a user wants to set invalid MTU, the driver will fail to satisfy this request and the interface will stay down. It is better to report an error and continue working with old mtu. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2fbbc625f106..93e4ef43fa9f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1999,22 +1999,27 @@ static int mlx5e_set_features(struct net_device *netdev, return err; } +#define MXL5_HW_MIN_MTU 64 +#define MXL5E_MIN_MTU (MXL5_HW_MIN_MTU + ETH_FCS_LEN) + static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; bool was_opened; u16 max_mtu; + u16 min_mtu; int err = 0; mlx5_query_port_max_mtu(mdev, &max_mtu, 1); max_mtu = MLX5E_HW2SW_MTU(max_mtu); + min_mtu = MLX5E_HW2SW_MTU(MXL5E_MIN_MTU); - if (new_mtu > max_mtu) { + if (new_mtu > max_mtu || new_mtu < min_mtu) { netdev_err(netdev, - "%s: Bad MTU (%d) > (%d) Max\n", - __func__, new_mtu, max_mtu); + "%s: Bad MTU (%d), valid range is: [%d..%d]\n", + __func__, new_mtu, min_mtu, max_mtu); return -EINVAL; } From cd255efff9baadd654d6160e52d17ae7c568c9d3 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 22 Apr 2016 00:33:05 +0300 Subject: [PATCH 086/181] net/mlx5e: Use vport MTU rather than physical port MTU Set and report vport MTU rather than physical MTU, Driver will set both vport and physical port mtu and will rely on the query of vport mtu. SRIOV VFs have to report their MTU to their vport manager (PF), and this will allow them to work with any MTU they need without failing the request. Also for some cases where the PF is not a port owner, PF can work with MTU less than the physical port mtu if set physical port mtu didn't take effect. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 44 +++++++++++++++---- .../net/ethernet/mellanox/mlx5/core/vport.c | 40 +++++++++++++++++ include/linux/mlx5/vport.h | 2 + 3 files changed, 77 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 93e4ef43fa9f..85773f8573e5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1404,24 +1404,50 @@ static int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5e_priv *priv) return 0; } -static int mlx5e_set_dev_port_mtu(struct net_device *netdev) +static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu) { - struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; - u16 hw_mtu; + u16 hw_mtu = MLX5E_SW2HW_MTU(mtu); int err; - err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1); + err = mlx5_set_port_mtu(mdev, hw_mtu, 1); if (err) return err; - mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1); + /* Update vport context MTU */ + mlx5_modify_nic_vport_mtu(mdev, hw_mtu); + return 0; +} - if (MLX5E_HW2SW_MTU(hw_mtu) != netdev->mtu) - netdev_warn(netdev, "%s: Port MTU %d is different than netdev mtu %d\n", - __func__, MLX5E_HW2SW_MTU(hw_mtu), netdev->mtu); +static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u16 hw_mtu = 0; + int err; - netdev->mtu = MLX5E_HW2SW_MTU(hw_mtu); + err = mlx5_query_nic_vport_mtu(mdev, &hw_mtu); + if (err || !hw_mtu) /* fallback to port oper mtu */ + mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1); + + *mtu = MLX5E_HW2SW_MTU(hw_mtu); +} + +static int mlx5e_set_dev_port_mtu(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + u16 mtu; + int err; + + err = mlx5e_set_mtu(priv, netdev->mtu); + if (err) + return err; + + mlx5e_query_mtu(priv, &mtu); + if (mtu != netdev->mtu) + netdev_warn(netdev, "%s: VPort MTU %d is different than netdev mtu %d\n", + __func__, mtu, netdev->mtu); + + netdev->mtu = mtu; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index bd518405859e..b69dadcfb897 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -196,6 +196,46 @@ int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev, } EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_address); +int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu) +{ + int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + u32 *out; + int err; + + out = mlx5_vzalloc(outlen); + if (!out) + return -ENOMEM; + + err = mlx5_query_nic_vport_context(mdev, 0, out, outlen); + if (!err) + *mtu = MLX5_GET(query_nic_vport_context_out, out, + nic_vport_context.mtu); + + kvfree(out); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_mtu); + +int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu) +{ + int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); + void *in; + int err; + + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + MLX5_SET(modify_nic_vport_context_in, in, field_select.mtu, 1); + MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.mtu, mtu); + + err = mlx5_modify_nic_vport_context(mdev, in, inlen); + + kvfree(in); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu); + int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, u32 vport, enum mlx5_list_type list_type, diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index bd93e6323603..301da4a5e6bf 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -45,6 +45,8 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u16 vport, u8 *addr); int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, u16 vport, u8 *addr); +int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu); +int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); From 78228cbdeb0aa5c96e2a721e7e0d6953b416b5a3 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Fri, 22 Apr 2016 00:33:06 +0300 Subject: [PATCH 087/181] net/mlx5_core: Remove static from local variable The static is not required and breaks re-entrancy if it will be required. Fixes: 2530236303d9 ("net/mlx5_core: Flow steering tree initialization") Signed-off-by: Eli Cohen Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3c7e3e581835..89cce97d46c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1276,7 +1276,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, { struct mlx5_flow_root_namespace *root_ns = dev->priv.root_ns; int prio; - static struct fs_prio *fs_prio; + struct fs_prio *fs_prio; struct mlx5_flow_namespace *ns; if (!root_ns) From 5fc7197d3a256d9c5de3134870304b24892a4908 Mon Sep 17 00:00:00 2001 From: Majd Dibbiny Date: Fri, 22 Apr 2016 00:33:07 +0300 Subject: [PATCH 088/181] net/mlx5: Add pci shutdown callback This patch introduces kexec support for mlx5. When switching kernels, kexec() calls shutdown, which unloads the driver and cleans its resources. In addition, remove unregister netdev from shutdown flow. This will allow a clean shutdown, even if some netdev clients did not release their reference from this netdev. Releasing The HW resources only is enough as the kernel is shutting down Signed-off-by: Majd Dibbiny Signed-off-by: Tariq Toukan Signed-off-by: Haggai Abramovsky Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 15 ++++++++++-- .../net/ethernet/mellanox/mlx5/core/main.c | 23 +++++++++++++++---- include/linux/mlx5/driver.h | 7 +++--- 3 files changed, 36 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 85773f8573e5..67d548b70e14 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2633,7 +2633,16 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) schedule_work(&priv->set_rx_mode_work); mlx5e_disable_async_events(priv); flush_scheduled_work(); - unregister_netdev(netdev); + if (test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) { + netif_device_detach(netdev); + mutex_lock(&priv->state_lock); + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_close_locked(netdev); + mutex_unlock(&priv->state_lock); + } else { + unregister_netdev(netdev); + } + mlx5e_tc_cleanup(priv); mlx5e_vxlan_cleanup(priv); mlx5e_destroy_flow_tables(priv); @@ -2646,7 +2655,9 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) mlx5_core_dealloc_transport_domain(priv->mdev, priv->tdn); mlx5_core_dealloc_pd(priv->mdev, priv->pdn); mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar); - free_netdev(netdev); + + if (!test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) + free_netdev(netdev); } static void *mlx5e_get_netdev(void *vpriv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index ddd352ae3dbd..6892746fd10d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -966,7 +966,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) int err; mutex_lock(&dev->intf_state_mutex); - if (dev->interface_state == MLX5_INTERFACE_STATE_UP) { + if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n", __func__); goto out; @@ -1133,7 +1133,8 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) if (err) pr_info("failed request module on %s\n", MLX5_IB_MOD); - dev->interface_state = MLX5_INTERFACE_STATE_UP; + clear_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state); + set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); out: mutex_unlock(&dev->intf_state_mutex); @@ -1207,7 +1208,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) } mutex_lock(&dev->intf_state_mutex); - if (dev->interface_state == MLX5_INTERFACE_STATE_DOWN) { + if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n", __func__); goto out; @@ -1241,7 +1242,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_cmd_cleanup(dev); out: - dev->interface_state = MLX5_INTERFACE_STATE_DOWN; + clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); + set_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state); mutex_unlock(&dev->intf_state_mutex); return err; } @@ -1452,6 +1454,18 @@ static const struct pci_error_handlers mlx5_err_handler = { .resume = mlx5_pci_resume }; +static void shutdown(struct pci_dev *pdev) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + struct mlx5_priv *priv = &dev->priv; + + dev_info(&pdev->dev, "Shutdown was called\n"); + /* Notify mlx5 clients that the kernel is being shut down */ + set_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &dev->intf_state); + mlx5_unload_one(dev, priv); + mlx5_pci_disable_device(dev); +} + static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1011) }, /* Connect-IB */ { PCI_VDEVICE(MELLANOX, 0x1012), MLX5_PCI_DEV_IS_VF}, /* Connect-IB VF */ @@ -1471,6 +1485,7 @@ static struct pci_driver mlx5_core_driver = { .id_table = mlx5_core_pci_table, .probe = init_one, .remove = remove_one, + .shutdown = shutdown, .err_handler = &mlx5_err_handler, .sriov_configure = mlx5_core_sriov_configure, }; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index dcd5ac8d3b14..369c837d40f5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -519,8 +519,9 @@ enum mlx5_device_state { }; enum mlx5_interface_state { - MLX5_INTERFACE_STATE_DOWN, - MLX5_INTERFACE_STATE_UP, + MLX5_INTERFACE_STATE_DOWN = BIT(0), + MLX5_INTERFACE_STATE_UP = BIT(1), + MLX5_INTERFACE_STATE_SHUTDOWN = BIT(2), }; enum mlx5_pci_status { @@ -544,7 +545,7 @@ struct mlx5_core_dev { enum mlx5_device_state state; /* sync interface state */ struct mutex intf_state_mutex; - enum mlx5_interface_state interface_state; + unsigned long intf_state; void (*event) (struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); From 94862a62dfe3ba1c7601115a2dc80721c5b256f0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 21 Apr 2016 20:57:47 +0200 Subject: [PATCH 089/181] Revert "cpufreq: governor: Fix negative idle_time when configured with CONFIG_HZ_PERIODIC" Revert commit 0df35026c6a5 (cpufreq: governor: Fix negative idle_time when configured with CONFIG_HZ_PERIODIC) that introduced a regression by causing the ondemand cpufreq governor to misbehave for CONFIG_TICK_CPU_ACCOUNTING unset (the frequency goes up to the max at one point and stays there indefinitely). The revert takes subsequent modifications of the code in question into account. Fixes: 0df35026c6a5 (cpufreq: governor: Fix negative idle_time when configured with CONFIG_HZ_PERIODIC) Link: https://bugzilla.kernel.org/show_bug.cgi?id=115261 Reported-and-tested-by: Timo Valtoaho Cc: 4.5+ # 4.5+ Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- drivers/cpufreq/cpufreq_governor.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 10a5cfeae8c5..5f1147fa9239 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -193,12 +193,8 @@ unsigned int dbs_update(struct cpufreq_policy *policy) wall_time = cur_wall_time - j_cdbs->prev_cpu_wall; j_cdbs->prev_cpu_wall = cur_wall_time; - if (cur_idle_time <= j_cdbs->prev_cpu_idle) { - idle_time = 0; - } else { - idle_time = cur_idle_time - j_cdbs->prev_cpu_idle; - j_cdbs->prev_cpu_idle = cur_idle_time; - } + idle_time = cur_idle_time - j_cdbs->prev_cpu_idle; + j_cdbs->prev_cpu_idle = cur_idle_time; if (ignore_nice) { u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE]; From 391a20333b8393ef2e13014e6e59d192c5594471 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 21 Apr 2016 22:23:31 +0200 Subject: [PATCH 090/181] ipv4/fib: don't warn when primary address is missing if in_dev is dead After commit fbd40ea0180a ("ipv4: Don't do expensive useless work during inetdev destroy.") when deleting an interface, fib_del_ifaddr() can be executed without any primary address present on the dead interface. The above is safe, but triggers some "bug: prim == NULL" warnings. This commit avoids warning if the in_dev is dead Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/ipv4/fib_frontend.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 8a9246deccfe..63566ec54794 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -904,7 +904,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { - pr_warn("%s: bug: prim == NULL\n", __func__); + /* if the device has been deleted, we don't perform + * address promotion + */ + if (!in_dev->dead) + pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { From da67e68c0e4601e87612918496fd8c7d72795e50 Mon Sep 17 00:00:00 2001 From: Eric Engestrom Date: Mon, 25 Apr 2016 01:24:04 +0100 Subject: [PATCH 091/181] Documentation: dt: arc: fix spelling mistakes Signed-off-by: Eric Engestrom Signed-off-by: Vineet Gupta --- Documentation/devicetree/bindings/arc/archs-pct.txt | 2 +- Documentation/devicetree/bindings/arc/pct.txt | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/arc/archs-pct.txt b/Documentation/devicetree/bindings/arc/archs-pct.txt index 1ae98b87c640..e4b9dcee6d41 100644 --- a/Documentation/devicetree/bindings/arc/archs-pct.txt +++ b/Documentation/devicetree/bindings/arc/archs-pct.txt @@ -2,7 +2,7 @@ The ARC HS can be configured with a pipeline performance monitor for counting CPU and cache events like cache misses and hits. Like conventional PCT there -are 100+ hardware conditions dynamically mapped to upto 32 counters. +are 100+ hardware conditions dynamically mapped to up to 32 counters. It also supports overflow interrupts. Required properties: diff --git a/Documentation/devicetree/bindings/arc/pct.txt b/Documentation/devicetree/bindings/arc/pct.txt index 7b9588444f20..4e874d9a38a6 100644 --- a/Documentation/devicetree/bindings/arc/pct.txt +++ b/Documentation/devicetree/bindings/arc/pct.txt @@ -2,7 +2,7 @@ The ARC700 can be configured with a pipeline performance monitor for counting CPU and cache events like cache misses and hits. Like conventional PCT there -are 100+ hardware conditions dynamically mapped to upto 32 counters +are 100+ hardware conditions dynamically mapped to up to 32 counters Note that: * The ARC 700 PCT does not support interrupts; although HW events may be From 3020ca711871fdaf0c15c8bab677a6bc302e28fe Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 22 Apr 2016 04:00:50 -0300 Subject: [PATCH 092/181] [media] v4l2-dv-timings.h: fix polarity for 4k formats The VSync polarity was negative instead of positive for the 4k CEA formats. I probably copy-and-pasted these from the DMT 4k format, which does have a negative VSync polarity. Signed-off-by: Hans Verkuil Reported-by: Martin Bugge Cc: # for v4.1 and up Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/v4l2-dv-timings.h | 30 ++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/include/uapi/linux/v4l2-dv-timings.h b/include/uapi/linux/v4l2-dv-timings.h index c039f1d68a09..086168e18ca8 100644 --- a/include/uapi/linux/v4l2-dv-timings.h +++ b/include/uapi/linux/v4l2-dv-timings.h @@ -183,7 +183,8 @@ #define V4L2_DV_BT_CEA_3840X2160P24 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1276, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -191,14 +192,16 @@ #define V4L2_DV_BT_CEA_3840X2160P25 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_3840X2160P30 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -206,14 +209,16 @@ #define V4L2_DV_BT_CEA_3840X2160P50 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_3840X2160P60 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -221,7 +226,8 @@ #define V4L2_DV_BT_CEA_4096X2160P24 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1020, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -229,14 +235,16 @@ #define V4L2_DV_BT_CEA_4096X2160P25 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_4096X2160P30 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -244,14 +252,16 @@ #define V4L2_DV_BT_CEA_4096X2160P50 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_4096X2160P60 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ From b93876845c5e30a92964eeb088d9d2e024118022 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Mon, 25 Apr 2016 06:04:45 -0300 Subject: [PATCH 093/181] [media] media: vb2: Fix regression on poll() for RW mode When using a device is read/write mode, vb2 does not handle properly the first select/poll operation. The reason for this, is that when this code has been refactored, some of the operations have changed their order, and now fileio emulator is not started. The reintroduced check to the core is enabled by a quirk flag, that avoids this check by other subsystems like DVB. Fixes: 49d8ab9feaf2 ("media] media: videobuf2: Separate vb2_poll()") Reported-by: Dimitrios Katsaros Cc: Junghak Sung Cc: # for v4.5 and up Signed-off-by: Ricardo Ribalda Delgado Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/videobuf2-core.c | 10 ++++++++++ drivers/media/v4l2-core/videobuf2-v4l2.c | 14 ++++++-------- include/media/videobuf2-core.h | 4 ++++ 3 files changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index 2169544883e8..9fbcb67a9ee6 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -2297,6 +2297,16 @@ unsigned int vb2_core_poll(struct vb2_queue *q, struct file *file, if (!vb2_is_streaming(q) || q->error) return POLLERR; + /* + * If this quirk is set and QBUF hasn't been called yet then + * return POLLERR as well. This only affects capture queues, output + * queues will always initialize waiting_for_buffers to false. + * This quirk is set by V4L2 for backwards compatibility reasons. + */ + if (q->quirk_poll_must_check_waiting_for_buffers && + q->waiting_for_buffers && (req_events & (POLLIN | POLLRDNORM))) + return POLLERR; + /* * For output streams you can call write() as long as there are fewer * buffers queued than there are buffers available. diff --git a/drivers/media/v4l2-core/videobuf2-v4l2.c b/drivers/media/v4l2-core/videobuf2-v4l2.c index 8da7470ca364..7f366f1b0377 100644 --- a/drivers/media/v4l2-core/videobuf2-v4l2.c +++ b/drivers/media/v4l2-core/videobuf2-v4l2.c @@ -771,6 +771,12 @@ int vb2_queue_init(struct vb2_queue *q) q->is_output = V4L2_TYPE_IS_OUTPUT(q->type); q->copy_timestamp = (q->timestamp_flags & V4L2_BUF_FLAG_TIMESTAMP_MASK) == V4L2_BUF_FLAG_TIMESTAMP_COPY; + /* + * For compatibility with vb1: if QBUF hasn't been called yet, then + * return POLLERR as well. This only affects capture queues, output + * queues will always initialize waiting_for_buffers to false. + */ + q->quirk_poll_must_check_waiting_for_buffers = true; return vb2_core_queue_init(q); } @@ -824,14 +830,6 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait) poll_wait(file, &fh->wait, wait); } - /* - * For compatibility with vb1: if QBUF hasn't been called yet, then - * return POLLERR as well. This only affects capture queues, output - * queues will always initialize waiting_for_buffers to false. - */ - if (q->waiting_for_buffers && (req_events & (POLLIN | POLLRDNORM))) - return POLLERR; - return res | vb2_core_poll(q, file, wait); } EXPORT_SYMBOL_GPL(vb2_poll); diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 5342ff4d748f..88e3ab496e8f 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -404,6 +404,9 @@ struct vb2_buf_ops { * @fileio_read_once: report EOF after reading the first buffer * @fileio_write_immediately: queue buffer after each write() call * @allow_zero_bytesused: allow bytesused == 0 to be passed to the driver + * @quirk_poll_must_check_waiting_for_buffers: Return POLLERR at poll when QBUF + * has not been called. This is a vb1 idiom that has been adopted + * also by vb2. * @lock: pointer to a mutex that protects the vb2_queue struct. The * driver can set this to a mutex to let the v4l2 core serialize * the queuing ioctls. If the driver wants to handle locking @@ -467,6 +470,7 @@ struct vb2_queue { unsigned fileio_read_once:1; unsigned fileio_write_immediately:1; unsigned allow_zero_bytesused:1; + unsigned quirk_poll_must_check_waiting_for_buffers:1; struct mutex *lock; void *owner; From 89a095668304e8a02502ffd35edacffdbf49aa8c Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Thu, 3 Mar 2016 16:12:48 -0300 Subject: [PATCH 094/181] [media] vb2-memops: Fix over allocation of frame vectors On page unaligned frames, create_framevec forces get_vaddr_frames to allocate an extra page at the end of the buffer. Under some circumstances, this leads to -EINVAL on VIDIOC_QBUF. E.g: We have vm_a that vm_area that goes from 0x1000 to 0x3000. And a frame that goes from 0x1800 to 0x2800, i.e. 2 pages. frame_vector_create will be called with the following params: get_vaddr_frames(0x1800, 2, write, 1, vec); get_vaddr will allocate the first page after checking that the memory 0x1800-0x27ff is valid, but it will not allocate the second page because the range 0x2800-0x37ff is out of the vm_a range. This results in create_framevec returning -EFAULT Error Trace: [ 9083.793015] video0: VIDIOC_QBUF: 00:00:00.00000000 index=1, type=vid-cap, flags=0x00002002, field=any, sequence=0, memory=userptr, bytesused=0, offset/userptr=0x7ff2b023ca80, length=5765760 [ 9083.793028] timecode=00:00:00 type=0, flags=0x00000000, frames=0, userbits=0x00000000 [ 9083.793117] video0: VIDIOC_QBUF: error -22: 00:00:00.00000000 index=2, type=vid-cap, flags=0x00000000, field=any, sequence=0, memory=userptr, bytesused=0, offset/userptr=0x7ff2b07bc500, length=5765760 Also use true instead of 1 since that argument is a bool in the get_vaddr_frames() prototype. Fixes: 21fb0cb7ec65 ("[media] vb2: Provide helpers for mapping virtual addresses") Reported-by: Albert Antony Signed-off-by: Ricardo Ribalda Delgado [hans.verkuil@cisco.com: merged the 'bool' change into this patch] Acked-by: Marek Szyprowski Reviewed-by: Jan Kara Cc: # for v4.3 and up Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/videobuf2-memops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/v4l2-core/videobuf2-memops.c b/drivers/media/v4l2-core/videobuf2-memops.c index dbec5923fcf0..3c3b517f1d1c 100644 --- a/drivers/media/v4l2-core/videobuf2-memops.c +++ b/drivers/media/v4l2-core/videobuf2-memops.c @@ -49,7 +49,7 @@ struct frame_vector *vb2_create_framevec(unsigned long start, vec = frame_vector_create(nr); if (!vec) return ERR_PTR(-ENOMEM); - ret = get_vaddr_frames(start, nr, write, 1, vec); + ret = get_vaddr_frames(start & PAGE_MASK, nr, write, true, vec); if (ret < 0) goto out_destroy; /* We accept only complete set of PFNs */ From a30b8f81d9d6fe24eab8a023794548b048f08e3c Mon Sep 17 00:00:00 2001 From: Azael Avalos Date: Fri, 22 Apr 2016 09:29:36 -0600 Subject: [PATCH 095/181] toshiba_acpi: Fix regression caused by hotkey enabling value Commit 52cbae0127ad ("toshiba_acpi: Change default Hotkey enabling value") changed the hotkeys enabling value, as it was the same value Windows uses, however, it turns out that the value tells the EC that the driver will now take care of the hardware events like the physical RFKill switch or the pointing device toggle button. This patch reverts such commit by changing the default hotkey enabling value to 0x09, which enables hotkey events only, making the hardware buttons working again. Fixes bugs 113331 and 114941. Signed-off-by: Azael Avalos Cc: stable@vger.kernel.org Signed-off-by: Darren Hart --- drivers/platform/x86/toshiba_acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index df1f1a76a862..01e12d221a8b 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -135,7 +135,7 @@ MODULE_LICENSE("GPL"); /* Field definitions */ #define HCI_ACCEL_MASK 0x7fff #define HCI_HOTKEY_DISABLE 0x0b -#define HCI_HOTKEY_ENABLE 0x01 +#define HCI_HOTKEY_ENABLE 0x09 #define HCI_HOTKEY_SPECIAL_FUNCTIONS 0x10 #define HCI_LCD_BRIGHTNESS_BITS 3 #define HCI_LCD_BRIGHTNESS_SHIFT (16-HCI_LCD_BRIGHTNESS_BITS) From 6c1ea260f89709e0021d2c59f8fd2a104b5b1123 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 11 Apr 2016 19:34:49 +0200 Subject: [PATCH 096/181] libceph: make authorizer destruction independent of ceph_auth_client Starting the kernel client with cephx disabled and then enabling cephx and restarting userspace daemons can result in a crash: [262671.478162] BUG: unable to handle kernel paging request at ffffebe000000000 [262671.531460] IP: [] kfree+0x5a/0x130 [262671.584334] PGD 0 [262671.635847] Oops: 0000 [#1] SMP [262672.055841] CPU: 22 PID: 2961272 Comm: kworker/22:2 Not tainted 4.2.0-34-generic #39~14.04.1-Ubuntu [262672.162338] Hardware name: Dell Inc. PowerEdge R720/068CDY, BIOS 2.4.3 07/09/2014 [262672.268937] Workqueue: ceph-msgr con_work [libceph] [262672.322290] task: ffff88081c2d0dc0 ti: ffff880149ae8000 task.ti: ffff880149ae8000 [262672.428330] RIP: 0010:[] [] kfree+0x5a/0x130 [262672.535880] RSP: 0018:ffff880149aeba58 EFLAGS: 00010286 [262672.589486] RAX: 000001e000000000 RBX: 0000000000000012 RCX: ffff8807e7461018 [262672.695980] RDX: 000077ff80000000 RSI: ffff88081af2be04 RDI: 0000000000000012 [262672.803668] RBP: ffff880149aeba78 R08: 0000000000000000 R09: 0000000000000000 [262672.912299] R10: ffffebe000000000 R11: ffff880819a60e78 R12: ffff8800aec8df40 [262673.021769] R13: ffffffffc035f70f R14: ffff8807e5b138e0 R15: ffff880da9785840 [262673.131722] FS: 0000000000000000(0000) GS:ffff88081fac0000(0000) knlGS:0000000000000000 [262673.245377] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [262673.303281] CR2: ffffebe000000000 CR3: 0000000001c0d000 CR4: 00000000001406e0 [262673.417556] Stack: [262673.472943] ffff880149aeba88 ffff88081af2be04 ffff8800aec8df40 ffff88081af2be04 [262673.583767] ffff880149aeba98 ffffffffc035f70f ffff880149aebac8 ffff8800aec8df00 [262673.694546] ffff880149aebac8 ffffffffc035c89e ffff8807e5b138e0 ffff8805b047f800 [262673.805230] Call Trace: [262673.859116] [] ceph_x_destroy_authorizer+0x1f/0x50 [libceph] [262673.968705] [] ceph_auth_destroy_authorizer+0x3e/0x60 [libceph] [262674.078852] [] put_osd+0x45/0x80 [libceph] [262674.134249] [] remove_osd+0xae/0x140 [libceph] [262674.189124] [] __reset_osd+0x103/0x150 [libceph] [262674.243749] [] kick_requests+0x223/0x460 [libceph] [262674.297485] [] ceph_osdc_handle_map+0x282/0x5e0 [libceph] [262674.350813] [] dispatch+0x4e/0x720 [libceph] [262674.403312] [] try_read+0x3d1/0x1090 [libceph] [262674.454712] [] ? dequeue_entity+0x152/0x690 [262674.505096] [] con_work+0xcb/0x1300 [libceph] [262674.555104] [] process_one_work+0x14e/0x3d0 [262674.604072] [] worker_thread+0x11a/0x470 [262674.652187] [] ? rescuer_thread+0x310/0x310 [262674.699022] [] kthread+0xd2/0xf0 [262674.744494] [] ? kthread_create_on_node+0x1c0/0x1c0 [262674.789543] [] ret_from_fork+0x3f/0x70 [262674.834094] [] ? kthread_create_on_node+0x1c0/0x1c0 What happens is the following: (1) new MON session is established (2) old "none" ac is destroyed (3) new "cephx" ac is constructed ... (4) old OSD session (w/ "none" authorizer) is put ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer) osd->o_auth.authorizer in the "none" case is just a bare pointer into ac, which contains a single static copy for all services. By the time we get to (4), "none" ac, freed in (2), is long gone. On top of that, a new vtable installed in (3) points us at ceph_x_destroy_authorizer(), so we end up trying to destroy a "none" authorizer with a "cephx" destructor operating on invalid memory! To fix this, decouple authorizer destruction from ac and do away with a single static "none" authorizer by making a copy for each OSD or MDS session. Authorizers themselves are independent of ac and so there is no reason for destroy_authorizer() to be an ac op. Make it an op on the authorizer itself by turning ceph_authorizer into a real struct. Fixes: http://tracker.ceph.com/issues/15447 Reported-by: Alan Zhang Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- fs/ceph/mds_client.c | 6 +-- include/linux/ceph/auth.h | 10 ++--- include/linux/ceph/osd_client.h | 1 - net/ceph/auth.c | 8 +--- net/ceph/auth_none.c | 71 ++++++++++++++++++--------------- net/ceph/auth_none.h | 3 +- net/ceph/auth_x.c | 21 +++++----- net/ceph/auth_x.h | 1 + net/ceph/osd_client.c | 6 +-- 9 files changed, 62 insertions(+), 65 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 541ead4d8965..85b8517f17a0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -386,9 +386,7 @@ void ceph_put_mds_session(struct ceph_mds_session *s) atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1); if (atomic_dec_and_test(&s->s_ref)) { if (s->s_auth.authorizer) - ceph_auth_destroy_authorizer( - s->s_mdsc->fsc->client->monc.auth, - s->s_auth.authorizer); + ceph_auth_destroy_authorizer(s->s_auth.authorizer); kfree(s); } } @@ -3900,7 +3898,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, struct ceph_auth_handshake *auth = &s->s_auth; if (force_new && auth->authorizer) { - ceph_auth_destroy_authorizer(ac, auth->authorizer); + ceph_auth_destroy_authorizer(auth->authorizer); auth->authorizer = NULL; } if (!auth->authorizer) { diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index 260d78b587c4..1563265d2097 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -12,9 +12,12 @@ */ struct ceph_auth_client; -struct ceph_authorizer; struct ceph_msg; +struct ceph_authorizer { + void (*destroy)(struct ceph_authorizer *); +}; + struct ceph_auth_handshake { struct ceph_authorizer *authorizer; void *authorizer_buf; @@ -62,8 +65,6 @@ struct ceph_auth_client_ops { struct ceph_auth_handshake *auth); int (*verify_authorizer_reply)(struct ceph_auth_client *ac, struct ceph_authorizer *a, size_t len); - void (*destroy_authorizer)(struct ceph_auth_client *ac, - struct ceph_authorizer *a); void (*invalidate_authorizer)(struct ceph_auth_client *ac, int peer_type); @@ -112,8 +113,7 @@ extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac); extern int ceph_auth_create_authorizer(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth); -extern void ceph_auth_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a); +void ceph_auth_destroy_authorizer(struct ceph_authorizer *a); extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *a); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4343df806710..cbf460927c42 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -16,7 +16,6 @@ struct ceph_msg; struct ceph_snap_context; struct ceph_osd_request; struct ceph_osd_client; -struct ceph_authorizer; /* * completion callback for async writepages diff --git a/net/ceph/auth.c b/net/ceph/auth.c index 6b923bcaa2a4..2bc5965fdd1e 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -293,13 +293,9 @@ int ceph_auth_create_authorizer(struct ceph_auth_client *ac, } EXPORT_SYMBOL(ceph_auth_create_authorizer); -void ceph_auth_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a) +void ceph_auth_destroy_authorizer(struct ceph_authorizer *a) { - mutex_lock(&ac->mutex); - if (ac->ops && ac->ops->destroy_authorizer) - ac->ops->destroy_authorizer(ac, a); - mutex_unlock(&ac->mutex); + a->destroy(a); } EXPORT_SYMBOL(ceph_auth_destroy_authorizer); diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c index 8c93fa8d81bc..5f836f02ae36 100644 --- a/net/ceph/auth_none.c +++ b/net/ceph/auth_none.c @@ -16,7 +16,6 @@ static void reset(struct ceph_auth_client *ac) struct ceph_auth_none_info *xi = ac->private; xi->starting = true; - xi->built_authorizer = false; } static void destroy(struct ceph_auth_client *ac) @@ -39,6 +38,27 @@ static int should_authenticate(struct ceph_auth_client *ac) return xi->starting; } +static int ceph_auth_none_build_authorizer(struct ceph_auth_client *ac, + struct ceph_none_authorizer *au) +{ + void *p = au->buf; + void *const end = p + sizeof(au->buf); + int ret; + + ceph_encode_8_safe(&p, end, 1, e_range); + ret = ceph_entity_name_encode(ac->name, &p, end); + if (ret < 0) + return ret; + + ceph_encode_64_safe(&p, end, ac->global_id, e_range); + au->buf_len = p - (void *)au->buf; + dout("%s built authorizer len %d\n", __func__, au->buf_len); + return 0; + +e_range: + return -ERANGE; +} + static int build_request(struct ceph_auth_client *ac, void *buf, void *end) { return 0; @@ -57,32 +77,32 @@ static int handle_reply(struct ceph_auth_client *ac, int result, return result; } +static void ceph_auth_none_destroy_authorizer(struct ceph_authorizer *a) +{ + kfree(a); +} + /* - * build an 'authorizer' with our entity_name and global_id. we can - * reuse a single static copy since it is identical for all services - * we connect to. + * build an 'authorizer' with our entity_name and global_id. it is + * identical for all services we connect to. */ static int ceph_auth_none_create_authorizer( struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth) { - struct ceph_auth_none_info *ai = ac->private; - struct ceph_none_authorizer *au = &ai->au; - void *p, *end; + struct ceph_none_authorizer *au; int ret; - if (!ai->built_authorizer) { - p = au->buf; - end = p + sizeof(au->buf); - ceph_encode_8(&p, 1); - ret = ceph_entity_name_encode(ac->name, &p, end - 8); - if (ret < 0) - goto bad; - ceph_decode_need(&p, end, sizeof(u64), bad2); - ceph_encode_64(&p, ac->global_id); - au->buf_len = p - (void *)au->buf; - ai->built_authorizer = true; - dout("built authorizer len %d\n", au->buf_len); + au = kmalloc(sizeof(*au), GFP_NOFS); + if (!au) + return -ENOMEM; + + au->base.destroy = ceph_auth_none_destroy_authorizer; + + ret = ceph_auth_none_build_authorizer(ac, au); + if (ret) { + kfree(au); + return ret; } auth->authorizer = (struct ceph_authorizer *) au; @@ -92,17 +112,6 @@ static int ceph_auth_none_create_authorizer( auth->authorizer_reply_buf_len = sizeof (au->reply_buf); return 0; - -bad2: - ret = -ERANGE; -bad: - return ret; -} - -static void ceph_auth_none_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a) -{ - /* nothing to do */ } static const struct ceph_auth_client_ops ceph_auth_none_ops = { @@ -114,7 +123,6 @@ static const struct ceph_auth_client_ops ceph_auth_none_ops = { .build_request = build_request, .handle_reply = handle_reply, .create_authorizer = ceph_auth_none_create_authorizer, - .destroy_authorizer = ceph_auth_none_destroy_authorizer, }; int ceph_auth_none_init(struct ceph_auth_client *ac) @@ -127,7 +135,6 @@ int ceph_auth_none_init(struct ceph_auth_client *ac) return -ENOMEM; xi->starting = true; - xi->built_authorizer = false; ac->protocol = CEPH_AUTH_NONE; ac->private = xi; diff --git a/net/ceph/auth_none.h b/net/ceph/auth_none.h index 059a3ce4b53f..62021535ae4a 100644 --- a/net/ceph/auth_none.h +++ b/net/ceph/auth_none.h @@ -12,6 +12,7 @@ */ struct ceph_none_authorizer { + struct ceph_authorizer base; char buf[128]; int buf_len; char reply_buf[0]; @@ -19,8 +20,6 @@ struct ceph_none_authorizer { struct ceph_auth_none_info { bool starting; - bool built_authorizer; - struct ceph_none_authorizer au; /* we only need one; it's static */ }; int ceph_auth_none_init(struct ceph_auth_client *ac); diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 9e43a315e662..a0905f04bd13 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -565,6 +565,14 @@ static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result, return -EAGAIN; } +static void ceph_x_destroy_authorizer(struct ceph_authorizer *a) +{ + struct ceph_x_authorizer *au = (void *)a; + + ceph_x_authorizer_cleanup(au); + kfree(au); +} + static int ceph_x_create_authorizer( struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth) @@ -581,6 +589,8 @@ static int ceph_x_create_authorizer( if (!au) return -ENOMEM; + au->base.destroy = ceph_x_destroy_authorizer; + ret = ceph_x_build_authorizer(ac, th, au); if (ret) { kfree(au); @@ -643,16 +653,6 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, return ret; } -static void ceph_x_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a) -{ - struct ceph_x_authorizer *au = (void *)a; - - ceph_x_authorizer_cleanup(au); - kfree(au); -} - - static void ceph_x_reset(struct ceph_auth_client *ac) { struct ceph_x_info *xi = ac->private; @@ -770,7 +770,6 @@ static const struct ceph_auth_client_ops ceph_x_ops = { .create_authorizer = ceph_x_create_authorizer, .update_authorizer = ceph_x_update_authorizer, .verify_authorizer_reply = ceph_x_verify_authorizer_reply, - .destroy_authorizer = ceph_x_destroy_authorizer, .invalidate_authorizer = ceph_x_invalidate_authorizer, .reset = ceph_x_reset, .destroy = ceph_x_destroy, diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h index 40b1a3cf7397..21a5af904bae 100644 --- a/net/ceph/auth_x.h +++ b/net/ceph/auth_x.h @@ -26,6 +26,7 @@ struct ceph_x_ticket_handler { struct ceph_x_authorizer { + struct ceph_authorizer base; struct ceph_crypto_key session_key; struct ceph_buffer *buf; unsigned int service; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 32355d9d0103..40a53a70efdf 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1087,10 +1087,8 @@ static void put_osd(struct ceph_osd *osd) dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref), atomic_read(&osd->o_ref) - 1); if (atomic_dec_and_test(&osd->o_ref)) { - struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth; - if (osd->o_auth.authorizer) - ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer); + ceph_auth_destroy_authorizer(osd->o_auth.authorizer); kfree(osd); } } @@ -2984,7 +2982,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, struct ceph_auth_handshake *auth = &o->o_auth; if (force_new && auth->authorizer) { - ceph_auth_destroy_authorizer(ac, auth->authorizer); + ceph_auth_destroy_authorizer(auth->authorizer); auth->authorizer = NULL; } if (!auth->authorizer) { From 841645b5f2dfceac69b78fcd0c9050868d41ea61 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 25 Apr 2016 15:33:55 -0400 Subject: [PATCH 097/181] ipv6: Revert optional address flusing on ifdown. This reverts the following three commits: 70af921db6f8835f4b11c65731116560adb00c14 799977d9aafbf0ca0b9c39b04cbfb16db71302c9 f1705ec197e705b79ea40fe7a2cc5acfa1d3bfac The feature was ill conceived, has terrible semantics, and has added nothing but regressions to the already fragile ipv6 stack. Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional") Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 -- include/linux/ipv6.h | 1 - include/uapi/linux/ipv6.h | 1 - net/ipv6/addrconf.c | 162 ++----------------------- 4 files changed, 12 insertions(+), 161 deletions(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index b183e2b606c8..e0ac25210f7c 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1568,15 +1568,6 @@ temp_prefered_lft - INTEGER Preferred lifetime (in seconds) for temporary addresses. Default: 86400 (1 day) -keep_addr_on_down - INTEGER - Keep all IPv6 addresses on an interface down event. If set static - global addresses with no expiration time are not flushed. - >0 : enabled - 0 : system default - <0 : disabled - - Default: 0 (addresses are removed) - max_desync_factor - INTEGER Maximum value for DESYNC_FACTOR, which is a random value that ensures that clients don't synchronize with each diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 7edc14fb66b6..4b2267e1b7c3 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -62,7 +62,6 @@ struct ipv6_devconf { struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; - __s32 keep_addr_on_down; void *sysctl; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 395876060f50..ec117b65d5a5 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -176,7 +176,6 @@ enum { DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, DEVCONF_DROP_UNSOLICITED_NA, - DEVCONF_KEEP_ADDR_ON_DOWN, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 23cec53b568a..d77ba395d593 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -216,7 +216,6 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, - .keep_addr_on_down = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -261,7 +260,6 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, - .keep_addr_on_down = 0, }; /* Check if a valid qdisc is available */ @@ -3176,81 +3174,6 @@ static void addrconf_gre_config(struct net_device *dev) } #endif -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) -/* If the host route is cached on the addr struct make sure it is associated - * with the proper table. e.g., enslavement can change and if so the cached - * host route needs to move to the new table. - */ -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ - if (ifp->rt) { - u32 tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; - - if (tb_id != ifp->rt->rt6i_table->tb6_id) { - ip6_del_rt(ifp->rt); - ifp->rt = NULL; - } - } -} -#else -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ -} -#endif - -static int fixup_permanent_addr(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ - l3mdev_check_host_rt(idev, ifp); - - if (!ifp->rt) { - struct rt6_info *rt; - - rt = addrconf_dst_alloc(idev, &ifp->addr, false); - if (unlikely(IS_ERR(rt))) - return PTR_ERR(rt); - - ifp->rt = rt; - } - - if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, - idev->dev, 0, 0); - } - - addrconf_dad_start(ifp); - - return 0; -} - -static void addrconf_permanent_addr(struct net_device *dev) -{ - struct inet6_ifaddr *ifp, *tmp; - struct inet6_dev *idev; - - idev = __in6_dev_get(dev); - if (!idev) - return; - - write_lock_bh(&idev->lock); - - list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { - if ((ifp->flags & IFA_F_PERMANENT) && - fixup_permanent_addr(idev, ifp) < 0) { - write_unlock_bh(&idev->lock); - ipv6_del_addr(ifp); - write_lock_bh(&idev->lock); - - net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", - idev->dev->name, &ifp->addr); - } - } - - write_unlock_bh(&idev->lock); -} - static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -3337,9 +3260,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } - /* restore routes for permanent addresses */ - addrconf_permanent_addr(dev); - switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3448,20 +3368,11 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event) ipv6_mc_unmap(idev); } -static bool addr_is_local(const struct in6_addr *addr) -{ - return ipv6_addr_type(addr) & - (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); -} - static int addrconf_ifdown(struct net_device *dev, int how) { struct net *net = dev_net(dev); struct inet6_dev *idev; - struct inet6_ifaddr *ifa, *tmp; - struct list_head del_list; - int _keep_addr; - bool keep_addr; + struct inet6_ifaddr *ifa; int state, i; ASSERT_RTNL(); @@ -3488,16 +3399,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) } - /* aggregate the system setting and interface setting */ - _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; - if (!_keep_addr) - _keep_addr = idev->cnf.keep_addr_on_down; - - /* combine the user config with event to determine if permanent - * addresses are to be removed from address hash table - */ - keep_addr = !(how || _keep_addr <= 0); - /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &inet6_addr_lst[i]; @@ -3506,16 +3407,9 @@ static int addrconf_ifdown(struct net_device *dev, int how) restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { + hlist_del_init_rcu(&ifa->addr_lst); addrconf_del_dad_work(ifa); - /* combined flag + permanent flag decide if - * address is retained on a down event - */ - if (!keep_addr || - !(ifa->flags & IFA_F_PERMANENT) || - addr_is_local(&ifa->addr)) { - hlist_del_init_rcu(&ifa->addr_lst); - goto restart; - } + goto restart; } } spin_unlock_bh(&addrconf_hash_lock); @@ -3549,54 +3443,31 @@ restart: write_lock_bh(&idev->lock); } - /* re-combine the user config with event to determine if permanent - * addresses are to be removed from the interface list - */ - keep_addr = (!how && _keep_addr > 0); - - INIT_LIST_HEAD(&del_list); - list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + while (!list_empty(&idev->addr_list)) { + ifa = list_first_entry(&idev->addr_list, + struct inet6_ifaddr, if_list); addrconf_del_dad_work(ifa); + list_del(&ifa->if_list); + write_unlock_bh(&idev->lock); + spin_lock_bh(&ifa->lock); - - if (keep_addr && (ifa->flags & IFA_F_PERMANENT) && - !addr_is_local(&ifa->addr)) { - /* set state to skip the notifier below */ - state = INET6_IFADDR_STATE_DEAD; - ifa->state = 0; - if (!(ifa->flags & IFA_F_NODAD)) - ifa->flags |= IFA_F_TENTATIVE; - } else { - state = ifa->state; - ifa->state = INET6_IFADDR_STATE_DEAD; - - list_del(&ifa->if_list); - list_add(&ifa->if_list, &del_list); - } - + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } + in6_ifa_put(ifa); write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); - /* now clean up addresses to be removed */ - while (!list_empty(&del_list)) { - ifa = list_first_entry(&del_list, - struct inet6_ifaddr, if_list); - list_del(&ifa->if_list); - - in6_ifa_put(ifa); - } - /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4861,7 +4732,6 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; - array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; } static inline size_t inet6_ifla6_size(void) @@ -5949,14 +5819,6 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "keep_addr_on_down", - .data = &ipv6_devconf.keep_addr_on_down, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - - }, { /* sentinel */ } From 5cf1cacb49aee39c3e02ae87068fc3c6430659b0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 21 Apr 2016 19:06:48 -0400 Subject: [PATCH 098/181] cgroup, cpuset: replace cpuset_post_attach_flush() with cgroup_subsys->post_attach callback Since e93ad19d0564 ("cpuset: make mm migration asynchronous"), cpuset kicks off asynchronous NUMA node migration if necessary during task migration and flushes it from cpuset_post_attach_flush() which is called at the end of __cgroup_procs_write(). This is to avoid performing migration with cgroup_threadgroup_rwsem write-locked which can lead to deadlock through dependency on kworker creation. memcg has a similar issue with charge moving, so let's convert it to an official callback rather than the current one-off cpuset specific function. This patch adds cgroup_subsys->post_attach callback and makes cpuset register cpuset_post_attach_flush() as its ->post_attach. The conversion is mostly one-to-one except that the new callback is called under cgroup_mutex. This is to guarantee that no other migration operations are started before ->post_attach callbacks are finished. cgroup_mutex is one of the outermost mutex in the system and has never been and shouldn't be a problem. We can add specialized synchronization around __cgroup_procs_write() but I don't think there's any noticeable benefit. Signed-off-by: Tejun Heo Cc: Li Zefan Cc: Johannes Weiner Cc: Michal Hocko Cc: # 4.4+ prerequisite for the next patch --- include/linux/cgroup-defs.h | 1 + include/linux/cpuset.h | 6 ------ kernel/cgroup.c | 7 +++++-- kernel/cpuset.c | 4 ++-- 4 files changed, 8 insertions(+), 10 deletions(-) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 3e39ae5bc799..5b17de62c962 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -444,6 +444,7 @@ struct cgroup_subsys { int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); void (*attach)(struct cgroup_taskset *tset); + void (*post_attach)(void); int (*can_fork)(struct task_struct *task); void (*cancel_fork)(struct task_struct *task); void (*fork)(struct task_struct *task); diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index fea160ee5803..85a868ccb493 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -137,8 +137,6 @@ static inline void set_mems_allowed(nodemask_t nodemask) task_unlock(current); } -extern void cpuset_post_attach_flush(void); - #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } @@ -245,10 +243,6 @@ static inline bool read_mems_allowed_retry(unsigned int seq) return false; } -static inline void cpuset_post_attach_flush(void) -{ -} - #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 671dc05c0b0f..909a7d31ffd3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2825,9 +2825,10 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct task_struct *tsk; + struct cgroup_subsys *ss; struct cgroup *cgrp; pid_t pid; - int ret; + int ssid, ret; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; @@ -2875,8 +2876,10 @@ out_unlock_rcu: rcu_read_unlock(); out_unlock_threadgroup: percpu_up_write(&cgroup_threadgroup_rwsem); + for_each_subsys(ss, ssid) + if (ss->post_attach) + ss->post_attach(); cgroup_kn_unlock(of->kn); - cpuset_post_attach_flush(); return ret ?: nbytes; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 00ab5c2b7c5b..1902956baba1 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -58,7 +58,6 @@ #include #include #include -#include #include #include @@ -1016,7 +1015,7 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, } } -void cpuset_post_attach_flush(void) +static void cpuset_post_attach(void) { flush_workqueue(cpuset_migrate_mm_wq); } @@ -2087,6 +2086,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = { .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, + .post_attach = cpuset_post_attach, .bind = cpuset_bind, .legacy_cftypes = files, .early_init = true, From 264a0ae164bc0e9144bebcd25ff030d067b1a878 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 21 Apr 2016 19:09:02 -0400 Subject: [PATCH 099/181] memcg: relocate charge moving from ->attach to ->post_attach Hello, So, this ended up a lot simpler than I originally expected. I tested it lightly and it seems to work fine. Petr, can you please test these two patches w/o the lru drain drop patch and see whether the problem is gone? Thanks. ------ 8< ------ If charge moving is used, memcg performs relabeling of the affected pages from its ->attach callback which is called under both cgroup_threadgroup_rwsem and thus can't create new kthreads. This is fragile as various operations may depend on workqueues making forward progress which relies on the ability to create new kthreads. There's no reason to perform charge moving from ->attach which is deep in the task migration path. Move it to ->post_attach which is called after the actual migration is finished and cgroup_threadgroup_rwsem is dropped. * move_charge_struct->mm is added and ->can_attach is now responsible for pinning and recording the target mm. mem_cgroup_clear_mc() is updated accordingly. This also simplifies mem_cgroup_move_task(). * mem_cgroup_move_task() is now called from ->post_attach instead of ->attach. Signed-off-by: Tejun Heo Cc: Johannes Weiner Acked-by: Michal Hocko Debugged-and-tested-by: Petr Mladek Reported-by: Cyril Hrubis Reported-by: Johannes Weiner Fixes: 1ed1328792ff ("sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem") Cc: # 4.4+ --- mm/memcontrol.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 36db05fa8acb..fe787f5c41bd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -207,6 +207,7 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); /* "mc" and its members are protected by cgroup_mutex */ static struct move_charge_struct { spinlock_t lock; /* for from, to */ + struct mm_struct *mm; struct mem_cgroup *from; struct mem_cgroup *to; unsigned long flags; @@ -4667,6 +4668,8 @@ static void __mem_cgroup_clear_mc(void) static void mem_cgroup_clear_mc(void) { + struct mm_struct *mm = mc.mm; + /* * we must clear moving_task before waking up waiters at the end of * task migration. @@ -4676,7 +4679,10 @@ static void mem_cgroup_clear_mc(void) spin_lock(&mc.lock); mc.from = NULL; mc.to = NULL; + mc.mm = NULL; spin_unlock(&mc.lock); + + mmput(mm); } static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -4733,6 +4739,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) VM_BUG_ON(mc.moved_swap); spin_lock(&mc.lock); + mc.mm = mm; mc.from = from; mc.to = memcg; mc.flags = move_flags; @@ -4742,8 +4749,9 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) ret = mem_cgroup_precharge_mc(mm); if (ret) mem_cgroup_clear_mc(); + } else { + mmput(mm); } - mmput(mm); return ret; } @@ -4852,11 +4860,11 @@ put: /* get_mctgt_type() gets the page */ return ret; } -static void mem_cgroup_move_charge(struct mm_struct *mm) +static void mem_cgroup_move_charge(void) { struct mm_walk mem_cgroup_move_charge_walk = { .pmd_entry = mem_cgroup_move_charge_pte_range, - .mm = mm, + .mm = mc.mm, }; lru_add_drain_all(); @@ -4868,7 +4876,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) atomic_inc(&mc.from->moving_account); synchronize_rcu(); retry: - if (unlikely(!down_read_trylock(&mm->mmap_sem))) { + if (unlikely(!down_read_trylock(&mc.mm->mmap_sem))) { /* * Someone who are holding the mmap_sem might be waiting in * waitq. So we cancel all extra charges, wake up all waiters, @@ -4885,23 +4893,16 @@ retry: * additional charge, the page walk just aborts. */ walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk); - up_read(&mm->mmap_sem); + up_read(&mc.mm->mmap_sem); atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { - struct cgroup_subsys_state *css; - struct task_struct *p = cgroup_taskset_first(tset, &css); - struct mm_struct *mm = get_task_mm(p); - - if (mm) { - if (mc.to) - mem_cgroup_move_charge(mm); - mmput(mm); - } - if (mc.to) + if (mc.to) { + mem_cgroup_move_charge(); mem_cgroup_clear_mc(); + } } #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -4911,7 +4912,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { } #endif @@ -5195,7 +5196,7 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, - .attach = mem_cgroup_move_task, + .post_attach = mem_cgroup_move_task, .bind = mem_cgroup_bind, .dfl_cftypes = memory_files, .legacy_cftypes = mem_cgroup_legacy_files, From 3d6d30d60abb19ba9a20e53ce65b18a9c148fcd1 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Fri, 22 Apr 2016 13:09:13 +0200 Subject: [PATCH 100/181] cxgbi: fix uninitialized flowi6 ip6_route_output looks into different fields in the passed flowi6 structure, yet cxgbi passes garbage in nearly all those fields. Zero the structure out first. Fixes: fc8d0590d9142 ("libcxgbi: Add ipv6 api to driver") Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/scsi/cxgbi/libcxgbi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index f3bb7af4e984..ead83a24bcd1 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -688,6 +688,7 @@ static struct rt6_info *find_route_ipv6(const struct in6_addr *saddr, { struct flowi6 fl; + memset(&fl, 0, sizeof(fl)); if (saddr) memcpy(&fl.saddr, saddr, sizeof(struct in6_addr)); if (daddr) From 1becf03545a0859ceaaf9e8c2d9861882a71cb01 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Fri, 22 Apr 2016 19:53:59 -0700 Subject: [PATCH 101/181] cpufreq: intel_pstate: Fix processing for turbo activation ratio When the config TDP level is not nominal (level = 0), the MSR values for reading level 1 and level 2 ratios contain power in low 14 bits and actual ratio bits are at bits [23:16]. The current processing for level 1 and level 2 is wrong as there is no shift done to get actual ratio. Fixes: 6a35fc2d6c22 (cpufreq: intel_pstate: get P1 from TAR when available) Signed-off-by: Srinivas Pandruvada Cc: 4.4+ # 4.4+ Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/intel_pstate.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 30fe323c4551..f502d5b90c25 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -813,6 +813,11 @@ static int core_get_max_pstate(void) if (err) goto skip_tar; + /* For level 1 and 2, bits[23:16] contain the ratio */ + if (tdp_ctrl) + tdp_ratio >>= 16; + + tdp_ratio &= 0xff; /* ratios are only 8 bits long */ if (tdp_ratio - 1 == tar) { max_pstate = tar; pr_debug("max_pstate=TAC %x\n", max_pstate); From 9f5db53507b6607dc1b5d59547097966c0e71047 Mon Sep 17 00:00:00 2001 From: Ivan Babrou Date: Sat, 23 Apr 2016 12:58:03 +0000 Subject: [PATCH 102/181] net: dummy: remove note about being Y by default Signed-off-by: Ivan Babrou Signed-off-by: David S. Miller --- drivers/net/Kconfig | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index a24c18eee598..befd67df08e1 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -62,9 +62,8 @@ config DUMMY this device is consigned into oblivion) with a configurable IP address. It is most commonly used in order to make your currently inactive SLIP address seem like a real address for local programs. - If you use SLIP or PPP, you might want to say Y here. Since this - thing often comes in handy, the default is Y. It won't enlarge your - kernel either. What a deal. Read about it in the Network + If you use SLIP or PPP, you might want to say Y here. It won't + enlarge your kernel. What a deal. Read about it in the Network Administrator's Guide, available from . From fc96256c906362e845d848d0f6a6354450059e81 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 23 Apr 2016 11:35:46 -0700 Subject: [PATCH 103/181] net/mlx4_en: fix spurious timestamping callbacks When multiple skb are TX-completed in a row, we might incorrectly keep a timestamp of a prior skb and cause extra work. Fixes: ec693d47010e8 ("net/mlx4_en: Add HW timestamping (TS) support") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Reviewed-by: Eran Ben Elisha Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index c0d7b7296236..a386f047c1af 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -405,7 +405,6 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, u32 packets = 0; u32 bytes = 0; int factor = priv->cqe_factor; - u64 timestamp = 0; int done = 0; int budget = priv->tx_work_limit; u32 last_nr_txbb; @@ -445,9 +444,12 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, new_index = be16_to_cpu(cqe->wqe_index) & size_mask; do { + u64 timestamp = 0; + txbbs_skipped += last_nr_txbb; ring_index = (ring_index + last_nr_txbb) & size_mask; - if (ring->tx_info[ring_index].ts_requested) + + if (unlikely(ring->tx_info[ring_index].ts_requested)) timestamp = mlx4_en_get_cqe_ts(cqe); /* free next descriptor */ From 037e119738120c1cdc460c6ae33871c3000531f3 Mon Sep 17 00:00:00 2001 From: Conrad Kostecki Date: Tue, 26 Apr 2016 10:08:10 +0200 Subject: [PATCH 104/181] ALSA: hda - Add dock support for ThinkPad X260 Fixes audio output on a ThinkPad X260, when using Lenovo CES 2013 docking station series (basic, pro, ultra). Signed-off-by: Conrad Kostecki Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 810bceee4fd2..ac4490a96863 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5584,6 +5584,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK), + SND_PCI_QUIRK(0x17aa, 0x504a, "ThinkPad X260", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), From bb03ed216370cb021f377f923471e56d1de3ff5d Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 21 Apr 2016 16:39:17 +0200 Subject: [PATCH 105/181] ALSA: hda - Update BCLK also at hotplug for i915 HSW/BDW The recent bug report suggests that BCLK setup for i915 HSW/BDW needs to be updated at each HDMI hotplug, not only at initialization and resume. That is, we need to update HSW_EM4 and HSW_EM5 registers at ELD notification, too. Otherwise the HDMI audio may be out of sync and played in a wrong pitch. However, the HDA codec driver has no access to the controller registers, and currently the code managing these registers is in hda_intel.c, i.e. local to the controller driver. For allowing the explicit BCLK update from the codec driver, as in this patch, the former haswell_set_bclk() in hda_intel.c is moved to hdac_i915.c and exposed as snd_hdac_i915_set_bclk(). This is called from both the HDA controller driver and intel_pin_eld_notify() in HDMI codec driver. Along with this change, snd_hdac_get_display_clk() gets dropped as it's no longer used. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91410 Cc: # v4.5+ Signed-off-by: Takashi Iwai --- include/sound/hda_i915.h | 5 ++-- sound/hda/hdac_i915.c | 60 +++++++++++++++++++++++++++++++------- sound/pci/hda/hda_intel.c | 56 +++-------------------------------- sound/pci/hda/patch_hdmi.c | 1 + 4 files changed, 57 insertions(+), 65 deletions(-) diff --git a/include/sound/hda_i915.h b/include/sound/hda_i915.h index fa341fcb5829..f5842bcd9c94 100644 --- a/include/sound/hda_i915.h +++ b/include/sound/hda_i915.h @@ -9,7 +9,7 @@ #ifdef CONFIG_SND_HDA_I915 int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable); int snd_hdac_display_power(struct hdac_bus *bus, bool enable); -int snd_hdac_get_display_clk(struct hdac_bus *bus); +void snd_hdac_i915_set_bclk(struct hdac_bus *bus); int snd_hdac_sync_audio_rate(struct hdac_bus *bus, hda_nid_t nid, int rate); int snd_hdac_acomp_get_eld(struct hdac_bus *bus, hda_nid_t nid, bool *audio_enabled, char *buffer, int max_bytes); @@ -25,9 +25,8 @@ static inline int snd_hdac_display_power(struct hdac_bus *bus, bool enable) { return 0; } -static inline int snd_hdac_get_display_clk(struct hdac_bus *bus) +static inline void snd_hdac_i915_set_bclk(struct hdac_bus *bus) { - return 0; } static inline int snd_hdac_sync_audio_rate(struct hdac_bus *bus, hda_nid_t nid, int rate) diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index 54babe1c0b16..607bbeaebddf 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -20,6 +20,7 @@ #include #include #include +#include static struct i915_audio_component *hdac_acomp; @@ -97,26 +98,65 @@ int snd_hdac_display_power(struct hdac_bus *bus, bool enable) } EXPORT_SYMBOL_GPL(snd_hdac_display_power); +#define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \ + ((pci)->device == 0x0c0c) || \ + ((pci)->device == 0x0d0c) || \ + ((pci)->device == 0x160c)) + /** - * snd_hdac_get_display_clk - Get CDCLK in kHz + * snd_hdac_i915_set_bclk - Reprogram BCLK for HSW/BDW * @bus: HDA core bus * - * This function is supposed to be used only by a HD-audio controller - * driver that needs the interaction with i915 graphics. + * Intel HSW/BDW display HDA controller is in GPU. Both its power and link BCLK + * depends on GPU. Two Extended Mode registers EM4 (M value) and EM5 (N Value) + * are used to convert CDClk (Core Display Clock) to 24MHz BCLK: + * BCLK = CDCLK * M / N + * The values will be lost when the display power well is disabled and need to + * be restored to avoid abnormal playback speed. * - * This function queries CDCLK value in kHz from the graphics driver and - * returns the value. A negative code is returned in error. + * Call this function at initializing and changing power well, as well as + * at ELD notifier for the hotplug. */ -int snd_hdac_get_display_clk(struct hdac_bus *bus) +void snd_hdac_i915_set_bclk(struct hdac_bus *bus) { struct i915_audio_component *acomp = bus->audio_component; + struct pci_dev *pci = to_pci_dev(bus->dev); + int cdclk_freq; + unsigned int bclk_m, bclk_n; - if (!acomp || !acomp->ops) - return -ENODEV; + if (!acomp || !acomp->ops || !acomp->ops->get_cdclk_freq) + return; /* only for i915 binding */ + if (!CONTROLLER_IN_GPU(pci)) + return; /* only HSW/BDW */ - return acomp->ops->get_cdclk_freq(acomp->dev); + cdclk_freq = acomp->ops->get_cdclk_freq(acomp->dev); + switch (cdclk_freq) { + case 337500: + bclk_m = 16; + bclk_n = 225; + break; + + case 450000: + default: /* default CDCLK 450MHz */ + bclk_m = 4; + bclk_n = 75; + break; + + case 540000: + bclk_m = 4; + bclk_n = 90; + break; + + case 675000: + bclk_m = 8; + bclk_n = 225; + break; + } + + snd_hdac_chip_writew(bus, HSW_EM4, bclk_m); + snd_hdac_chip_writew(bus, HSW_EM5, bclk_n); } -EXPORT_SYMBOL_GPL(snd_hdac_get_display_clk); +EXPORT_SYMBOL_GPL(snd_hdac_i915_set_bclk); /* There is a fixed mapping between audio pin node and display port * on current Intel platforms: diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 637b8a0e2a91..9a0d1445ca5c 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -857,50 +857,6 @@ static int param_set_xint(const char *val, const struct kernel_param *kp) #define azx_del_card_list(chip) /* NOP */ #endif /* CONFIG_PM */ -/* Intel HSW/BDW display HDA controller is in GPU. Both its power and link BCLK - * depends on GPU. Two Extended Mode registers EM4 (M value) and EM5 (N Value) - * are used to convert CDClk (Core Display Clock) to 24MHz BCLK: - * BCLK = CDCLK * M / N - * The values will be lost when the display power well is disabled and need to - * be restored to avoid abnormal playback speed. - */ -static void haswell_set_bclk(struct hda_intel *hda) -{ - struct azx *chip = &hda->chip; - int cdclk_freq; - unsigned int bclk_m, bclk_n; - - if (!hda->need_i915_power) - return; - - cdclk_freq = snd_hdac_get_display_clk(azx_bus(chip)); - switch (cdclk_freq) { - case 337500: - bclk_m = 16; - bclk_n = 225; - break; - - case 450000: - default: /* default CDCLK 450MHz */ - bclk_m = 4; - bclk_n = 75; - break; - - case 540000: - bclk_m = 4; - bclk_n = 90; - break; - - case 675000: - bclk_m = 8; - bclk_n = 225; - break; - } - - azx_writew(chip, HSW_EM4, bclk_m); - azx_writew(chip, HSW_EM5, bclk_n); -} - #if defined(CONFIG_PM_SLEEP) || defined(SUPPORT_VGA_SWITCHEROO) /* * power management @@ -958,7 +914,7 @@ static int azx_resume(struct device *dev) if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL && hda->need_i915_power) { snd_hdac_display_power(azx_bus(chip), true); - haswell_set_bclk(hda); + snd_hdac_i915_set_bclk(azx_bus(chip)); } if (chip->msi) if (pci_enable_msi(pci) < 0) @@ -1058,7 +1014,7 @@ static int azx_runtime_resume(struct device *dev) bus = azx_bus(chip); if (hda->need_i915_power) { snd_hdac_display_power(bus, true); - haswell_set_bclk(hda); + snd_hdac_i915_set_bclk(bus); } else { /* toggle codec wakeup bit for STATESTS read */ snd_hdac_set_codec_wakeup(bus, true); @@ -1796,12 +1752,8 @@ static int azx_first_init(struct azx *chip) /* initialize chip */ azx_init_pci(chip); - if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) { - struct hda_intel *hda; - - hda = container_of(chip, struct hda_intel, chip); - haswell_set_bclk(hda); - } + if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) + snd_hdac_i915_set_bclk(bus); hda_intel_init_chip(chip, (probe_only[dev] & 2) == 0); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 40933aa33afe..1483f85999ec 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2232,6 +2232,7 @@ static void intel_pin_eld_notify(void *audio_ptr, int port) if (atomic_read(&(codec)->core.in_pm)) return; + snd_hdac_i915_set_bclk(&codec->bus->core); check_presence_and_report(codec, pin_nid); } From 978fa436231a834dc686292efc7d944d9013e035 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Fri, 22 Apr 2016 16:18:02 +0100 Subject: [PATCH 106/181] drivers: firmware: psci: unify enable-method binding on ARM {64,32}-bit systems Currently ARM CPUs DT bindings allows different enable-method value for PSCI based systems. On ARM 64-bit this property is required and must be "psci" while on ARM 32-bit systems this property is optional and must be "arm,psci" if present. However, "arm,psci" has always been the compatible string for the PSCI node, and was never intended to be the enable-method. So this is a bug in the binding and not a deliberate attempt at specifying 32-bit differently. This is problematic if 32-bit OS is run on 64-bit system which has "psci" as enable-method rather than the expected "arm,psci". So let's unify the value into "psci" and remove support for "arm,psci" before it finds any users. Reported-by: Soby Mathew Cc: Rob Herring Acked-by: Mark Rutland Acked-by: Lorenzo Pieralisi Signed-off-by: Sudeep Holla Signed-off-by: Arnd Bergmann --- Documentation/devicetree/bindings/arm/cpus.txt | 1 - drivers/firmware/psci.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt index ccc62f145306..3f0cbbb8395f 100644 --- a/Documentation/devicetree/bindings/arm/cpus.txt +++ b/Documentation/devicetree/bindings/arm/cpus.txt @@ -192,7 +192,6 @@ nodes to be present and contain the properties described below. can be one of: "allwinner,sun6i-a31" "allwinner,sun8i-a23" - "arm,psci" "arm,realview-smp" "brcm,bcm-nsp-smp" "brcm,brahma-b15" diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c index 11bfee8b79a9..b5d05807e6ec 100644 --- a/drivers/firmware/psci.c +++ b/drivers/firmware/psci.c @@ -360,7 +360,7 @@ static struct cpuidle_ops psci_cpuidle_ops __initdata = { .init = psci_dt_cpu_init_idle, }; -CPUIDLE_METHOD_OF_DECLARE(psci, "arm,psci", &psci_cpuidle_ops); +CPUIDLE_METHOD_OF_DECLARE(psci, "psci", &psci_cpuidle_ops); #endif #endif From 346c09f80459a3ad97df1816d6d606169a51001a Mon Sep 17 00:00:00 2001 From: Roman Pen Date: Tue, 26 Apr 2016 13:15:35 +0200 Subject: [PATCH 107/181] workqueue: fix ghost PENDING flag while doing MQ IO The bug in a workqueue leads to a stalled IO request in MQ ctx->rq_list with the following backtrace: [ 601.347452] INFO: task kworker/u129:5:1636 blocked for more than 120 seconds. [ 601.347574] Tainted: G O 4.4.5-1-storage+ #6 [ 601.347651] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 601.348142] kworker/u129:5 D ffff880803077988 0 1636 2 0x00000000 [ 601.348519] Workqueue: ibnbd_server_fileio_wq ibnbd_dev_file_submit_io_worker [ibnbd_server] [ 601.348999] ffff880803077988 ffff88080466b900 ffff8808033f9c80 ffff880803078000 [ 601.349662] ffff880807c95000 7fffffffffffffff ffffffff815b0920 ffff880803077ad0 [ 601.350333] ffff8808030779a0 ffffffff815b01d5 0000000000000000 ffff880803077a38 [ 601.350965] Call Trace: [ 601.351203] [] ? bit_wait+0x60/0x60 [ 601.351444] [] schedule+0x35/0x80 [ 601.351709] [] schedule_timeout+0x192/0x230 [ 601.351958] [] ? blk_flush_plug_list+0xc7/0x220 [ 601.352208] [] ? ktime_get+0x37/0xa0 [ 601.352446] [] ? bit_wait+0x60/0x60 [ 601.352688] [] io_schedule_timeout+0xa4/0x110 [ 601.352951] [] ? _raw_spin_unlock_irqrestore+0xe/0x10 [ 601.353196] [] bit_wait_io+0x1b/0x70 [ 601.353440] [] __wait_on_bit+0x5d/0x90 [ 601.353689] [] wait_on_page_bit+0xc0/0xd0 [ 601.353958] [] ? autoremove_wake_function+0x40/0x40 [ 601.354200] [] __filemap_fdatawait_range+0xe4/0x140 [ 601.354441] [] filemap_fdatawait_range+0x14/0x30 [ 601.354688] [] filemap_write_and_wait_range+0x3f/0x70 [ 601.354932] [] blkdev_fsync+0x1b/0x50 [ 601.355193] [] vfs_fsync_range+0x49/0xa0 [ 601.355432] [] blkdev_write_iter+0xca/0x100 [ 601.355679] [] __vfs_write+0xaa/0xe0 [ 601.355925] [] vfs_write+0xa9/0x1a0 [ 601.356164] [] kernel_write+0x38/0x50 The underlying device is a null_blk, with default parameters: queue_mode = MQ submit_queues = 1 Verification that nullb0 has something inflight: root@pserver8:~# cat /sys/block/nullb0/inflight 0 1 root@pserver8:~# find /sys/block/nullb0/mq/0/cpu* -name rq_list -print -exec cat {} \; ... /sys/block/nullb0/mq/0/cpu2/rq_list CTX pending: ffff8838038e2400 ... During debug it became clear that stalled request is always inserted in the rq_list from the following path: save_stack_trace_tsk + 34 blk_mq_insert_requests + 231 blk_mq_flush_plug_list + 281 blk_flush_plug_list + 199 wait_on_page_bit + 192 __filemap_fdatawait_range + 228 filemap_fdatawait_range + 20 filemap_write_and_wait_range + 63 blkdev_fsync + 27 vfs_fsync_range + 73 blkdev_write_iter + 202 __vfs_write + 170 vfs_write + 169 kernel_write + 56 So blk_flush_plug_list() was called with from_schedule == true. If from_schedule is true, that means that finally blk_mq_insert_requests() offloads execution of __blk_mq_run_hw_queue() and uses kblockd workqueue, i.e. it calls kblockd_schedule_delayed_work_on(). That means, that we race with another CPU, which is about to execute __blk_mq_run_hw_queue() work. Further debugging shows the following traces from different CPUs: CPU#0 CPU#1 ---------------------------------- ------------------------------- reqeust A inserted STORE hctx->ctx_map[0] bit marked kblockd_schedule...() returns 1 request B inserted STORE hctx->ctx_map[1] bit marked kblockd_schedule...() returns 0 *** WORK PENDING bit is cleared *** flush_busy_ctxs() is executed, but bit 1, set by CPU#1, is not observed As a result request B pended forever. This behaviour can be explained by speculative LOAD of hctx->ctx_map on CPU#0, which is reordered with clear of PENDING bit and executed _before_ actual STORE of bit 1 on CPU#1. The proper fix is an explicit full barrier , which guarantees that clear of PENDING bit is to be executed before all possible speculative LOADS or STORES inside actual work function. Signed-off-by: Roman Pen Cc: Gioh Kim Cc: Michael Wang Cc: Tejun Heo Cc: Jens Axboe Cc: linux-block@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Tejun Heo --- kernel/workqueue.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 16e13d8628a3..801a698564d4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -666,6 +666,35 @@ static void set_work_pool_and_clear_pending(struct work_struct *work, */ smp_wmb(); set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); + /* + * The following mb guarantees that previous clear of a PENDING bit + * will not be reordered with any speculative LOADS or STORES from + * work->current_func, which is executed afterwards. This possible + * reordering can lead to a missed execution on attempt to qeueue + * the same @work. E.g. consider this case: + * + * CPU#0 CPU#1 + * ---------------------------- -------------------------------- + * + * 1 STORE event_indicated + * 2 queue_work_on() { + * 3 test_and_set_bit(PENDING) + * 4 } set_..._and_clear_pending() { + * 5 set_work_data() # clear bit + * 6 smp_mb() + * 7 work->current_func() { + * 8 LOAD event_indicated + * } + * + * Without an explicit full barrier speculative LOAD on line 8 can + * be executed before CPU#0 does STORE on line 1. If that happens, + * CPU#0 observes the PENDING bit is still set and new execution of + * a @work is not queued in a hope, that CPU#1 will eventually + * finish the queued @work. Meanwhile CPU#1 does not see + * event_indicated is set, because speculative LOAD was executed + * before actual STORE. + */ + smp_mb(); } static void clear_work_data(struct work_struct *work) From 6a923934c33c750a595868af6bef5f1a1fa90054 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 26 Apr 2016 11:47:41 -0400 Subject: [PATCH 108/181] Revert "ipv6: Revert optional address flusing on ifdown." This reverts commit 841645b5f2dfceac69b78fcd0c9050868d41ea61. Ok, this puts the feature back. I've decided to apply David A.'s bug fix and run with that rather than make everyone wait another whole release for this feature. Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 ++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 162 +++++++++++++++++++++++-- 4 files changed, 161 insertions(+), 12 deletions(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index e0ac25210f7c..b183e2b606c8 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1568,6 +1568,15 @@ temp_prefered_lft - INTEGER Preferred lifetime (in seconds) for temporary addresses. Default: 86400 (1 day) +keep_addr_on_down - INTEGER + Keep all IPv6 addresses on an interface down event. If set static + global addresses with no expiration time are not flushed. + >0 : enabled + 0 : system default + <0 : disabled + + Default: 0 (addresses are removed) + max_desync_factor - INTEGER Maximum value for DESYNC_FACTOR, which is a random value that ensures that clients don't synchronize with each diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4b2267e1b7c3..7edc14fb66b6 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -62,6 +62,7 @@ struct ipv6_devconf { struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; + __s32 keep_addr_on_down; void *sysctl; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index ec117b65d5a5..395876060f50 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -176,6 +176,7 @@ enum { DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, DEVCONF_DROP_UNSOLICITED_NA, + DEVCONF_KEEP_ADDR_ON_DOWN, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d77ba395d593..23cec53b568a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -216,6 +216,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -260,6 +261,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; /* Check if a valid qdisc is available */ @@ -3174,6 +3176,81 @@ static void addrconf_gre_config(struct net_device *dev) } #endif +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) +/* If the host route is cached on the addr struct make sure it is associated + * with the proper table. e.g., enslavement can change and if so the cached + * host route needs to move to the new table. + */ +static void l3mdev_check_host_rt(struct inet6_dev *idev, + struct inet6_ifaddr *ifp) +{ + if (ifp->rt) { + u32 tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; + + if (tb_id != ifp->rt->rt6i_table->tb6_id) { + ip6_del_rt(ifp->rt); + ifp->rt = NULL; + } + } +} +#else +static void l3mdev_check_host_rt(struct inet6_dev *idev, + struct inet6_ifaddr *ifp) +{ +} +#endif + +static int fixup_permanent_addr(struct inet6_dev *idev, + struct inet6_ifaddr *ifp) +{ + l3mdev_check_host_rt(idev, ifp); + + if (!ifp->rt) { + struct rt6_info *rt; + + rt = addrconf_dst_alloc(idev, &ifp->addr, false); + if (unlikely(IS_ERR(rt))) + return PTR_ERR(rt); + + ifp->rt = rt; + } + + if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + idev->dev, 0, 0); + } + + addrconf_dad_start(ifp); + + return 0; +} + +static void addrconf_permanent_addr(struct net_device *dev) +{ + struct inet6_ifaddr *ifp, *tmp; + struct inet6_dev *idev; + + idev = __in6_dev_get(dev); + if (!idev) + return; + + write_lock_bh(&idev->lock); + + list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { + if ((ifp->flags & IFA_F_PERMANENT) && + fixup_permanent_addr(idev, ifp) < 0) { + write_unlock_bh(&idev->lock); + ipv6_del_addr(ifp); + write_lock_bh(&idev->lock); + + net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", + idev->dev->name, &ifp->addr); + } + } + + write_unlock_bh(&idev->lock); +} + static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -3260,6 +3337,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } + /* restore routes for permanent addresses */ + addrconf_permanent_addr(dev); + switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3368,11 +3448,20 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event) ipv6_mc_unmap(idev); } +static bool addr_is_local(const struct in6_addr *addr) +{ + return ipv6_addr_type(addr) & + (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); +} + static int addrconf_ifdown(struct net_device *dev, int how) { struct net *net = dev_net(dev); struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + struct inet6_ifaddr *ifa, *tmp; + struct list_head del_list; + int _keep_addr; + bool keep_addr; int state, i; ASSERT_RTNL(); @@ -3399,6 +3488,16 @@ static int addrconf_ifdown(struct net_device *dev, int how) } + /* aggregate the system setting and interface setting */ + _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + if (!_keep_addr) + _keep_addr = idev->cnf.keep_addr_on_down; + + /* combine the user config with event to determine if permanent + * addresses are to be removed from address hash table + */ + keep_addr = !(how || _keep_addr <= 0); + /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &inet6_addr_lst[i]; @@ -3407,9 +3506,16 @@ static int addrconf_ifdown(struct net_device *dev, int how) restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { - hlist_del_init_rcu(&ifa->addr_lst); addrconf_del_dad_work(ifa); - goto restart; + /* combined flag + permanent flag decide if + * address is retained on a down event + */ + if (!keep_addr || + !(ifa->flags & IFA_F_PERMANENT) || + addr_is_local(&ifa->addr)) { + hlist_del_init_rcu(&ifa->addr_lst); + goto restart; + } } } spin_unlock_bh(&addrconf_hash_lock); @@ -3443,31 +3549,54 @@ restart: write_lock_bh(&idev->lock); } - while (!list_empty(&idev->addr_list)) { - ifa = list_first_entry(&idev->addr_list, - struct inet6_ifaddr, if_list); + /* re-combine the user config with event to determine if permanent + * addresses are to be removed from the interface list + */ + keep_addr = (!how && _keep_addr > 0); + + INIT_LIST_HEAD(&del_list); + list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { addrconf_del_dad_work(ifa); - list_del(&ifa->if_list); - write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->lock); - state = ifa->state; - ifa->state = INET6_IFADDR_STATE_DEAD; + + if (keep_addr && (ifa->flags & IFA_F_PERMANENT) && + !addr_is_local(&ifa->addr)) { + /* set state to skip the notifier below */ + state = INET6_IFADDR_STATE_DEAD; + ifa->state = 0; + if (!(ifa->flags & IFA_F_NODAD)) + ifa->flags |= IFA_F_TENTATIVE; + } else { + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; + + list_del(&ifa->if_list); + list_add(&ifa->if_list, &del_list); + } + spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } - in6_ifa_put(ifa); write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); + /* now clean up addresses to be removed */ + while (!list_empty(&del_list)) { + ifa = list_first_entry(&del_list, + struct inet6_ifaddr, if_list); + list_del(&ifa->if_list); + + in6_ifa_put(ifa); + } + /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4732,6 +4861,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; + array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; } static inline size_t inet6_ifla6_size(void) @@ -5819,6 +5949,14 @@ static struct addrconf_sysctl_table .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "keep_addr_on_down", + .data = &ipv6_devconf.keep_addr_on_down, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + + }, { /* sentinel */ } From 38bd10c447f8e8980753149a8a65108159871df5 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 21 Apr 2016 20:56:12 -0700 Subject: [PATCH 109/181] net: ipv6: Delete host routes on an ifdown It was a simple idea -- save IPv6 configured addresses on a link down so that IPv6 behaves similar to IPv4. As always the devil is in the details and the IPv6 stack as too many behavioral differences from IPv4 making the simple idea more complicated than it needs to be. The current implementation for keeping IPv6 addresses can panic or spit out a warning in one of many paths: 1. IPv6 route gets an IPv4 route as its 'next' which causes a panic in rt6_fill_node while handling a route dump request. 2. rt->dst.obsolete is set to DST_OBSOLETE_DEAD hitting the WARN_ON in fib6_del 3. Panic in fib6_purge_rt because rt6i_ref count is not 1. The root cause of all these is references related to the host route for an address that is retained. So, this patch deletes the host route every time the ifdown loop runs. Since the host route is deleted and will be re-generated an up there is no longer a need for the l3mdev fix up. On the 'admin up' side move addrconf_permanent_addr into the NETDEV_UP event handling so that it runs only once versus on UP and CHANGE events. All of the current panics and warnings appear to be related to addresses on the loopback device, but given the catastrophic nature when a bug is triggered this patch takes the conservative approach and evicts all host routes rather than trying to determine when it can be re-used and when it can not. That can be a later optimizaton if desired. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 48 ++++++++++++++------------------------------- 1 file changed, 15 insertions(+), 33 deletions(-) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 23cec53b568a..8ec4b3089e20 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3176,35 +3176,9 @@ static void addrconf_gre_config(struct net_device *dev) } #endif -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) -/* If the host route is cached on the addr struct make sure it is associated - * with the proper table. e.g., enslavement can change and if so the cached - * host route needs to move to the new table. - */ -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ - if (ifp->rt) { - u32 tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; - - if (tb_id != ifp->rt->rt6i_table->tb6_id) { - ip6_del_rt(ifp->rt); - ifp->rt = NULL; - } - } -} -#else -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ -} -#endif - static int fixup_permanent_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { - l3mdev_check_host_rt(idev, ifp); - if (!ifp->rt) { struct rt6_info *rt; @@ -3304,6 +3278,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, break; if (event == NETDEV_UP) { + /* restore routes for permanent addresses */ + addrconf_permanent_addr(dev); + if (!addrconf_qdisc_ok(dev)) { /* device is not ready yet. */ pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n", @@ -3337,9 +3314,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } - /* restore routes for permanent addresses */ - addrconf_permanent_addr(dev); - switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3556,6 +3530,8 @@ restart: INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + struct rt6_info *rt = NULL; + addrconf_del_dad_work(ifa); write_unlock_bh(&idev->lock); @@ -3568,6 +3544,9 @@ restart: ifa->state = 0; if (!(ifa->flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; + + rt = ifa->rt; + ifa->rt = NULL; } else { state = ifa->state; ifa->state = INET6_IFADDR_STATE_DEAD; @@ -3578,6 +3557,9 @@ restart: spin_unlock_bh(&ifa->lock); + if (rt) + ip6_del_rt(rt); + if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); @@ -5343,10 +5325,10 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (rt) ip6_del_rt(rt); } - dst_hold(&ifp->rt->dst); - - ip6_del_rt(ifp->rt); - + if (ifp->rt) { + dst_hold(&ifp->rt->dst); + ip6_del_rt(ifp->rt); + } rt_genid_bump_ipv6(net); break; } From 42235f80ab205bf5020cf33cb3e94455410abe36 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 26 Apr 2016 17:55:38 +0300 Subject: [PATCH 110/181] IB/core: Don't drain non-existent rq queue-pair The drain_rq function expects a normal receive qp to drain. A qp can only have either a normal rq or an srq. If there is an srq, there is no rq to drain. Until the API supports draining SRQs, simply skip draining the rq when the qp has an srq attached. Fixes: 765d67748bcf ("IB: new common API for draining queues") Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- drivers/infiniband/core/verbs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 15b8adbf39c0..b65b3541e732 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1860,6 +1860,7 @@ EXPORT_SYMBOL(ib_drain_rq); void ib_drain_qp(struct ib_qp *qp) { ib_drain_sq(qp); - ib_drain_rq(qp); + if (!qp->srq) + ib_drain_rq(qp); } EXPORT_SYMBOL(ib_drain_qp); From 851d7b6b8a954b28f85e62a53cbba472907e21e4 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Tue, 12 Apr 2016 06:54:54 -0700 Subject: [PATCH 111/181] iw_cxgb4: initialize ibdev.iwcm->ifname for port mapping The IWCM uses ibdev.iwcm->ifname for registration with the iwarp port map daemon. But iw_cxgb4 did not initialize this field which causes intermittent registration failures based on the contents of the uninitialized memory. Fixes: 170003c894d9 ("iw_cxgb4: remove port mapper related code") Signed-off-by: Steve Wise Signed-off-by: Doug Ledford --- drivers/infiniband/hw/cxgb4/provider.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 124682dc5709..7574f394fdac 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -580,6 +580,8 @@ int c4iw_register_device(struct c4iw_dev *dev) dev->ibdev.iwcm->add_ref = c4iw_qp_add_ref; dev->ibdev.iwcm->rem_ref = c4iw_qp_rem_ref; dev->ibdev.iwcm->get_qp = c4iw_get_qp; + memcpy(dev->ibdev.iwcm->ifname, dev->rdev.lldi.ports[0]->name, + sizeof(dev->ibdev.iwcm->ifname)); ret = ib_register_device(&dev->ibdev, NULL); if (ret) From ad202348fe3fa8187c43af5ab5b86fe6de057bd3 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Tue, 12 Apr 2016 06:55:01 -0700 Subject: [PATCH 112/181] iw_cxgb3: initialize ibdev.iwcm->ifname for port mapping The IWCM uses ibdev.iwcm->ifname for registration with the iwarp port map daemon. But iw_cxgb3 did not initialize this field which causes intermittent registration failures based on the contents of the uninitialized memory. Fixes: c1340e8aa628 ("iw_cxgb3: support for iWARP port mapping") Signed-off-by: Steve Wise Signed-off-by: Doug Ledford --- drivers/infiniband/hw/cxgb3/iwch_provider.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 42a7b8952d13..3234a8be16f6 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -1390,6 +1390,8 @@ int iwch_register_device(struct iwch_dev *dev) dev->ibdev.iwcm->add_ref = iwch_qp_add_ref; dev->ibdev.iwcm->rem_ref = iwch_qp_rem_ref; dev->ibdev.iwcm->get_qp = iwch_get_qp; + memcpy(dev->ibdev.iwcm->ifname, dev->rdev.t3cdev_p->lldev->name, + sizeof(dev->ibdev.iwcm->ifname)); ret = ib_register_device(&dev->ibdev, NULL); if (ret) From 40edd7fdfc8a2c838c313b982f318cd69e638750 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Tue, 12 Apr 2016 06:55:03 -0700 Subject: [PATCH 113/181] iw_cxgb4: handle draining an idle qp In c4iw_drain_sq/rq(), if the particular queue is already empty then don't block. Fixes: ce4af14d94aa ('iw_cxgb4: add queue drain functions') Signed-off-by: Steve Wise Signed-off-by: Doug Ledford --- drivers/infiniband/hw/cxgb4/qp.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index e17fb5d5e033..8aa2e52b453e 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1895,13 +1895,27 @@ int c4iw_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, void c4iw_drain_sq(struct ib_qp *ibqp) { struct c4iw_qp *qp = to_c4iw_qp(ibqp); + unsigned long flag; + bool need_to_wait; - wait_for_completion(&qp->sq_drained); + spin_lock_irqsave(&qp->lock, flag); + need_to_wait = !t4_sq_empty(&qp->wq); + spin_unlock_irqrestore(&qp->lock, flag); + + if (need_to_wait) + wait_for_completion(&qp->sq_drained); } void c4iw_drain_rq(struct ib_qp *ibqp) { struct c4iw_qp *qp = to_c4iw_qp(ibqp); + unsigned long flag; + bool need_to_wait; - wait_for_completion(&qp->rq_drained); + spin_lock_irqsave(&qp->lock, flag); + need_to_wait = !t4_rq_empty(&qp->wq); + spin_unlock_irqrestore(&qp->lock, flag); + + if (need_to_wait) + wait_for_completion(&qp->rq_drained); } From 32cc92c7b5e52357a0a24010bae9eb257fa75d3e Mon Sep 17 00:00:00 2001 From: Hariprasad S Date: Tue, 5 Apr 2016 10:23:48 +0530 Subject: [PATCH 114/181] RDMA/iw_cxgb4: Fix bar2 virt addr calculation for T4 chips For T4, kernel mode qps don't use the user doorbell. User mode qps during flow control db ringing are forced into kernel, where user doorbell is treated as kernel doorbell and proper bar2 offset in bar2 virtual space is calculated, which incase of T4 is a bogus address, causing a kernel panic due to illegal write during doorbell ringing. In case of T4, kernel mode qp bar2 virtual address should be 0. Added T4 check during bar2 virtual address calculation to return 0. Fixed Bar2 range checks based on bar2 physical address. The below oops will be fixed <1>BUG: unable to handle kernel paging request at 000000000002aa08 <1>IP: [] c4iw_uld_control+0x4e0/0x880 [iw_cxgb4] <4>PGD 1416a8067 PUD 15bf35067 PMD 0 <4>Oops: 0002 [#1] SMP <4>last sysfs file: /sys/devices/pci0000:00/0000:00:03.0/0000:02:00.4/infiniband/cxgb4_0/node_guid <4>CPU 5 <4>Modules linked in: rdma_ucm rdma_cm ib_cm ib_sa ib_mad ib_uverbs ip6table_filter ip6_tables ebtable_nat ebtables ipt_MASQUERADE iptable_nat nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ipt_REJECT xt_CHECKSUM iptable_mangle iptable_filter ip_tables bridge autofs4 target_core_iblock target_core_file target_core_pscsi target_core_mod configfs bnx2fc cnic uio fcoe libfcoe libfc scsi_transport_fc scsi_tgt 8021q garp stp llc cpufreq_ondemand acpi_cpufreq freq_table mperf vhost_net macvtap macvlan tun kvm uinput microcode iTCO_wdt iTCO_vendor_support sg joydev serio_raw i2c_i801 i2c_core lpc_ich mfd_core e1000e ptp pps_core ioatdma dca i7core_edac edac_core shpchp ext3 jbd mbcache sd_mod crc_t10dif pata_acpi ata_generic ata_piix iw_cxgb4 iw_cm ib_core ib_addr cxgb4 ipv6 dm_mirror dm_region_hash dm_log dm_mod [last unloaded: scsi_wait_scan] <4> Supermicro X8ST3/X8ST3 <4>RIP: 0010:[] [] c4iw_uld_control+0x4e0/0x880 [iw_cxgb4] <4>RSP: 0000:ffff880155a03db0 EFLAGS: 00010006 <4>RAX: 000000000000001d RBX: ffff88013ae5fc00 RCX: ffff880155adb180 <4>RDX: 000000000002aa00 RSI: 0000000000000001 RDI: ffff88013ae5fdf8 <4>RBP: ffff880155a03e10 R08: 0000000000000000 R09: 0000000000000001 <4>R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 <4>R13: 000000000000001d R14: ffff880156414ab0 R15: ffffe8ffffc05b88 <4>FS: 0000000000000000(0000) GS:ffff8800282a0000(0000) knlGS:0000000000000000 <4>CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b <4>CR2: 000000000002aa08 CR3: 000000015bd0e000 CR4: 00000000000007e0 <4>DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 <4>DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 <4>Process cxgb4 (pid: 394, threadinfo ffff880155a00000, task ffff880156414ab0) <4>Stack: <4> ffff880156415068 ffff880155adb180 ffff880155a03df0 ffffffffa00a344b <4> 00000000000003e8 ffff880155920000 0000000000000004 ffff880155920000 <4> ffff88015592d438 ffffffffa00a3860 ffff880155a03fd8 ffffe8ffffc05b88 <4>Call Trace: <4> [] ? enable_txq_db+0x2b/0x80 [cxgb4] <4> [] ? process_db_full+0x0/0xa0 [cxgb4] <4> [] process_db_full+0x46/0xa0 [cxgb4] <4> [] worker_thread+0x170/0x2a0 <4> [] ? autoremove_wake_function+0x0/0x40 <4> [] ? worker_thread+0x0/0x2a0 <4> [] kthread+0x9e/0xc0 <4> [] child_rip+0xa/0x20 <4> [] ? kthread+0x0/0xc0 <4> [] ? child_rip+0x0/0x20 <4>Code: e9 ba 00 00 00 66 0f 1f 44 00 00 44 8b 05 29 07 02 00 45 85 c0 0f 85 71 02 00 00 8b 83 70 01 00 00 45 0f b7 ed c1 e0 0f 44 09 e8 <89> 42 08 0f ae f8 66 c7 83 82 01 00 00 00 00 44 0f b7 ab dc 01 <1>RIP [] c4iw_uld_control+0x4e0/0x880 [iw_cxgb4] <4> RSP <4>CR2: 000000000002aa08` Based on original work by Bharat Potnuri Fixes: 74217d4c6a4fb0d8 ("iw_cxgb4: support for bar2 qid densities exceeding the page size") Signed-off-by: Steve Wise Signed-off-by: Hariprasad Shenai Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/cxgb4/cq.c | 2 +- drivers/infiniband/hw/cxgb4/qp.c | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index b4eeb783573c..b0b955724458 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -162,7 +162,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq, cq->bar2_va = c4iw_bar2_addrs(rdev, cq->cqid, T4_BAR2_QTYPE_INGRESS, &cq->bar2_qid, user ? &cq->bar2_pa : NULL); - if (user && !cq->bar2_va) { + if (user && !cq->bar2_pa) { pr_warn(MOD "%s: cqid %u not in BAR2 range.\n", pci_name(rdev->lldi.pdev), cq->cqid); ret = -EINVAL; diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 8aa2e52b453e..e8993e49b8b3 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -185,6 +185,10 @@ void __iomem *c4iw_bar2_addrs(struct c4iw_rdev *rdev, unsigned int qid, if (pbar2_pa) *pbar2_pa = (rdev->bar2_pa + bar2_qoffset) & PAGE_MASK; + + if (is_t4(rdev->lldi.adapter_type)) + return NULL; + return rdev->bar2_kva + bar2_qoffset; } @@ -270,7 +274,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq, /* * User mode must have bar2 access. */ - if (user && (!wq->sq.bar2_va || !wq->rq.bar2_va)) { + if (user && (!wq->sq.bar2_pa || !wq->rq.bar2_pa)) { pr_warn(MOD "%s: sqid %u or rqid %u not in BAR2 range.\n", pci_name(rdev->lldi.pdev), wq->sq.qid, wq->rq.qid); goto free_dma; From e16d8a6cbb499c5c8bfe9330d3351b649bded4af Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 26 Apr 2016 08:52:44 -0700 Subject: [PATCH 115/181] Revert "x86/mm/32: Set NX in __supported_pte_mask before enabling paging" This reverts commit 320d25b6a05f8b73c23fc21025d2906ecdd2d4fc. This change was problematic for a couple of reasons: 1. It missed a some entry points (Xen things and 64-bit native). 2. The entry it changed can be executed more than once. This isn't really a problem, but it conflated per-cpu state setup and global state setup. 3. It broke 64-bit non-NX. 64-bit non-NX worked the other way around from 32-bit -- __supported_pte_mask had NX set initially and was *cleared* in x86_configure_nx. With the patch applied, it never got cleared. Reported-and-tested-by: Meelis Roos Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/59bd15f7f4b56b633a611b7f70876c6d2ad01a98.1461685884.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/kernel/head_32.S | 6 ------ arch/x86/mm/setup_nx.c | 5 +++-- 2 files changed, 3 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 54cdbd2003fe..af1112980dd4 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -389,12 +389,6 @@ default_entry: /* Make changes effective */ wrmsr - /* - * And make sure that all the mappings we set up have NX set from - * the beginning. - */ - orl $(1 << (_PAGE_BIT_NX - 32)), pa(__supported_pte_mask + 4) - enable_paging: /* diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index 8bea84724a7d..f65a33f505b6 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -32,8 +32,9 @@ early_param("noexec", noexec_setup); void x86_configure_nx(void) { - /* If disable_nx is set, clear NX on all new mappings going forward. */ - if (disable_nx) + if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) + __supported_pte_mask |= _PAGE_NX; + else __supported_pte_mask &= ~_PAGE_NX; } From 8358b02bf67d3a5d8a825070e1aa73f25fb2e4c7 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 26 Apr 2016 22:26:26 +0200 Subject: [PATCH 116/181] bpf: fix double-fdput in replace_map_fd_with_map_ptr() When bpf(BPF_PROG_LOAD, ...) was invoked with a BPF program whose bytecode references a non-map file descriptor as a map file descriptor, the error handling code called fdput() twice instead of once (in __bpf_map_get() and in replace_map_fd_with_map_ptr()). If the file descriptor table of the current task is shared, this causes f_count to be decremented too much, allowing the struct file to be freed while it is still in use (use-after-free). This can be exploited to gain root privileges by an unprivileged user. This bug was introduced in commit 0246e64d9a5f ("bpf: handle pseudo BPF_LD_IMM64 insn"), but is only exploitable since commit 1be7f75d1668 ("bpf: enable non-root eBPF programs") because previously, CAP_SYS_ADMIN was required to reach the vulnerable code. (posted publicly according to request by maintainer) Signed-off-by: Jann Horn Signed-off-by: Linus Torvalds Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 618ef77c302a..db2574e7b8b0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2030,7 +2030,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env) if (IS_ERR(map)) { verbose("fd %d is not pointing to valid bpf_map\n", insn->imm); - fdput(f); return PTR_ERR(map); } From 8ead9dd54716d1e05e129959f702fcc1786f82b4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 25 Apr 2016 20:04:08 -0700 Subject: [PATCH 117/181] devpts: more pty driver interface cleanups This is more prep-work for the upcoming pty changes. Still just code cleanup with no actual semantic changes. This removes a bunch pointless complexity by just having the slave pty side remember the dentry associated with the devpts slave rather than the inode. That allows us to remove all the "look up the dentry" code for when we want to remove it again. Together with moving the tty pointer from "inode->i_private" to "dentry->d_fsdata" and getting rid of pointless inode locking, this removes about 30 lines of code. Not only is the end result smaller, it's simpler and easier to understand. The old code, for example, depended on the d_find_alias() to not just find the dentry, but also to check that it is still hashed, which in turn validated the tty pointer in the inode. That is a _very_ roundabout way to say "invalidate the cached tty pointer when the dentry is removed". The new code just does dentry->d_fsdata = NULL; in devpts_pty_kill() instead, invalidating the tty pointer rather more directly and obviously. Don't do something complex and subtle when the obvious straightforward approach will do. The rest of the patch (ie apart from code deletion and the above tty pointer clearing) is just switching the calling convention to pass the dentry or file pointer around instead of the inode. Cc: Eric Biederman Cc: Peter Anvin Cc: Andy Lutomirski Cc: Al Viro Cc: Peter Hurley Cc: Serge Hallyn Cc: Willy Tarreau Cc: Aurelien Jarno Cc: Alan Cox Cc: Jann Horn Cc: Greg KH Cc: Jiri Slaby Cc: Florian Weimer Signed-off-by: Linus Torvalds --- drivers/tty/pty.c | 18 ++++++------- drivers/tty/tty_io.c | 6 ++--- fs/devpts/inode.c | 53 +++++++++----------------------------- include/linux/devpts_fs.h | 6 ++--- include/linux/tty_driver.h | 4 +-- 5 files changed, 28 insertions(+), 59 deletions(-) diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 0058d9fbf931..cf0dc51a2690 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -626,7 +626,7 @@ static int pty_unix98_ioctl(struct tty_struct *tty, */ static struct tty_struct *ptm_unix98_lookup(struct tty_driver *driver, - struct inode *ptm_inode, int idx) + struct file *file, int idx) { /* Master must be open via /dev/ptmx */ return ERR_PTR(-EIO); @@ -642,12 +642,12 @@ static struct tty_struct *ptm_unix98_lookup(struct tty_driver *driver, */ static struct tty_struct *pts_unix98_lookup(struct tty_driver *driver, - struct inode *pts_inode, int idx) + struct file *file, int idx) { struct tty_struct *tty; mutex_lock(&devpts_mutex); - tty = devpts_get_priv(pts_inode); + tty = devpts_get_priv(file->f_path.dentry); mutex_unlock(&devpts_mutex); /* Master must be open before slave */ if (!tty) @@ -722,7 +722,7 @@ static int ptmx_open(struct inode *inode, struct file *filp) { struct pts_fs_info *fsi; struct tty_struct *tty; - struct inode *slave_inode; + struct dentry *dentry; int retval; int index; @@ -769,14 +769,12 @@ static int ptmx_open(struct inode *inode, struct file *filp) tty_add_file(tty, filp); - slave_inode = devpts_pty_new(fsi, - MKDEV(UNIX98_PTY_SLAVE_MAJOR, index), index, - tty->link); - if (IS_ERR(slave_inode)) { - retval = PTR_ERR(slave_inode); + dentry = devpts_pty_new(fsi, index, tty->link); + if (IS_ERR(dentry)) { + retval = PTR_ERR(dentry); goto err_release; } - tty->link->driver_data = slave_inode; + tty->link->driver_data = dentry; retval = ptm_driver->ops->open(tty, filp); if (retval) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 9b04d72e752e..24d5491ef0da 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1367,12 +1367,12 @@ static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p) * Locking: tty_mutex must be held. If the tty is found, bump the tty kref. */ static struct tty_struct *tty_driver_lookup_tty(struct tty_driver *driver, - struct inode *inode, int idx) + struct file *file, int idx) { struct tty_struct *tty; if (driver->ops->lookup) - tty = driver->ops->lookup(driver, inode, idx); + tty = driver->ops->lookup(driver, file, idx); else tty = driver->ttys[idx]; @@ -2040,7 +2040,7 @@ static struct tty_struct *tty_open_by_driver(dev_t device, struct inode *inode, } /* check whether we're reopening an existing tty */ - tty = tty_driver_lookup_tty(driver, inode, index); + tty = tty_driver_lookup_tty(driver, filp, index); if (IS_ERR(tty)) { mutex_unlock(&tty_mutex); goto out; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 0af8e7d70d27..0b2954d7172d 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -604,8 +604,7 @@ void devpts_put_ref(struct pts_fs_info *fsi) * * The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill. */ -struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index, - void *priv) +struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv) { struct dentry *dentry; struct super_block *sb; @@ -629,25 +628,21 @@ struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index, inode->i_uid = opts->setuid ? opts->uid : current_fsuid(); inode->i_gid = opts->setgid ? opts->gid : current_fsgid(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - init_special_inode(inode, S_IFCHR|opts->mode, device); - inode->i_private = priv; + init_special_inode(inode, S_IFCHR|opts->mode, MKDEV(UNIX98_PTY_SLAVE_MAJOR, index)); sprintf(s, "%d", index); - inode_lock(d_inode(root)); - dentry = d_alloc_name(root, s); if (dentry) { + dentry->d_fsdata = priv; d_add(dentry, inode); fsnotify_create(d_inode(root), dentry); } else { iput(inode); - inode = ERR_PTR(-ENOMEM); + dentry = ERR_PTR(-ENOMEM); } - inode_unlock(d_inode(root)); - - return inode; + return dentry; } /** @@ -656,24 +651,10 @@ struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index, * * Returns whatever was passed as priv in devpts_pty_new for a given inode. */ -void *devpts_get_priv(struct inode *pts_inode) +void *devpts_get_priv(struct dentry *dentry) { - struct dentry *dentry; - void *priv = NULL; - - BUG_ON(pts_inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR)); - - /* Ensure dentry has not been deleted by devpts_pty_kill() */ - dentry = d_find_alias(pts_inode); - if (!dentry) - return NULL; - - if (pts_inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC) - priv = pts_inode->i_private; - - dput(dentry); - - return priv; + WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC); + return dentry->d_fsdata; } /** @@ -682,24 +663,14 @@ void *devpts_get_priv(struct inode *pts_inode) * * This is an inverse operation of devpts_pty_new. */ -void devpts_pty_kill(struct inode *inode) +void devpts_pty_kill(struct dentry *dentry) { - struct super_block *sb = pts_sb_from_inode(inode); - struct dentry *root = sb->s_root; - struct dentry *dentry; + WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC); - BUG_ON(inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR)); - - inode_lock(d_inode(root)); - - dentry = d_find_alias(inode); - - drop_nlink(inode); + dentry->d_fsdata = NULL; + drop_nlink(dentry->d_inode); d_delete(dentry); dput(dentry); /* d_alloc_name() in devpts_pty_new() */ - dput(dentry); /* d_find_alias above */ - - inode_unlock(d_inode(root)); } static int __init init_devpts_fs(void) diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 358a4db72a27..5871f292b596 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -27,11 +27,11 @@ int devpts_new_index(struct pts_fs_info *); void devpts_kill_index(struct pts_fs_info *, int); /* mknod in devpts */ -struct inode *devpts_pty_new(struct pts_fs_info *, dev_t, int, void *); +struct dentry *devpts_pty_new(struct pts_fs_info *, int, void *); /* get private structure */ -void *devpts_get_priv(struct inode *pts_inode); +void *devpts_get_priv(struct dentry *); /* unlink */ -void devpts_pty_kill(struct inode *inode); +void devpts_pty_kill(struct dentry *); #endif diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 161052477f77..b742b5e47cc2 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -7,7 +7,7 @@ * defined; unless noted otherwise, they are optional, and can be * filled in with a null pointer. * - * struct tty_struct * (*lookup)(struct tty_driver *self, int idx) + * struct tty_struct * (*lookup)(struct tty_driver *self, struct file *, int idx) * * Return the tty device corresponding to idx, NULL if there is not * one currently in use and an ERR_PTR value on error. Called under @@ -250,7 +250,7 @@ struct serial_icounter_struct; struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, - struct inode *inode, int idx); + struct file *filp, int idx); int (*install)(struct tty_driver *driver, struct tty_struct *tty); void (*remove)(struct tty_driver *driver, struct tty_struct *tty); int (*open)(struct tty_struct * tty, struct file * filp); From 263efde31f97c498e1ebad30e4d2906609d7ad6b Mon Sep 17 00:00:00 2001 From: "cpaul@redhat.com" Date: Fri, 22 Apr 2016 16:08:46 -0400 Subject: [PATCH 118/181] drm/dp/mst: Get validated port ref in drm_dp_update_payload_part1() We can thank KASAN for finding this, otherwise I probably would have spent hours on it. This fixes a somewhat harder to trigger kernel panic, occuring while enabling MST where the port we were currently updating the payload on would have all of it's refs dropped before we finished what we were doing: ================================================================== BUG: KASAN: use-after-free in drm_dp_update_payload_part1+0xb3f/0xdb0 [drm_kms_helper] at addr ffff8800d29de018 Read of size 4 by task Xorg/973 ============================================================================= BUG kmalloc-2048 (Tainted: G B W ): kasan: bad access detected ----------------------------------------------------------------------------- INFO: Allocated in drm_dp_add_port+0x1aa/0x1ed0 [drm_kms_helper] age=16477 cpu=0 pid=2175 ___slab_alloc+0x472/0x490 __slab_alloc+0x20/0x40 kmem_cache_alloc_trace+0x151/0x190 drm_dp_add_port+0x1aa/0x1ed0 [drm_kms_helper] drm_dp_send_link_address+0x526/0x960 [drm_kms_helper] drm_dp_check_and_send_link_address+0x1ac/0x210 [drm_kms_helper] drm_dp_mst_link_probe_work+0x77/0xd0 [drm_kms_helper] process_one_work+0x562/0x1350 worker_thread+0xd9/0x1390 kthread+0x1c5/0x260 ret_from_fork+0x22/0x40 INFO: Freed in drm_dp_free_mst_port+0x50/0x60 [drm_kms_helper] age=7521 cpu=0 pid=2175 __slab_free+0x17f/0x2d0 kfree+0x169/0x180 drm_dp_free_mst_port+0x50/0x60 [drm_kms_helper] drm_dp_destroy_connector_work+0x2b8/0x490 [drm_kms_helper] process_one_work+0x562/0x1350 worker_thread+0xd9/0x1390 kthread+0x1c5/0x260 ret_from_fork+0x22/0x40 which on this T460s, would eventually lead to kernel panics in somewhat random places later in intel_mst_enable_dp() if we got lucky enough. Signed-off-by: Lyude Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_dp_mst_topology.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index e17fbdaf874b..935d8cc46841 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1796,6 +1796,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) req_payload.start_slot = cur_slots; if (mgr->proposed_vcpis[i]) { port = container_of(mgr->proposed_vcpis[i], struct drm_dp_mst_port, vcpi); + port = drm_dp_get_validated_port_ref(mgr, port); + if (!port) { + mutex_unlock(&mgr->payload_lock); + return -EINVAL; + } req_payload.num_slots = mgr->proposed_vcpis[i]->num_slots; req_payload.vcpi = mgr->proposed_vcpis[i]->vcpi; } else { @@ -1823,6 +1828,9 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) mgr->payloads[i].payload_state = req_payload.payload_state; } cur_slots += req_payload.num_slots; + + if (port) + drm_dp_put_port(port); } for (i = 0; i < mgr->max_payloads; i++) { From 9dc0487d96a0396367a1451b31873482080b527f Mon Sep 17 00:00:00 2001 From: Lyude Date: Wed, 13 Apr 2016 16:50:18 -0400 Subject: [PATCH 119/181] drm/dp/mst: Restore primary hub guid on resume Some hubs are forgetful, and end up forgetting whatever GUID we set previously after we do a suspend/resume cycle. This can lead to hotplugging breaking (along with probably other things) since the hub will start sending connection notifications with the wrong GUID. As such, we need to check on resume whether or not the GUID the hub is giving us is valid. Signed-off-by: Lyude Reviewed-by: Harry Wentland Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1460580618-7421-1-git-send-email-cpaul@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_dp_mst_topology.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 935d8cc46841..71ea0521ea96 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -2136,6 +2136,8 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) if (mgr->mst_primary) { int sret; + u8 guid[16]; + sret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd, DP_RECEIVER_CAP_SIZE); if (sret != DP_RECEIVER_CAP_SIZE) { DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); @@ -2150,6 +2152,16 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) ret = -1; goto out_unlock; } + + /* Some hubs forget their guids after they resume */ + sret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (sret != 16) { + DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); + ret = -1; + goto out_unlock; + } + drm_dp_check_mstb_guid(mgr->mst_primary, guid); + ret = 0; } else ret = -1; From 9a11d2e7e66b6b8764a2430686b8716637bf812e Mon Sep 17 00:00:00 2001 From: Gustavo Padovan Date: Thu, 14 Apr 2016 10:58:54 -0700 Subject: [PATCH 120/181] drm/virtio: send vblank event after crtc updates virtio_gpu was failing to send vblank events when using the atomic IOCTL with the DRM_MODE_PAGE_FLIP_EVENT flag set. This patch fixes each and enables atomic pageflips updates. Signed-off-by: Gustavo Padovan Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie --- drivers/gpu/drm/virtio/virtgpu_display.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 4854dac87e24..5fd1fd06effc 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -267,11 +267,23 @@ static int virtio_gpu_crtc_atomic_check(struct drm_crtc *crtc, return 0; } +static void virtio_gpu_crtc_atomic_flush(struct drm_crtc *crtc, + struct drm_crtc_state *old_state) +{ + unsigned long flags; + + spin_lock_irqsave(&crtc->dev->event_lock, flags); + if (crtc->state->event) + drm_crtc_send_vblank_event(crtc, crtc->state->event); + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); +} + static const struct drm_crtc_helper_funcs virtio_gpu_crtc_helper_funcs = { .enable = virtio_gpu_crtc_enable, .disable = virtio_gpu_crtc_disable, .mode_set_nofb = virtio_gpu_crtc_mode_set_nofb, .atomic_check = virtio_gpu_crtc_atomic_check, + .atomic_flush = virtio_gpu_crtc_atomic_flush, }; static void virtio_gpu_enc_mode_set(struct drm_encoder *encoder, From d6776bba44d9752f6cdf640046070e71ee4bba7b Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 22 Apr 2016 14:57:48 +1000 Subject: [PATCH 121/181] cxl: Keep IRQ mappings on context teardown Keep IRQ mappings on context teardown. This won't leak IRQs as if we allocate the mapping again, the generic code will give the same mapping used last time. Doing this works around a race in the generic code. Masking the interrupt introduces a race which can crash the kernel or result in IRQ that is never EOIed. The lost of EOI results in all subsequent mappings to the same HW IRQ never receiving an interrupt. We've seen this race with cxl test cases which are doing heavy context startup and teardown at the same time as heavy interrupt load. A fix to the generic code is being investigated also. Signed-off-by: Michael Neuling Cc: stable@vger.kernel.org # 3.8 Tested-by: Andrew Donnellan Acked-by: Ian Munsie Tested-by: Vaibhav Jain Signed-off-by: Michael Ellerman --- drivers/misc/cxl/irq.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c index be646dc41a2c..8def4553acba 100644 --- a/drivers/misc/cxl/irq.c +++ b/drivers/misc/cxl/irq.c @@ -203,7 +203,6 @@ unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq, void cxl_unmap_irq(unsigned int virq, void *cookie) { free_irq(virq, cookie); - irq_dispose_mapping(virq); } int cxl_register_one_irq(struct cxl *adapter, From 2bc79ffcbb817873cc43d63118008ab75181b73d Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 22 Apr 2016 14:57:49 +1000 Subject: [PATCH 122/181] cxl: Poll for outstanding IRQs when detaching a context When detaching contexts, we may still have interrupts in the system which are yet to be delivered to any CPU and be acked in the PSL. This can result in a subsequent unrelated process getting an spurious IRQ or an interrupt for a non-existent context. This polls the PSL to ensure that the PSL is clear of IRQs for the detached context, before removing the context from the idr. Signed-off-by: Michael Neuling Tested-by: Andrew Donnellan Acked-by: Ian Munsie Tested-by: Vaibhav Jain Signed-off-by: Michael Ellerman --- drivers/misc/cxl/context.c | 7 +++++++ drivers/misc/cxl/cxl.h | 2 ++ drivers/misc/cxl/native.c | 31 +++++++++++++++++++++++++++++++ 3 files changed, 40 insertions(+) diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c index 10370f280500..7edea9c19199 100644 --- a/drivers/misc/cxl/context.c +++ b/drivers/misc/cxl/context.c @@ -223,6 +223,13 @@ int __detach_context(struct cxl_context *ctx) cxl_ops->link_ok(ctx->afu->adapter, ctx->afu)); flush_work(&ctx->fault_work); /* Only needed for dedicated process */ + /* + * Wait until no further interrupts are presented by the PSL + * for this context. + */ + if (cxl_ops->irq_wait) + cxl_ops->irq_wait(ctx); + /* release the reference to the group leader and mm handling pid */ put_pid(ctx->pid); put_pid(ctx->glpid); diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index 38e21cf7806e..73dc2a33da74 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -274,6 +274,7 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An = {0x0A0}; #define CXL_PSL_DSISR_An_PE (1ull << (63-4)) /* PSL Error (implementation specific) */ #define CXL_PSL_DSISR_An_AE (1ull << (63-5)) /* AFU Error */ #define CXL_PSL_DSISR_An_OC (1ull << (63-6)) /* OS Context Warning */ +#define CXL_PSL_DSISR_PENDING (CXL_PSL_DSISR_TRANS | CXL_PSL_DSISR_An_PE | CXL_PSL_DSISR_An_AE | CXL_PSL_DSISR_An_OC) /* NOTE: Bits 32:63 are undefined if DSISR[DS] = 1 */ #define CXL_PSL_DSISR_An_M DSISR_NOHPTE /* PTE not found */ #define CXL_PSL_DSISR_An_P DSISR_PROTFAULT /* Storage protection violation */ @@ -855,6 +856,7 @@ struct cxl_backend_ops { u64 dsisr, u64 errstat); irqreturn_t (*psl_interrupt)(int irq, void *data); int (*ack_irq)(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask); + void (*irq_wait)(struct cxl_context *ctx); int (*attach_process)(struct cxl_context *ctx, bool kernel, u64 wed, u64 amr); int (*detach_process)(struct cxl_context *ctx); diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index 387fcbdf9793..ecf7557cd657 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -797,6 +798,35 @@ static irqreturn_t native_irq_multiplexed(int irq, void *data) return fail_psl_irq(afu, &irq_info); } +void native_irq_wait(struct cxl_context *ctx) +{ + u64 dsisr; + int timeout = 1000; + int ph; + + /* + * Wait until no further interrupts are presented by the PSL + * for this context. + */ + while (timeout--) { + ph = cxl_p2n_read(ctx->afu, CXL_PSL_PEHandle_An) & 0xffff; + if (ph != ctx->pe) + return; + dsisr = cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An); + if ((dsisr & CXL_PSL_DSISR_PENDING) == 0) + return; + /* + * We are waiting for the workqueue to process our + * irq, so need to let that run here. + */ + msleep(1); + } + + dev_warn(&ctx->afu->dev, "WARNING: waiting on DSI for PE %i" + " DSISR %016llx!\n", ph, dsisr); + return; +} + static irqreturn_t native_slice_irq_err(int irq, void *data) { struct cxl_afu *afu = data; @@ -1076,6 +1106,7 @@ const struct cxl_backend_ops cxl_native_ops = { .handle_psl_slice_error = native_handle_psl_slice_error, .psl_interrupt = NULL, .ack_irq = native_ack_irq, + .irq_wait = native_irq_wait, .attach_process = native_attach_process, .detach_process = native_detach_process, .support_attributes = native_support_attributes, From d701cca6744fe0d67c86346dcfc9b128b17b5045 Mon Sep 17 00:00:00 2001 From: Rui Salvaterra Date: Tue, 19 Apr 2016 13:23:36 +0100 Subject: [PATCH 123/181] powerpc: wire up preadv2 and pwritev2 syscalls Wire up preadv2/pwritev2 in the same way as preadv/pwritev. Fixes two build warnings on ppc64. mpe: Lightly tested with fio (slightly hacked to add the syscall wrappers): fio-4217 [009] .... 1304.635300: sys_preadv2(fd: 3, vec: 10025821de0, vlen: 1, pos_l: 6253000, pos_h: 0, flags: 1) fio-4217 [009] .... 1304.635474: sys_preadv2 -> 0x1000 Signed-off-by: Rui Salvaterra Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/systbl.h | 2 ++ arch/powerpc/include/asm/unistd.h | 2 +- arch/powerpc/include/uapi/asm/unistd.h | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 3fa9df70aa20..2fc5d4db503c 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -384,3 +384,5 @@ SYSCALL(ni_syscall) SYSCALL(ni_syscall) SYSCALL(mlock2) SYSCALL(copy_file_range) +COMPAT_SYS_SPU(preadv2) +COMPAT_SYS_SPU(pwritev2) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 1f2594d45605..cf12c580f6b2 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include -#define NR_syscalls 380 +#define NR_syscalls 382 #define __NR__exit __NR_exit diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 940290d45b08..e9f5f41aa55a 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -390,5 +390,7 @@ #define __NR_membarrier 365 #define __NR_mlock2 378 #define __NR_copy_file_range 379 +#define __NR_preadv2 380 +#define __NR_pwritev2 381 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ From 532c34b5fbf1687df63b3fcd5b2846312ac943c6 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 25 Apr 2016 17:54:28 +0200 Subject: [PATCH 124/181] s390/sclp_ctl: fix potential information leak with /dev/sclp The sclp_ctl_ioctl_sccb function uses two copy_from_user calls to retrieve the sclp request from user space. The first copy_from_user fetches the length of the request which is stored in the first two bytes of the request. The second copy_from_user gets the complete sclp request, but this copies the length field a second time. A malicious user may have changed the length in the meantime. Reported-by: Pengfei Wang Reviewed-by: Michael Holzheu Signed-off-by: Martin Schwidefsky --- drivers/s390/char/sclp_ctl.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/s390/char/sclp_ctl.c b/drivers/s390/char/sclp_ctl.c index 648cb86afd42..ea607a4a1bdd 100644 --- a/drivers/s390/char/sclp_ctl.c +++ b/drivers/s390/char/sclp_ctl.c @@ -56,6 +56,7 @@ static int sclp_ctl_ioctl_sccb(void __user *user_area) { struct sclp_ctl_sccb ctl_sccb; struct sccb_header *sccb; + unsigned long copied; int rc; if (copy_from_user(&ctl_sccb, user_area, sizeof(ctl_sccb))) @@ -65,14 +66,15 @@ static int sclp_ctl_ioctl_sccb(void __user *user_area) sccb = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA); if (!sccb) return -ENOMEM; - if (copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), sizeof(*sccb))) { + copied = PAGE_SIZE - + copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), PAGE_SIZE); + if (offsetof(struct sccb_header, length) + + sizeof(sccb->length) > copied || sccb->length > copied) { rc = -EFAULT; goto out_free; } - if (sccb->length > PAGE_SIZE || sccb->length < 8) - return -EINVAL; - if (copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), sccb->length)) { - rc = -EFAULT; + if (sccb->length < 8) { + rc = -EINVAL; goto out_free; } rc = sclp_sync_request(ctl_sccb.cmdw, sccb); From a8950e49bd241dc9ad90c24e92e23e95dbe9f018 Mon Sep 17 00:00:00 2001 From: Romain Perier Date: Tue, 19 Apr 2016 18:17:32 +0800 Subject: [PATCH 125/181] nios2: memset: use the right constraint modifier for the %4 output operand Depending on the size of the area to be memset'ed, the nios2 memset implementation either uses a naive loop (for buffers smaller or equal than 8 bytes) or a more optimized implementation (for buffers larger than 8 bytes). This implementation does 4-byte stores rather than 1-byte stores to speed up memset. However, we discovered that on our nios2 platform, memset() was not properly setting the buffer to the expected value. A memset of 0xff would not set the entire buffer to 0xff, but to: 0xff 0x00 0xff 0x00 0xff 0x00 0xff 0x00 ... Which is obviously incorrect. Our investigation has revealed that the problem lies in the incorrect constraints used in the inline assembly. The following piece of assembly, from the nios2 memset implementation, is supposed to create a 4-byte value that repeats 4 times the 1-byte pattern passed as memset argument: /* fill8 %3, %5 (c & 0xff) */ " slli %4, %5, 8\n" " or %4, %4, %5\n" " slli %3, %4, 16\n" " or %3, %3, %4\n" However, depending on the compiler and optimization level, this code might be compiled as: 34: 280a923a slli r5,r5,8 38: 294ab03a or r5,r5,r5 3c: 2808943a slli r4,r5,16 40: 2148b03a or r4,r4,r5 This is wrong because r5 gets used both for %5 and %4, which leads to the final pattern stored in r4 to be 0xff00ff00 rather than the expected 0xffffffff. %4 is defined with the "=r" constraint, i.e as an output operand. However, as explained in http://www.ethernut.de/en/documents/arm-inline-asm.html, this does not prevent gcc from using the same register for an output operand (%4) and input operand (%5). By using the constraint modifier '&', we indicate that the register should be used for output only. With this change, we get the following assembly output: 34: 2810923a slli r8,r5,8 38: 4150b03a or r8,r8,r5 3c: 400e943a slli r7,r8,16 40: 3a0eb03a or r7,r7,r8 Which correctly produces the 0xffffffff pattern when 0xff is passed as the memset() pattern. It is worth mentioning the observed consequence of this bug: we were hitting the kernel BUG() in mm/bootmem.c:__free() that verifies when marking a page as free that it was previously marked as occupied (i.e that the bit was set to 1). The entire bootmem bitmap is set to 0xff bit via a memset() during the bootmem initialization. The bootmem_free() call right after the initialization was finding some bits to be set to 0, which didn't make sense since the bitmap has just been memset'ed to 0xff. Except that due to the bug explained above, the bitmap was in fact initialized to 0xff00ff00. Thanks to Marek Vasut for his help and feedback. Signed-off-by: Romain Perier Acked-by: Marek Vasut Acked-by: Ley Foon Tan --- arch/nios2/lib/memset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/nios2/lib/memset.c b/arch/nios2/lib/memset.c index c2cfcb121e34..2fcefe720283 100644 --- a/arch/nios2/lib/memset.c +++ b/arch/nios2/lib/memset.c @@ -68,7 +68,7 @@ void *memset(void *s, int c, size_t count) "=r" (charcnt), /* %1 Output */ "=r" (dwordcnt), /* %2 Output */ "=r" (fill8reg), /* %3 Output */ - "=r" (wrkrega) /* %4 Output */ + "=&r" (wrkrega) /* %4 Output only */ : "r" (c), /* %5 Input */ "0" (s), /* %0 Input/Output */ "1" (count) /* %1 Input/Output */ From 32ed9a0e0ddcf58ef343bcb6ae44ee60d1ee31ce Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Tue, 26 Apr 2016 19:29:33 +0300 Subject: [PATCH 126/181] ARC: support generic per-device coherent dma mem Signed-off-by: Alexey Brodkin Cc: linux-kernel@vger.kernel.org Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 12d0284a46e5..28d47f8eb934 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -37,6 +37,7 @@ config ARC select OF_EARLY_FLATTREE select PERF_USE_VMALLOC select HAVE_DEBUG_STACKOVERFLOW + select HAVE_GENERIC_DMA_COHERENT config MIGHT_HAVE_PCI bool From 1b10cb21d888c021bedbe678f7c26aee1bf04ffa Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Tue, 26 Apr 2016 19:29:34 +0300 Subject: [PATCH 127/181] ARC: add support for reserved memory defined by device tree Enable reserved memory initialization from device tree. Signed-off-by: Alexey Brodkin Cc: Grant Likely Cc: Marek Szyprowski Cc: linux-kernel@vger.kernel.org Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 1 + arch/arc/mm/init.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 28d47f8eb934..ec4791ea6911 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -35,6 +35,7 @@ config ARC select NO_BOOTMEM select OF select OF_EARLY_FLATTREE + select OF_RESERVED_MEM select PERF_USE_VMALLOC select HAVE_DEBUG_STACKOVERFLOW select HAVE_GENERIC_DMA_COHERENT diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 7d2c4fbf4f22..5487d0b97400 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -13,6 +13,7 @@ #ifdef CONFIG_BLK_DEV_INITRD #include #endif +#include #include #include #include @@ -136,6 +137,9 @@ void __init setup_arch_memory(void) memblock_reserve(__pa(initrd_start), initrd_end - initrd_start); #endif + early_init_fdt_reserve_self(); + early_init_fdt_scan_reserved_mem(); + memblock_dump_all(); /*----------------- node/zones setup --------------------------*/ From 56fc350224f16901db709cd8cba86bac751aa2a2 Mon Sep 17 00:00:00 2001 From: Flora Cui Date: Wed, 20 Apr 2016 10:23:47 +0800 Subject: [PATCH 128/181] drm/ttm: fix kref count mess in ttm_bo_move_to_lru_tail MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes the following scenario: 1. Page table bo allocated in vram and linked to man->lru. tbo->list_kref.refcount=2 2. Page table bo is swapped out and removed from man->lru. tbo->list_kref.refcount=1 3. Command submission from userspace. Page table bo is moved to vram. ttm_bo_move_to_lru_tail() link it to man->lru and don't increase the kref count. Reviewed-by: Thomas Hellstrom Signed-off-by: Flora Cui Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/ttm/ttm_bo.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 4cbf26555093..e3daafa1be13 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -230,22 +230,13 @@ EXPORT_SYMBOL(ttm_bo_del_sub_from_lru); void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo) { - struct ttm_bo_device *bdev = bo->bdev; - struct ttm_mem_type_manager *man; + int put_count = 0; lockdep_assert_held(&bo->resv->lock.base); - if (bo->mem.placement & TTM_PL_FLAG_NO_EVICT) { - list_del_init(&bo->swap); - list_del_init(&bo->lru); - - } else { - if (bo->ttm && !(bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) - list_move_tail(&bo->swap, &bo->glob->swap_lru); - - man = &bdev->man[bo->mem.mem_type]; - list_move_tail(&bo->lru, &man->lru); - } + put_count = ttm_bo_del_from_lru(bo); + ttm_bo_list_ref_sub(bo, put_count, true); + ttm_bo_add_to_lru(bo); } EXPORT_SYMBOL(ttm_bo_move_to_lru_tail); From 5d5b7803c49bbb01bdf4c6e95e8314d0515b9484 Mon Sep 17 00:00:00 2001 From: Vitaly Prosyak Date: Thu, 14 Apr 2016 13:34:03 -0400 Subject: [PATCH 129/181] drm/radeon: fix vertical bars appear on monitor (v2) When crtc/timing is disabled on boot the dig block should be stopped in order ignore timing from crtc, reset the steering fifo otherwise we get display corruption or hung in dp sst mode. v2: agd: fix coding style Signed-off-by: Vitaly Prosyak Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/evergreen.c | 154 ++++++++++++++++++++++++- drivers/gpu/drm/radeon/evergreen_reg.h | 46 ++++++++ 2 files changed, 199 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 76c4bdf21b20..34f7a29d9366 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2608,10 +2608,152 @@ static void evergreen_agp_enable(struct radeon_device *rdev) WREG32(VM_CONTEXT1_CNTL, 0); } +static const unsigned ni_dig_offsets[] = +{ + NI_DIG0_REGISTER_OFFSET, + NI_DIG1_REGISTER_OFFSET, + NI_DIG2_REGISTER_OFFSET, + NI_DIG3_REGISTER_OFFSET, + NI_DIG4_REGISTER_OFFSET, + NI_DIG5_REGISTER_OFFSET +}; + +static const unsigned ni_tx_offsets[] = +{ + NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1 +}; + +static const unsigned evergreen_dp_offsets[] = +{ + EVERGREEN_DP0_REGISTER_OFFSET, + EVERGREEN_DP1_REGISTER_OFFSET, + EVERGREEN_DP2_REGISTER_OFFSET, + EVERGREEN_DP3_REGISTER_OFFSET, + EVERGREEN_DP4_REGISTER_OFFSET, + EVERGREEN_DP5_REGISTER_OFFSET +}; + + +/* + * Assumption is that EVERGREEN_CRTC_MASTER_EN enable for requested crtc + * We go from crtc to connector and it is not relible since it + * should be an opposite direction .If crtc is enable then + * find the dig_fe which selects this crtc and insure that it enable. + * if such dig_fe is found then find dig_be which selects found dig_be and + * insure that it enable and in DP_SST mode. + * if UNIPHY_PLL_CONTROL1.enable then we should disconnect timing + * from dp symbols clocks . + */ +static bool evergreen_is_dp_sst_stream_enabled(struct radeon_device *rdev, + unsigned crtc_id, unsigned *ret_dig_fe) +{ + unsigned i; + unsigned dig_fe; + unsigned dig_be; + unsigned dig_en_be; + unsigned uniphy_pll; + unsigned digs_fe_selected; + unsigned dig_be_mode; + unsigned dig_fe_mask; + bool is_enabled = false; + bool found_crtc = false; + + /* loop through all running dig_fe to find selected crtc */ + for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) { + dig_fe = RREG32(NI_DIG_FE_CNTL + ni_dig_offsets[i]); + if (dig_fe & NI_DIG_FE_CNTL_SYMCLK_FE_ON && + crtc_id == NI_DIG_FE_CNTL_SOURCE_SELECT(dig_fe)) { + /* found running pipe */ + found_crtc = true; + dig_fe_mask = 1 << i; + dig_fe = i; + break; + } + } + + if (found_crtc) { + /* loop through all running dig_be to find selected dig_fe */ + for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) { + dig_be = RREG32(NI_DIG_BE_CNTL + ni_dig_offsets[i]); + /* if dig_fe_selected by dig_be? */ + digs_fe_selected = NI_DIG_BE_CNTL_FE_SOURCE_SELECT(dig_be); + dig_be_mode = NI_DIG_FE_CNTL_MODE(dig_be); + if (dig_fe_mask & digs_fe_selected && + /* if dig_be in sst mode? */ + dig_be_mode == NI_DIG_BE_DPSST) { + dig_en_be = RREG32(NI_DIG_BE_EN_CNTL + + ni_dig_offsets[i]); + uniphy_pll = RREG32(NI_DCIO_UNIPHY0_PLL_CONTROL1 + + ni_tx_offsets[i]); + /* dig_be enable and tx is running */ + if (dig_en_be & NI_DIG_BE_EN_CNTL_ENABLE && + dig_en_be & NI_DIG_BE_EN_CNTL_SYMBCLK_ON && + uniphy_pll & NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE) { + is_enabled = true; + *ret_dig_fe = dig_fe; + break; + } + } + } + } + + return is_enabled; +} + +/* + * Blank dig when in dp sst mode + * Dig ignores crtc timing + */ +static void evergreen_blank_dp_output(struct radeon_device *rdev, + unsigned dig_fe) +{ + unsigned stream_ctrl; + unsigned fifo_ctrl; + unsigned counter = 0; + + if (dig_fe >= ARRAY_SIZE(evergreen_dp_offsets)) { + DRM_ERROR("invalid dig_fe %d\n", dig_fe); + return; + } + + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + if (!(stream_ctrl & EVERGREEN_DP_VID_STREAM_CNTL_ENABLE)) { + DRM_ERROR("dig %d , should be enable\n", dig_fe); + return; + } + + stream_ctrl &=~EVERGREEN_DP_VID_STREAM_CNTL_ENABLE; + WREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe], stream_ctrl); + + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + while (counter < 32 && stream_ctrl & EVERGREEN_DP_VID_STREAM_STATUS) { + msleep(1); + counter++; + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + } + if (counter >= 32 ) + DRM_ERROR("counter exceeds %d\n", counter); + + fifo_ctrl = RREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe]); + fifo_ctrl |= EVERGREEN_DP_STEER_FIFO_RESET; + WREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe], fifo_ctrl); + +} + void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save) { u32 crtc_enabled, tmp, frame_count, blackout; int i, j; + unsigned dig_fe; if (!ASIC_IS_NODCE(rdev)) { save->vga_render_control = RREG32(VGA_RENDER_CONTROL); @@ -2651,7 +2793,17 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav break; udelay(1); } - + /*we should disable dig if it drives dp sst*/ + /*but we are in radeon_device_init and the topology is unknown*/ + /*and it is available after radeon_modeset_init*/ + /*the following method radeon_atom_encoder_dpms_dig*/ + /*does the job if we initialize it properly*/ + /*for now we do it this manually*/ + /**/ + if (ASIC_IS_DCE5(rdev) && + evergreen_is_dp_sst_stream_enabled(rdev, i ,&dig_fe)) + evergreen_blank_dp_output(rdev, dig_fe); + /*we could remove 6 lines below*/ /* XXX this is a hack to avoid strange behavior with EFI on certain systems */ WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]); diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h index aa939dfed3a3..b436badf9efa 100644 --- a/drivers/gpu/drm/radeon/evergreen_reg.h +++ b/drivers/gpu/drm/radeon/evergreen_reg.h @@ -250,8 +250,43 @@ /* HDMI blocks at 0x7030, 0x7c30, 0x10830, 0x11430, 0x12030, 0x12c30 */ #define EVERGREEN_HDMI_BASE 0x7030 +/*DIG block*/ +#define NI_DIG0_REGISTER_OFFSET (0x7000 - 0x7000) +#define NI_DIG1_REGISTER_OFFSET (0x7C00 - 0x7000) +#define NI_DIG2_REGISTER_OFFSET (0x10800 - 0x7000) +#define NI_DIG3_REGISTER_OFFSET (0x11400 - 0x7000) +#define NI_DIG4_REGISTER_OFFSET (0x12000 - 0x7000) +#define NI_DIG5_REGISTER_OFFSET (0x12C00 - 0x7000) + + +#define NI_DIG_FE_CNTL 0x7000 +# define NI_DIG_FE_CNTL_SOURCE_SELECT(x) ((x) & 0x3) +# define NI_DIG_FE_CNTL_SYMCLK_FE_ON (1<<24) + + +#define NI_DIG_BE_CNTL 0x7140 +# define NI_DIG_BE_CNTL_FE_SOURCE_SELECT(x) (((x) >> 8 ) & 0x3F) +# define NI_DIG_FE_CNTL_MODE(x) (((x) >> 16) & 0x7 ) + +#define NI_DIG_BE_EN_CNTL 0x7144 +# define NI_DIG_BE_EN_CNTL_ENABLE (1 << 0) +# define NI_DIG_BE_EN_CNTL_SYMBCLK_ON (1 << 8) +# define NI_DIG_BE_DPSST 0 /* Display Port block */ +#define EVERGREEN_DP0_REGISTER_OFFSET (0x730C - 0x730C) +#define EVERGREEN_DP1_REGISTER_OFFSET (0x7F0C - 0x730C) +#define EVERGREEN_DP2_REGISTER_OFFSET (0x10B0C - 0x730C) +#define EVERGREEN_DP3_REGISTER_OFFSET (0x1170C - 0x730C) +#define EVERGREEN_DP4_REGISTER_OFFSET (0x1230C - 0x730C) +#define EVERGREEN_DP5_REGISTER_OFFSET (0x12F0C - 0x730C) + + +#define EVERGREEN_DP_VID_STREAM_CNTL 0x730C +# define EVERGREEN_DP_VID_STREAM_CNTL_ENABLE (1 << 0) +# define EVERGREEN_DP_VID_STREAM_STATUS (1 <<16) +#define EVERGREEN_DP_STEER_FIFO 0x7310 +# define EVERGREEN_DP_STEER_FIFO_RESET (1 << 0) #define EVERGREEN_DP_SEC_CNTL 0x7280 # define EVERGREEN_DP_SEC_STREAM_ENABLE (1 << 0) # define EVERGREEN_DP_SEC_ASP_ENABLE (1 << 4) @@ -266,4 +301,15 @@ # define EVERGREEN_DP_SEC_N_BASE_MULTIPLE(x) (((x) & 0xf) << 24) # define EVERGREEN_DP_SEC_SS_EN (1 << 28) +/*DCIO_UNIPHY block*/ +#define NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1 (0x6600 -0x6600) +#define NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1 (0x6640 -0x6600) +#define NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1 (0x6680 - 0x6600) +#define NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1 (0x66C0 - 0x6600) +#define NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1 (0x6700 - 0x6600) +#define NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1 (0x6740 - 0x6600) + +#define NI_DCIO_UNIPHY0_PLL_CONTROL1 0x6618 +# define NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE (1 << 0) + #endif From e9bef455af8eb0e837e179aab8988ae2649fd8d3 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 25 Apr 2016 13:12:18 -0400 Subject: [PATCH 130/181] Revert "drm/amdgpu: disable runtime pm on PX laptops without dGPU power control" This reverts commit bedf2a65c1aa8fb29ba8527fd00c0f68ec1f55f1. See the radeon revert for an extended description. Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c | 8 ++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 +------- 2 files changed, 5 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 0020a0ea43ff..fa948dcbdd5d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -63,10 +63,6 @@ bool amdgpu_has_atpx(void) { return amdgpu_atpx_priv.atpx_detected; } -bool amdgpu_has_atpx_dgpu_power_cntl(void) { - return amdgpu_atpx_priv.atpx.functions.power_cntl; -} - /** * amdgpu_atpx_call - call an ATPX method * @@ -146,6 +142,10 @@ static void amdgpu_atpx_parse_functions(struct amdgpu_atpx_functions *f, u32 mas */ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx) { + /* make sure required functions are enabled */ + /* dGPU power control is required */ + atpx->functions.power_cntl = true; + if (atpx->functions.px_params) { union acpi_object *info; struct atpx_px_params output; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 612117478b57..2139da773da6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -62,12 +62,6 @@ static const char *amdgpu_asic_name[] = { "LAST", }; -#if defined(CONFIG_VGA_SWITCHEROO) -bool amdgpu_has_atpx_dgpu_power_cntl(void); -#else -static inline bool amdgpu_has_atpx_dgpu_power_cntl(void) { return false; } -#endif - bool amdgpu_device_is_px(struct drm_device *dev) { struct amdgpu_device *adev = dev->dev_private; @@ -1485,7 +1479,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, if (amdgpu_runtime_pm == 1) runtime = true; - if (amdgpu_device_is_px(ddev) && amdgpu_has_atpx_dgpu_power_cntl()) + if (amdgpu_device_is_px(ddev)) runtime = true; vga_switcheroo_register_client(adev->pdev, &amdgpu_switcheroo_ops, runtime); if (runtime) From c8791a13d28161a1fa1138112dfe1f986a1358cf Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 25 Apr 2016 13:14:47 -0400 Subject: [PATCH 131/181] drm/amdgpu: print a message if ATPX dGPU power control is missing It will help identify problematic boards. Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index fa948dcbdd5d..35a1248aaa77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -144,7 +144,10 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx) { /* make sure required functions are enabled */ /* dGPU power control is required */ - atpx->functions.power_cntl = true; + if (atpx->functions.power_cntl == false) { + printk("ATPX dGPU power cntl not present, forcing\n"); + atpx->functions.power_cntl = true; + } if (atpx->functions.px_params) { union acpi_object *info; From afc4542105f2b5a3bc6f0f3530d7ccbc94ca90fb Mon Sep 17 00:00:00 2001 From: Flora Cui Date: Mon, 25 Apr 2016 16:06:17 +0800 Subject: [PATCH 132/181] drm/amdgpu: disable vm interrupts with vm_fault_stop=2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit V2: disable all vm interrupts in late_init() Signed-off-by: Flora Cui Reviewed-by: Ken Wang Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c | 5 ++++- drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 05b0353d3880..a4a2e6cc61bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -910,7 +910,10 @@ static int gmc_v7_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS) + return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + else + return 0; } static int gmc_v7_0_sw_init(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 02deb3229405..7a9db2c72c89 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -870,7 +870,10 @@ static int gmc_v8_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS) + return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + else + return 0; } #define mmMC_SEQ_MISC0_FIJI 0xA71 From 5fdfc48bb0da2aa8a912024a6ecca06486eb9141 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Tue, 29 Mar 2016 19:23:32 +0800 Subject: [PATCH 133/181] thermal: hisilicon: increase temperature resolution When calculate temperature, old code firstly do division and then convert to "millicelsius" unit. This will lose resolution and only can read back temperature with "Celsius" unit. So firstly scale step value to "millicelsius" and then do division, so finally we can increase resolution for temperature value. Also refine the calculation from temperature value to step value. Signed-off-by: Leo Yan Signed-off-by: Eduardo Valentin --- drivers/thermal/hisi_thermal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index 36d07295f8e3..5e820b541506 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -68,12 +68,12 @@ static inline int _step_to_temp(int step) * Every step equals (1 * 200) / 255 celsius, and finally * need convert to millicelsius. */ - return (HISI_TEMP_BASE + (step * 200 / 255)) * 1000; + return (HISI_TEMP_BASE * 1000 + (step * 200000 / 255)); } static inline long _temp_to_step(long temp) { - return ((temp / 1000 - HISI_TEMP_BASE) * 255 / 200); + return ((temp - HISI_TEMP_BASE * 1000) * 255) / 200000; } static long hisi_thermal_get_sensor_temp(struct hisi_thermal_data *data, From 15333e3af1de37b1b214b28c85fe9a7b257fb92c Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Tue, 29 Mar 2016 19:24:15 +0800 Subject: [PATCH 134/181] thermal: use %d to print S32 parameters Power allocator's parameters are S32 type, so use %d to print them. Acked-by: Javi Merino Signed-off-by: Leo Yan Signed-off-by: Eduardo Valentin --- drivers/thermal/thermal_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index f1db49625555..5133cd1e10b7 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -959,7 +959,7 @@ static DEVICE_ATTR(sustainable_power, S_IWUSR | S_IRUGO, sustainable_power_show, struct thermal_zone_device *tz = to_thermal_zone(dev); \ \ if (tz->tzp) \ - return sprintf(buf, "%u\n", tz->tzp->name); \ + return sprintf(buf, "%d\n", tz->tzp->name); \ else \ return -EIO; \ } \ From 1bdb8970392a68489b469c3a330a1adb5ef61beb Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 27 Apr 2016 14:22:32 -0600 Subject: [PATCH 135/181] x86/apic: Handle zero vector gracefully in clear_vector_irq() If x86_vector_alloc_irq() fails x86_vector_free_irqs() is invoked to cleanup the already allocated vectors. This subsequently calls clear_vector_irq(). The failed irq has no vector assigned, which triggers the BUG_ON(!vector) in clear_vector_irq(). We cannot suppress the call to x86_vector_free_irqs() for the failed interrupt, because the other data related to this irq must be cleaned up as well. So calling clear_vector_irq() with vector == 0 is legitimate. Remove the BUG_ON and return if vector is zero, [ tglx: Massaged changelog ] Fixes: b5dc8e6c21e7 "x86/irq: Use hierarchical irqdomain to manage CPU interrupt vectors" Signed-off-by: Keith Busch Cc: stable@vger.kernel.org Signed-off-by: Thomas Gleixner --- arch/x86/kernel/apic/vector.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index ad59d70bcb1a..ef495511f019 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -256,7 +256,8 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) struct irq_desc *desc; int cpu, vector; - BUG_ON(!data->cfg.vector); + if (!data->cfg.vector) + return; vector = data->cfg.vector; for_each_cpu_and(cpu, data->domain, cpu_online_mask) From 811c6688774613a78bfa020f64b570b73f6974c8 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 15 Apr 2016 16:22:16 +0200 Subject: [PATCH 136/181] rbd: fix rbd map vs notify races A while ago, commit 9875201e1049 ("rbd: fix use-after free of rbd_dev->disk") fixed rbd unmap vs notify race by introducing an exported wrapper for flushing notifies and sticking it into do_rbd_remove(). A similar problem exists on the rbd map path, though: the watch is registered in rbd_dev_image_probe(), while the disk is set up quite a few steps later, in rbd_dev_device_setup(). Nothing prevents a notify from coming in and crashing on a NULL rbd_dev->disk: BUG: unable to handle kernel NULL pointer dereference at 0000000000000050 Call Trace: [] rbd_watch_cb+0x34/0x180 [rbd] [] do_event_work+0x40/0xb0 [libceph] [] process_one_work+0x17b/0x470 [] worker_thread+0x11b/0x400 [] ? rescuer_thread+0x400/0x400 [] kthread+0xcf/0xe0 [] ? finish_task_switch+0x53/0x170 [] ? kthread_create_on_node+0x140/0x140 [] ret_from_fork+0x58/0x90 [] ? kthread_create_on_node+0x140/0x140 RIP [] rbd_dev_refresh+0xfa/0x180 [rbd] If an error occurs during rbd map, we have to error out, potentially tearing down a watch. Just like on rbd unmap, notifies have to be flushed, otherwise rbd_watch_cb() may end up trying to read in the image header after rbd_dev_image_release() has run: Assertion failure in rbd_dev_header_info() at line 4722: rbd_assert(rbd_image_format_valid(rbd_dev->image_format)); Call Trace: [] ? rbd_parent_request_create+0x150/0x150 [] rbd_dev_refresh+0x59/0x390 [] rbd_watch_cb+0x69/0x290 [] do_event_work+0x10f/0x1c0 [] process_one_work+0x689/0x1a80 [] ? process_one_work+0x5e7/0x1a80 [] ? finish_task_switch+0x225/0x640 [] ? pwq_dec_nr_in_flight+0x2b0/0x2b0 [] worker_thread+0xd9/0x1320 [] ? process_one_work+0x1a80/0x1a80 [] kthread+0x21d/0x2e0 [] ? kthread_stop+0x550/0x550 [] ret_from_fork+0x22/0x40 [] ? kthread_stop+0x550/0x550 RIP [] rbd_dev_header_info+0xa19/0x1e30 To fix this, a) check if RBD_DEV_FLAG_EXISTS is set before calling revalidate_disk(), b) move ceph_osdc_flush_notifies() call into rbd_dev_header_unwatch_sync() to cover rbd map error paths and c) turn header read-in into a critical section. The latter also happens to take care of rbd map foo@bar vs rbd snap rm foo@bar race. Fixes: http://tracker.ceph.com/issues/15490 Signed-off-by: Ilya Dryomov Reviewed-by: Josh Durgin --- drivers/block/rbd.c | 43 +++++++++++++++++++------------------------ 1 file changed, 19 insertions(+), 24 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 94a1843b0426..25d22da47f6e 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -538,7 +538,6 @@ static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id, u8 *order, u64 *snap_size); static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, u64 *snap_features); -static u64 rbd_snap_id_by_name(struct rbd_device *rbd_dev, const char *name); static int rbd_open(struct block_device *bdev, fmode_t mode) { @@ -3127,9 +3126,6 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data) struct rbd_device *rbd_dev = (struct rbd_device *)data; int ret; - if (!rbd_dev) - return; - dout("%s: \"%s\" notify_id %llu opcode %u\n", __func__, rbd_dev->header_name, (unsigned long long)notify_id, (unsigned int)opcode); @@ -3263,6 +3259,9 @@ static void rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev) ceph_osdc_cancel_event(rbd_dev->watch_event); rbd_dev->watch_event = NULL; + + dout("%s flushing notifies\n", __func__); + ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc); } /* @@ -3642,21 +3641,14 @@ static void rbd_exists_validate(struct rbd_device *rbd_dev) static void rbd_dev_update_size(struct rbd_device *rbd_dev) { sector_t size; - bool removing; /* - * Don't hold the lock while doing disk operations, - * or lock ordering will conflict with the bdev mutex via: - * rbd_add() -> blkdev_get() -> rbd_open() + * If EXISTS is not set, rbd_dev->disk may be NULL, so don't + * try to update its size. If REMOVING is set, updating size + * is just useless work since the device can't be opened. */ - spin_lock_irq(&rbd_dev->lock); - removing = test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags); - spin_unlock_irq(&rbd_dev->lock); - /* - * If the device is being removed, rbd_dev->disk has - * been destroyed, so don't try to update its size - */ - if (!removing) { + if (test_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags) && + !test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags)) { size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE; dout("setting size to %llu sectors", (unsigned long long)size); set_capacity(rbd_dev->disk, size); @@ -5187,6 +5179,10 @@ out_err: return ret; } +/* + * rbd_dev->header_rwsem must be locked for write and will be unlocked + * upon return. + */ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) { int ret; @@ -5195,7 +5191,7 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) ret = rbd_dev_id_get(rbd_dev); if (ret) - return ret; + goto err_out_unlock; BUILD_BUG_ON(DEV_NAME_LEN < sizeof (RBD_DRV_NAME) + MAX_INT_FORMAT_WIDTH); @@ -5236,8 +5232,9 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) /* Everything's ready. Announce the disk to the world. */ set_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags); - add_disk(rbd_dev->disk); + up_write(&rbd_dev->header_rwsem); + add_disk(rbd_dev->disk); pr_info("%s: added with size 0x%llx\n", rbd_dev->disk->disk_name, (unsigned long long) rbd_dev->mapping.size); @@ -5252,6 +5249,8 @@ err_out_blkdev: unregister_blkdev(rbd_dev->major, rbd_dev->name); err_out_id: rbd_dev_id_put(rbd_dev); +err_out_unlock: + up_write(&rbd_dev->header_rwsem); return ret; } @@ -5442,6 +5441,7 @@ static ssize_t do_rbd_add(struct bus_type *bus, spec = NULL; /* rbd_dev now owns this */ rbd_opts = NULL; /* rbd_dev now owns this */ + down_write(&rbd_dev->header_rwsem); rc = rbd_dev_image_probe(rbd_dev, 0); if (rc < 0) goto err_out_rbd_dev; @@ -5471,6 +5471,7 @@ out: return rc; err_out_rbd_dev: + up_write(&rbd_dev->header_rwsem); rbd_dev_destroy(rbd_dev); err_out_client: rbd_put_client(rbdc); @@ -5577,12 +5578,6 @@ static ssize_t do_rbd_remove(struct bus_type *bus, return ret; rbd_dev_header_unwatch_sync(rbd_dev); - /* - * flush remaining watch callbacks - these must be complete - * before the osd_client is shutdown - */ - dout("%s: flushing notifies", __func__); - ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc); /* * Don't free anything from rbd_dev->disk until after all From d3767f0faeda5abdf205f947ae912d48dc70fa06 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 13 Apr 2016 14:15:50 +0200 Subject: [PATCH 137/181] rbd: report unsupported features to syslog ... instead of just returning an error. Signed-off-by: Ilya Dryomov Reviewed-by: Josh Durgin --- drivers/block/rbd.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 25d22da47f6e..0ede6d7e2568 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4183,7 +4183,7 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, __le64 features; __le64 incompat; } __attribute__ ((packed)) features_buf = { 0 }; - u64 incompat; + u64 unsup; int ret; ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name, @@ -4196,9 +4196,12 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, if (ret < sizeof (features_buf)) return -ERANGE; - incompat = le64_to_cpu(features_buf.incompat); - if (incompat & ~RBD_FEATURES_SUPPORTED) + unsup = le64_to_cpu(features_buf.incompat) & ~RBD_FEATURES_SUPPORTED; + if (unsup) { + rbd_warn(rbd_dev, "image uses unsupported features: 0x%llx", + unsup); return -ENXIO; + } *snap_features = le64_to_cpu(features_buf.features); From 0a25556f84d5f79e68e9502bb1f32a43377ab2bf Mon Sep 17 00:00:00 2001 From: Adam Borowski Date: Wed, 27 Apr 2016 11:35:31 +0200 Subject: [PATCH 138/181] perf/x86/amd: Set the size of event map array to PERF_COUNT_HW_MAX The entry for PERF_COUNT_HW_REF_CPU_CYCLES is not used on AMD, but is referenced by filter_events() which expects undefined events to have a value of 0. Found via KASAN: UBSAN: Undefined behaviour in arch/x86/events/amd/core.c:132:30 index 9 is out of range for type 'u64 [9]' UBSAN: Undefined behaviour in arch/x86/events/amd/core.c:132:9 load of address ffffffff81c021c8 with insufficient space for an object of type 'const u64' Signed-off-by: Adam Borowski Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Jiri Olsa Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/1461749731-30979-1-git-send-email-kilobyte@angband.pl Signed-off-by: Ingo Molnar --- arch/x86/events/amd/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 86a9bec18dab..bd3e8421b57c 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -115,7 +115,7 @@ static __initconst const u64 amd_hw_cache_event_ids /* * AMD Performance Monitor K7 and later. */ -static const u64 amd_perfmon_event_map[] = +static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, From 79c9ce57eb2d5f1497546a3946b4ae21b6fdc438 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 26 Apr 2016 11:36:53 +0200 Subject: [PATCH 139/181] perf/core: Fix perf_event_open() vs. execve() race Jann reported that the ptrace_may_access() check in find_lively_task_by_vpid() is racy against exec(). Specifically: perf_event_open() execve() ptrace_may_access() commit_creds() ... if (get_dumpable() != SUID_DUMP_USER) perf_event_exit_task(); perf_install_in_context() would result in installing a counter across the creds boundary. Fix this by wrapping lots of perf_event_open() in cred_guard_mutex. This should be fine as perf_event_exit_task() is already called with cred_guard_mutex held, so all perf locks already nest inside it. Reported-by: Jann Horn Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Signed-off-by: Ingo Molnar --- kernel/events/core.c | 52 ++++++++++++++++++++++++++++++-------------- 1 file changed, 36 insertions(+), 16 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 2c78b6f47339..4e2ebf6f2f1f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1106,6 +1106,7 @@ static void put_ctx(struct perf_event_context *ctx) * function. * * Lock order: + * cred_guard_mutex * task_struct::perf_event_mutex * perf_event_context::mutex * perf_event::child_mutex; @@ -3421,7 +3422,6 @@ static struct task_struct * find_lively_task_by_vpid(pid_t vpid) { struct task_struct *task; - int err; rcu_read_lock(); if (!vpid) @@ -3435,16 +3435,7 @@ find_lively_task_by_vpid(pid_t vpid) if (!task) return ERR_PTR(-ESRCH); - /* Reuse ptrace permission checks for now. */ - err = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) - goto errout; - return task; -errout: - put_task_struct(task); - return ERR_PTR(err); - } /* @@ -8414,6 +8405,24 @@ SYSCALL_DEFINE5(perf_event_open, get_online_cpus(); + if (task) { + err = mutex_lock_interruptible(&task->signal->cred_guard_mutex); + if (err) + goto err_cpus; + + /* + * Reuse ptrace permission checks for now. + * + * We must hold cred_guard_mutex across this and any potential + * perf_install_in_context() call for this new event to + * serialize against exec() altering our credentials (and the + * perf_event_exit_task() that could imply). + */ + err = -EACCES; + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) + goto err_cred; + } + if (flags & PERF_FLAG_PID_CGROUP) cgroup_fd = pid; @@ -8421,7 +8430,7 @@ SYSCALL_DEFINE5(perf_event_open, NULL, NULL, cgroup_fd); if (IS_ERR(event)) { err = PTR_ERR(event); - goto err_cpus; + goto err_cred; } if (is_sampling_event(event)) { @@ -8480,11 +8489,6 @@ SYSCALL_DEFINE5(perf_event_open, goto err_context; } - if (task) { - put_task_struct(task); - task = NULL; - } - /* * Look up the group leader (we will attach this event to it): */ @@ -8582,6 +8586,11 @@ SYSCALL_DEFINE5(perf_event_open, WARN_ON_ONCE(ctx->parent_ctx); + /* + * This is the point on no return; we cannot fail hereafter. This is + * where we start modifying current state. + */ + if (move_group) { /* * See perf_event_ctx_lock() for comments on the details @@ -8653,6 +8662,11 @@ SYSCALL_DEFINE5(perf_event_open, mutex_unlock(&gctx->mutex); mutex_unlock(&ctx->mutex); + if (task) { + mutex_unlock(&task->signal->cred_guard_mutex); + put_task_struct(task); + } + put_online_cpus(); mutex_lock(¤t->perf_event_mutex); @@ -8685,6 +8699,9 @@ err_alloc: */ if (!event_file) free_event(event); +err_cred: + if (task) + mutex_unlock(&task->signal->cred_guard_mutex); err_cpus: put_online_cpus(); err_task: @@ -8969,6 +8986,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) /* * When a child task exits, feed back event values to parent events. + * + * Can be called with cred_guard_mutex held when called from + * install_exec_creds(). */ void perf_event_exit_task(struct task_struct *child) { From 1c5ac21a0e9bab7fc45d0ba9e11623e9ad99d02e Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Tue, 29 Mar 2016 17:43:10 +0300 Subject: [PATCH 140/181] perf/x86/intel/pt: Don't die on VMXON Some versions of Intel PT do not support tracing across VMXON, more specifically, VMXON will clear TraceEn control bit and any attempt to set it before VMXOFF will throw a #GP, which in the current state of things will crash the kernel. Namely: $ perf record -e intel_pt// kvm -nographic on such a machine will kill it. To avoid this, notify the intel_pt driver before VMXON and after VMXOFF so that it knows when not to enable itself. Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Gleb Natapov Cc: Jiri Olsa Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: hpa@zytor.com Link: http://lkml.kernel.org/r/87oa9dwrfk.fsf@ashishki-desk.ger.corp.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/pt.c | 75 ++++++++++++++++++++++++++----- arch/x86/events/intel/pt.h | 3 ++ arch/x86/include/asm/perf_event.h | 4 ++ arch/x86/kvm/vmx.c | 4 ++ 4 files changed, 75 insertions(+), 11 deletions(-) diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 6af7cf71d6b2..09a77dbc73c9 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -136,9 +136,21 @@ static int __init pt_pmu_hw_init(void) struct dev_ext_attribute *de_attrs; struct attribute **attrs; size_t size; + u64 reg; int ret; long i; + if (boot_cpu_has(X86_FEATURE_VMX)) { + /* + * Intel SDM, 36.5 "Tracing post-VMXON" says that + * "IA32_VMX_MISC[bit 14]" being 1 means PT can trace + * post-VMXON. + */ + rdmsrl(MSR_IA32_VMX_MISC, reg); + if (reg & BIT(14)) + pt_pmu.vmx = true; + } + attrs = NULL; for (i = 0; i < PT_CPUID_LEAVES; i++) { @@ -269,20 +281,23 @@ static void pt_config(struct perf_event *event) reg |= (event->attr.config & PT_CONFIG_MASK); + event->hw.config = reg; wrmsrl(MSR_IA32_RTIT_CTL, reg); } -static void pt_config_start(bool start) +static void pt_config_stop(struct perf_event *event) { - u64 ctl; + u64 ctl = READ_ONCE(event->hw.config); - rdmsrl(MSR_IA32_RTIT_CTL, ctl); - if (start) - ctl |= RTIT_CTL_TRACEEN; - else - ctl &= ~RTIT_CTL_TRACEEN; + /* may be already stopped by a PMI */ + if (!(ctl & RTIT_CTL_TRACEEN)) + return; + + ctl &= ~RTIT_CTL_TRACEEN; wrmsrl(MSR_IA32_RTIT_CTL, ctl); + WRITE_ONCE(event->hw.config, ctl); + /* * A wrmsr that disables trace generation serializes other PT * registers and causes all data packets to be written to memory, @@ -291,8 +306,7 @@ static void pt_config_start(bool start) * The below WMB, separating data store and aux_head store matches * the consumer's RMB that separates aux_head load and data load. */ - if (!start) - wmb(); + wmb(); } static void pt_config_buffer(void *buf, unsigned int topa_idx, @@ -942,11 +956,17 @@ void intel_pt_interrupt(void) if (!ACCESS_ONCE(pt->handle_nmi)) return; - pt_config_start(false); + /* + * If VMX is on and PT does not support it, don't touch anything. + */ + if (READ_ONCE(pt->vmx_on)) + return; if (!event) return; + pt_config_stop(event); + buf = perf_get_aux(&pt->handle); if (!buf) return; @@ -983,6 +1003,35 @@ void intel_pt_interrupt(void) } } +void intel_pt_handle_vmx(int on) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct perf_event *event; + unsigned long flags; + + /* PT plays nice with VMX, do nothing */ + if (pt_pmu.vmx) + return; + + /* + * VMXON will clear RTIT_CTL.TraceEn; we need to make + * sure to not try to set it while VMX is on. Disable + * interrupts to avoid racing with pmu callbacks; + * concurrent PMI should be handled fine. + */ + local_irq_save(flags); + WRITE_ONCE(pt->vmx_on, on); + + if (on) { + /* prevent pt_config_stop() from writing RTIT_CTL */ + event = pt->handle.event; + if (event) + event->hw.config = 0; + } + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(intel_pt_handle_vmx); + /* * PMU callbacks */ @@ -992,6 +1041,9 @@ static void pt_event_start(struct perf_event *event, int mode) struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); + if (READ_ONCE(pt->vmx_on)) + return; + if (!buf || pt_buffer_is_full(buf, pt)) { event->hw.state = PERF_HES_STOPPED; return; @@ -1014,7 +1066,8 @@ static void pt_event_stop(struct perf_event *event, int mode) * see comment in intel_pt_interrupt(). */ ACCESS_ONCE(pt->handle_nmi) = 0; - pt_config_start(false); + + pt_config_stop(event); if (event->hw.state == PERF_HES_STOPPED) return; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 336878a5d205..3abb5f5cccc8 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -65,6 +65,7 @@ enum pt_capabilities { struct pt_pmu { struct pmu pmu; u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; + bool vmx; }; /** @@ -107,10 +108,12 @@ struct pt_buffer { * struct pt - per-cpu pt context * @handle: perf output handle * @handle_nmi: do handle PT PMI on this cpu, there's an active event + * @vmx_on: 1 if VMX is ON on this cpu */ struct pt { struct perf_output_handle handle; int handle_nmi; + int vmx_on; }; #endif /* __INTEL_PT_H__ */ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 5a2ed3ed2f26..f353061bba1d 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -285,6 +285,10 @@ static inline void perf_events_lapic_init(void) { } static inline void perf_check_microcode(void) { } #endif +#ifdef CONFIG_CPU_SUP_INTEL + extern void intel_pt_handle_vmx(int on); +#endif + #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) extern void amd_pmu_enable_virt(void); extern void amd_pmu_disable_virt(void); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ee1c8a93871c..133679d520af 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3103,6 +3103,8 @@ static __init int vmx_disabled_by_bios(void) static void kvm_cpu_vmxon(u64 addr) { + intel_pt_handle_vmx(1); + asm volatile (ASM_VMX_VMXON_RAX : : "a"(&addr), "m"(addr) : "memory", "cc"); @@ -3172,6 +3174,8 @@ static void vmclear_local_loaded_vmcss(void) static void kvm_cpu_vmxoff(void) { asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc"); + + intel_pt_handle_vmx(0); } static void hardware_disable(void) From cf3beb7c90a8efa16a06b26634cddddc92bb819c Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 21 Apr 2016 02:30:10 -0700 Subject: [PATCH 141/181] perf/x86/intel: Fix incorrect lbr_sel_mask value This patch fixes a bug which was introduced by: b16a5b52eb90 ("perf/x86: Add option to disable reading branch flags/cycles") In this patch, lbr_sel_mask is used to mask the lbr_select. But LBR_SEL_MASK doesn't include the bit for LBR_CALL_STACK. So LBR call stack will never be set in lbr_select. This patch corrects the LBR_SEL_MASK by including all valid bits in LBR_SELECT. Also, the LBR_CALL_STACK bit is different as other bit in LBR_SELECT. It does not operate in suppress mode, so it needs to be specially handled in intel_pmu_setup_hw_lbr_filter. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: http://lkml.kernel.org/r/1461231010-4399-1-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/lbr.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 6c3b7c1780c9..1ca5d1e7d4f2 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -63,7 +63,7 @@ static enum { #define LBR_PLM (LBR_KERNEL | LBR_USER) -#define LBR_SEL_MASK 0x1ff /* valid bits in LBR_SELECT */ +#define LBR_SEL_MASK 0x3ff /* valid bits in LBR_SELECT */ #define LBR_NOT_SUPP -1 /* LBR filter not supported */ #define LBR_IGN 0 /* ignored */ @@ -610,8 +610,10 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate * in suppress mode. So LBR_SELECT should be set to * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK) + * But the 10th bit LBR_CALL_STACK does not operate + * in suppress mode. */ - reg->config = mask ^ x86_pmu.lbr_sel_mask; + reg->config = mask ^ (x86_pmu.lbr_sel_mask & ~LBR_CALL_STACK); if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && From 2963070a0f8184fe40be11927344e3fcc7e18e7c Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Tue, 26 Apr 2016 23:37:26 +0800 Subject: [PATCH 142/181] mmc: sunxi: Disable eMMC HS-DDR (MMC_CAP_1_8V_DDR) for Allwinner A80 eMMC HS-DDR no longer works on the A80, despite it working when support for this developed. Disable it for now. Signed-off-by: Chen-Yu Tsai Signed-off-by: Ulf Hansson --- drivers/mmc/host/sunxi-mmc.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index 8372a413848c..7fc8b7aa83f0 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1129,6 +1129,11 @@ static int sunxi_mmc_probe(struct platform_device *pdev) MMC_CAP_1_8V_DDR | MMC_CAP_ERASE | MMC_CAP_SDIO_IRQ; + /* TODO MMC DDR is not working on A80 */ + if (of_device_is_compatible(pdev->dev.of_node, + "allwinner,sun9i-a80-mmc")) + mmc->caps &= ~MMC_CAP_1_8V_DDR; + ret = mmc_of_parse(mmc); if (ret) goto error_free_dma; From 986ef95ecdd3eb6fa29433e68faa94c7624083be Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 31 Mar 2016 19:03:25 +0300 Subject: [PATCH 143/181] IB/mlx5: Expose correct max_sge_rd limit mlx5 devices (Connect-IB, ConnectX-4, ConnectX-4-LX) has a limitation where rdma read work queue entries cannot exceed 512 bytes. A rdma_read wqe needs to fit in 512 bytes: - wqe control segment (16 bytes) - rdma segment (16 bytes) - scatter elements (16 bytes each) So max_sge_rd should be: (512 - 16 - 16) / 16 = 30. Cc: linux-stable@vger.kernel.org Reported-by: Christoph Hellwig Tested-by: Christoph Hellwig Signed-off-by: Sagi Grimberg Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx5/main.c | 2 +- include/linux/mlx5/device.h | 11 +++++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5acf346e048e..049754f6e638 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -530,7 +530,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, sizeof(struct mlx5_wqe_ctrl_seg)) / sizeof(struct mlx5_wqe_data_seg); props->max_sge = min(max_rq_sg, max_sq_sg); - props->max_sge_rd = props->max_sge; + props->max_sge_rd = MLX5_MAX_SGE_RD; props->max_cq = 1 << MLX5_CAP_GEN(mdev, log_max_cq); props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_cq_sz)) - 1; props->max_mr = 1 << MLX5_CAP_GEN(mdev, log_max_mkey); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8156e3c9239c..b3575f392492 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -392,6 +392,17 @@ enum { MLX5_CAP_OFF_CMDIF_CSUM = 46, }; +enum { + /* + * Max wqe size for rdma read is 512 bytes, so this + * limits our max_sge_rd as the wqe needs to fit: + * - ctrl segment (16 bytes) + * - rdma segment (16 bytes) + * - scatter elements (16 bytes each) + */ + MLX5_MAX_SGE_RD = (512 - 16 - 16) / 16 +}; + struct mlx5_inbox_hdr { __be16 opcode; u8 rsvd[4]; From e7d2c25d94bf4bb6f73d185e5514414a15a56f46 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Sun, 3 Apr 2016 15:03:12 +0300 Subject: [PATCH 144/181] MAINTAINERS: Update iser/isert maintainer contact info Signed-off-by: Sagi Grimberg Acked-by: Nicholas Bellinger Signed-off-by: Doug Ledford --- MAINTAINERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 1c32f8a3d6c4..03413249f89b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6027,7 +6027,7 @@ F: include/scsi/*iscsi* ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR M: Or Gerlitz -M: Sagi Grimberg +M: Sagi Grimberg M: Roi Dayan L: linux-rdma@vger.kernel.org S: Supported @@ -6037,7 +6037,7 @@ Q: http://patchwork.kernel.org/project/linux-rdma/list/ F: drivers/infiniband/ulp/iser/ ISCSI EXTENSIONS FOR RDMA (ISER) TARGET -M: Sagi Grimberg +M: Sagi Grimberg T: git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master L: linux-rdma@vger.kernel.org L: target-devel@vger.kernel.org From f19bd643dbded8672bfeffe9e51322464e4a9239 Mon Sep 17 00:00:00 2001 From: Mitko Haralanov Date: Tue, 12 Apr 2016 10:45:57 -0700 Subject: [PATCH 145/181] IB/hfi1: Prevent NULL pointer deferences in caching code There is a potential kernel crash when the MMU notifier calls the invalidation routines in the hfi1 pinned page caching code for sdma. The invalidation routine could call the remove callback for the node, which in turn ends up dereferencing the current task_struct to get a pointer to the mm_struct. However, the mm_struct pointer could be NULL resulting in the following backtrace: BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8 IP: [] sdma_rb_remove+0xaa/0x100 [hfi1] 15 task: ffff88085e66e080 ti: ffff88085c244000 task.ti: ffff88085c244000 RIP: 0010:[] [] sdma_rb_remove+0xaa/0x100 [hfi1] RSP: 0000:ffff88085c245878 EFLAGS: 00010002 RAX: 0000000000000000 RBX: ffff88105b9bbd40 RCX: ffffea003931a830 RDX: 0000000000000004 RSI: ffff88105754a9c0 RDI: ffff88105754a9c0 RBP: ffff88085c245890 R08: ffff88105b9bbd70 R09: 00000000fffffffb R10: ffff88105b9bbd58 R11: 0000000000000013 R12: ffff88105754a9c0 R13: 0000000000000001 R14: 0000000000000001 R15: ffff88105b9bbd40 FS: 0000000000000000(0000) GS:ffff88107ef40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000a8 CR3: 0000000001a0b000 CR4: 00000000001407e0 Stack: ffff88105b9bbd40 ffff88080ec481a8 ffff88080ec481b8 ffff88085c2458c0 ffffffffa03fa00e ffff88080ec48190 ffff88080ed9cd00 0000000001024000 0000000000000000 ffff88085c245920 ffffffffa03fa0e7 0000000000000282 Call Trace: [] __mmu_rb_remove.isra.5+0x5e/0x70 [hfi1] [] mmu_notifier_mem_invalidate+0xc7/0xf0 [hfi1] [] mmu_notifier_page+0x13/0x20 [hfi1] [] __mmu_notifier_invalidate_page+0x50/0x70 [] try_to_unmap_one+0x20b/0x470 [] try_to_unmap_anon+0xa7/0x120 [] try_to_unmap+0x4d/0x60 [] shrink_page_list+0x2eb/0x9d0 [] shrink_inactive_list+0x243/0x490 [] shrink_lruvec+0x4c1/0x640 [] shrink_zone+0x31/0x100 [] kswapd_shrink_zone.constprop.62+0xef/0x1c0 [] kswapd+0x403/0x7e0 [] ? shrink_all_memory+0xf0/0xf0 [] kthread+0xc0/0xd0 [] ? insert_kthread_work+0x40/0x40 [] ret_from_fork+0x7c/0xb0 [] ? insert_kthread_work+0x40/0x40 To correct this, the mm_struct passed to us by the MMU notifier is used (which is what should have been done to begin with). This avoids the broken derefences and ensures that the correct mm_struct is used. Reviewed-by: Dennis Dalessandro Reviewed-by: Dean Luick Signed-off-by: Mitko Haralanov Signed-off-by: Doug Ledford --- drivers/staging/rdma/hfi1/mmu_rb.c | 24 ++++++++++++++---------- drivers/staging/rdma/hfi1/mmu_rb.h | 3 ++- drivers/staging/rdma/hfi1/user_exp_rcv.c | 9 +++++---- drivers/staging/rdma/hfi1/user_sdma.c | 24 ++++++++++++++++-------- 4 files changed, 37 insertions(+), 23 deletions(-) diff --git a/drivers/staging/rdma/hfi1/mmu_rb.c b/drivers/staging/rdma/hfi1/mmu_rb.c index c7ad0164ea9a..eac4d041d351 100644 --- a/drivers/staging/rdma/hfi1/mmu_rb.c +++ b/drivers/staging/rdma/hfi1/mmu_rb.c @@ -71,6 +71,7 @@ static inline void mmu_notifier_range_start(struct mmu_notifier *, struct mm_struct *, unsigned long, unsigned long); static void mmu_notifier_mem_invalidate(struct mmu_notifier *, + struct mm_struct *, unsigned long, unsigned long); static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *, unsigned long, unsigned long); @@ -137,7 +138,7 @@ void hfi1_mmu_rb_unregister(struct rb_root *root) rbnode = rb_entry(node, struct mmu_rb_node, node); rb_erase(node, root); if (handler->ops->remove) - handler->ops->remove(root, rbnode, false); + handler->ops->remove(root, rbnode, NULL); } } @@ -201,14 +202,14 @@ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, } static void __mmu_rb_remove(struct mmu_rb_handler *handler, - struct mmu_rb_node *node, bool arg) + struct mmu_rb_node *node, struct mm_struct *mm) { /* Validity of handler and node pointers has been checked by caller. */ hfi1_cdbg(MMU, "Removing node addr 0x%llx, len %u", node->addr, node->len); __mmu_int_rb_remove(node, handler->root); if (handler->ops->remove) - handler->ops->remove(handler->root, node, arg); + handler->ops->remove(handler->root, node, mm); } struct mmu_rb_node *hfi1_mmu_rb_search(struct rb_root *root, unsigned long addr, @@ -237,7 +238,7 @@ void hfi1_mmu_rb_remove(struct rb_root *root, struct mmu_rb_node *node) return; spin_lock_irqsave(&handler->lock, flags); - __mmu_rb_remove(handler, node, false); + __mmu_rb_remove(handler, node, NULL); spin_unlock_irqrestore(&handler->lock, flags); } @@ -260,7 +261,7 @@ unlock: static inline void mmu_notifier_page(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long addr) { - mmu_notifier_mem_invalidate(mn, addr, addr + PAGE_SIZE); + mmu_notifier_mem_invalidate(mn, mm, addr, addr + PAGE_SIZE); } static inline void mmu_notifier_range_start(struct mmu_notifier *mn, @@ -268,25 +269,28 @@ static inline void mmu_notifier_range_start(struct mmu_notifier *mn, unsigned long start, unsigned long end) { - mmu_notifier_mem_invalidate(mn, start, end); + mmu_notifier_mem_invalidate(mn, mm, start, end); } static void mmu_notifier_mem_invalidate(struct mmu_notifier *mn, + struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_rb_handler *handler = container_of(mn, struct mmu_rb_handler, mn); struct rb_root *root = handler->root; - struct mmu_rb_node *node; + struct mmu_rb_node *node, *ptr = NULL; unsigned long flags; spin_lock_irqsave(&handler->lock, flags); - for (node = __mmu_int_rb_iter_first(root, start, end - 1); node; - node = __mmu_int_rb_iter_next(node, start, end - 1)) { + for (node = __mmu_int_rb_iter_first(root, start, end - 1); + node; node = ptr) { + /* Guard against node removal. */ + ptr = __mmu_int_rb_iter_next(node, start, end - 1); hfi1_cdbg(MMU, "Invalidating node addr 0x%llx, len %u", node->addr, node->len); if (handler->ops->invalidate(root, node)) - __mmu_rb_remove(handler, node, true); + __mmu_rb_remove(handler, node, mm); } spin_unlock_irqrestore(&handler->lock, flags); } diff --git a/drivers/staging/rdma/hfi1/mmu_rb.h b/drivers/staging/rdma/hfi1/mmu_rb.h index f8523fdb8a18..19a306e83c7d 100644 --- a/drivers/staging/rdma/hfi1/mmu_rb.h +++ b/drivers/staging/rdma/hfi1/mmu_rb.h @@ -59,7 +59,8 @@ struct mmu_rb_node { struct mmu_rb_ops { bool (*filter)(struct mmu_rb_node *, unsigned long, unsigned long); int (*insert)(struct rb_root *, struct mmu_rb_node *); - void (*remove)(struct rb_root *, struct mmu_rb_node *, bool); + void (*remove)(struct rb_root *, struct mmu_rb_node *, + struct mm_struct *); int (*invalidate)(struct rb_root *, struct mmu_rb_node *); }; diff --git a/drivers/staging/rdma/hfi1/user_exp_rcv.c b/drivers/staging/rdma/hfi1/user_exp_rcv.c index 0861e095df8d..5b72849bbd71 100644 --- a/drivers/staging/rdma/hfi1/user_exp_rcv.c +++ b/drivers/staging/rdma/hfi1/user_exp_rcv.c @@ -87,7 +87,8 @@ static u32 find_phys_blocks(struct page **, unsigned, struct tid_pageset *); static int set_rcvarray_entry(struct file *, unsigned long, u32, struct tid_group *, struct page **, unsigned); static int mmu_rb_insert(struct rb_root *, struct mmu_rb_node *); -static void mmu_rb_remove(struct rb_root *, struct mmu_rb_node *, bool); +static void mmu_rb_remove(struct rb_root *, struct mmu_rb_node *, + struct mm_struct *); static int mmu_rb_invalidate(struct rb_root *, struct mmu_rb_node *); static int program_rcvarray(struct file *, unsigned long, struct tid_group *, struct tid_pageset *, unsigned, u16, struct page **, @@ -899,7 +900,7 @@ static int unprogram_rcvarray(struct file *fp, u32 tidinfo, if (!node || node->rcventry != (uctxt->expected_base + rcventry)) return -EBADF; if (HFI1_CAP_IS_USET(TID_UNMAP)) - mmu_rb_remove(&fd->tid_rb_root, &node->mmu, false); + mmu_rb_remove(&fd->tid_rb_root, &node->mmu, NULL); else hfi1_mmu_rb_remove(&fd->tid_rb_root, &node->mmu); @@ -965,7 +966,7 @@ static void unlock_exp_tids(struct hfi1_ctxtdata *uctxt, continue; if (HFI1_CAP_IS_USET(TID_UNMAP)) mmu_rb_remove(&fd->tid_rb_root, - &node->mmu, false); + &node->mmu, NULL); else hfi1_mmu_rb_remove(&fd->tid_rb_root, &node->mmu); @@ -1032,7 +1033,7 @@ static int mmu_rb_insert(struct rb_root *root, struct mmu_rb_node *node) } static void mmu_rb_remove(struct rb_root *root, struct mmu_rb_node *node, - bool notifier) + struct mm_struct *mm) { struct hfi1_filedata *fdata = container_of(root, struct hfi1_filedata, tid_rb_root); diff --git a/drivers/staging/rdma/hfi1/user_sdma.c b/drivers/staging/rdma/hfi1/user_sdma.c index ab6b6a42000f..e08c74fe4c6b 100644 --- a/drivers/staging/rdma/hfi1/user_sdma.c +++ b/drivers/staging/rdma/hfi1/user_sdma.c @@ -299,7 +299,8 @@ static int defer_packet_queue( static void activate_packet_queue(struct iowait *, int); static bool sdma_rb_filter(struct mmu_rb_node *, unsigned long, unsigned long); static int sdma_rb_insert(struct rb_root *, struct mmu_rb_node *); -static void sdma_rb_remove(struct rb_root *, struct mmu_rb_node *, bool); +static void sdma_rb_remove(struct rb_root *, struct mmu_rb_node *, + struct mm_struct *); static int sdma_rb_invalidate(struct rb_root *, struct mmu_rb_node *); static struct mmu_rb_ops sdma_rb_ops = { @@ -1063,8 +1064,10 @@ static int pin_vector_pages(struct user_sdma_request *req, rb_node = hfi1_mmu_rb_search(&pq->sdma_rb_root, (unsigned long)iovec->iov.iov_base, iovec->iov.iov_len); - if (rb_node) + if (rb_node && !IS_ERR(rb_node)) node = container_of(rb_node, struct sdma_mmu_node, rb); + else + rb_node = NULL; if (!node) { node = kzalloc(sizeof(*node), GFP_KERNEL); @@ -1502,7 +1505,7 @@ static void user_sdma_free_request(struct user_sdma_request *req, bool unpin) &req->pq->sdma_rb_root, (unsigned long)req->iovs[i].iov.iov_base, req->iovs[i].iov.iov_len); - if (!mnode) + if (!mnode || IS_ERR(mnode)) continue; node = container_of(mnode, struct sdma_mmu_node, rb); @@ -1547,7 +1550,7 @@ static int sdma_rb_insert(struct rb_root *root, struct mmu_rb_node *mnode) } static void sdma_rb_remove(struct rb_root *root, struct mmu_rb_node *mnode, - bool notifier) + struct mm_struct *mm) { struct sdma_mmu_node *node = container_of(mnode, struct sdma_mmu_node, rb); @@ -1557,14 +1560,19 @@ static void sdma_rb_remove(struct rb_root *root, struct mmu_rb_node *mnode, node->pq->n_locked -= node->npages; spin_unlock(&node->pq->evict_lock); - unpin_vector_pages(notifier ? NULL : current->mm, node->pages, - node->npages); + /* + * If mm is set, we are being called by the MMU notifier and we + * should not pass a mm_struct to unpin_vector_page(). This is to + * prevent a deadlock when hfi1_release_user_pages() attempts to + * take the mmap_sem, which the MMU notifier has already taken. + */ + unpin_vector_pages(mm ? NULL : current->mm, node->pages, node->npages); /* * If called by the MMU notifier, we have to adjust the pinned * page count ourselves. */ - if (notifier) - current->mm->pinned_vm -= node->npages; + if (mm) + mm->pinned_vm -= node->npages; kfree(node); } From de82bdff62a9078a6e4f1452e2f2604686e51e49 Mon Sep 17 00:00:00 2001 From: Mitko Haralanov Date: Tue, 12 Apr 2016 10:46:03 -0700 Subject: [PATCH 146/181] IB/hfi1: Fix deadlock caused by locking with wrong scope The locking around the interval RB tree is designed to prevent access to the tree while it's being modified. The locking in its current form is too overzealous, which is causing a deadlock in certain cases with the following backtrace: Kernel panic - not syncing: Watchdog detected hard LOCKUP on cpu 0 CPU: 0 PID: 5836 Comm: IMB-MPI1 Tainted: G O 3.12.18-wfr+ #1 0000000000000000 ffff88087f206c50 ffffffff814f1caa ffffffff817b53f0 ffff88087f206cc8 ffffffff814ecd56 0000000000000010 ffff88087f206cd8 ffff88087f206c78 0000000000000000 0000000000000000 0000000000001662 Call Trace: [] dump_stack+0x45/0x56 [] panic+0xc2/0x1cb [] ? restart_watchdog_hrtimer+0x50/0x50 [] watchdog_overflow_callback+0xc2/0xd0 [] __perf_event_overflow+0x8e/0x2b0 [] perf_event_overflow+0x14/0x20 [] intel_pmu_handle_irq+0x1b6/0x390 [] perf_event_nmi_handler+0x2b/0x50 [] nmi_handle.isra.3+0x88/0x180 [] do_nmi+0x169/0x310 [] end_repeat_nmi+0x1e/0x2e [] ? unmap_single+0x30/0x30 [] ? _raw_spin_lock_irqsave+0x2d/0x40 [] ? _raw_spin_lock_irqsave+0x2d/0x40 [] ? _raw_spin_lock_irqsave+0x2d/0x40 <> [] hfi1_mmu_rb_search+0x38/0x70 [hfi1] [] user_sdma_free_request+0xcb/0x120 [hfi1] [] user_sdma_txreq_cb+0x263/0x350 [hfi1] [] ? sdma_txclean+0x27/0x1c0 [hfi1] [] ? user_sdma_send_pkts+0x1710/0x1710 [hfi1] [] sdma_make_progress+0x166/0x480 [hfi1] [] ? ttwu_do_wakeup+0x19/0xd0 [] sdma_engine_interrupt+0x8e/0x100 [hfi1] [] sdma_interrupt+0x5d/0xa0 [hfi1] [] handle_irq_event_percpu+0x47/0x1d0 [] handle_irq_event+0x37/0x60 [] handle_edge_irq+0x6f/0x120 [] handle_irq+0xbf/0x150 [] ? irq_enter+0x17/0x80 [] do_IRQ+0x4d/0xc0 [] common_interrupt+0x6a/0x6a [] ? finish_task_switch+0x54/0xe0 [] __schedule+0x3b6/0x7e0 [] __cond_resched+0x26/0x30 [] _cond_resched+0x3a/0x50 [] down_write+0x12/0x30 [] hfi1_release_user_pages+0x69/0x90 [hfi1] [] sdma_rb_remove+0x9a/0xc0 [hfi1] [] __mmu_rb_remove.isra.5+0x5d/0x70 [hfi1] [] hfi1_mmu_rb_remove+0x56/0x70 [hfi1] [] hfi1_user_sdma_process_request+0x74b/0x1160 [hfi1] [] hfi1_aio_write+0xc3/0x100 [hfi1] [] do_sync_readv_writev+0x4c/0x80 [] do_readv_writev+0xbb/0x230 [] ? fsnotify+0x241/0x320 [] ? finish_task_switch+0x54/0xe0 [] vfs_writev+0x35/0x60 [] SyS_writev+0x49/0xc0 [] ? __audit_syscall_exit+0x1f6/0x2a0 [] system_call_fastpath+0x16/0x1b As evident from the backtrace above, the process was being put to sleep while holding the lock. Limiting the scope of the lock only to the RB tree operation fixes the above error allowing for proper locking and the process being put to sleep when needed. Reviewed-by: Dennis Dalessandro Reviewed-by: Dean Luick Signed-off-by: Mitko Haralanov Signed-off-by: Doug Ledford --- drivers/staging/rdma/hfi1/mmu_rb.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/staging/rdma/hfi1/mmu_rb.c b/drivers/staging/rdma/hfi1/mmu_rb.c index eac4d041d351..b3f0682a36c9 100644 --- a/drivers/staging/rdma/hfi1/mmu_rb.c +++ b/drivers/staging/rdma/hfi1/mmu_rb.c @@ -177,7 +177,7 @@ unlock: return ret; } -/* Caller must host handler lock */ +/* Caller must hold handler lock */ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, unsigned long addr, unsigned long len) @@ -201,13 +201,19 @@ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, return node; } +/* Caller must *not* hold handler lock. */ static void __mmu_rb_remove(struct mmu_rb_handler *handler, struct mmu_rb_node *node, struct mm_struct *mm) { + unsigned long flags; + /* Validity of handler and node pointers has been checked by caller. */ hfi1_cdbg(MMU, "Removing node addr 0x%llx, len %u", node->addr, node->len); + spin_lock_irqsave(&handler->lock, flags); __mmu_int_rb_remove(node, handler->root); + spin_unlock_irqrestore(&handler->lock, flags); + if (handler->ops->remove) handler->ops->remove(handler->root, node, mm); } @@ -232,14 +238,11 @@ struct mmu_rb_node *hfi1_mmu_rb_search(struct rb_root *root, unsigned long addr, void hfi1_mmu_rb_remove(struct rb_root *root, struct mmu_rb_node *node) { struct mmu_rb_handler *handler = find_mmu_handler(root); - unsigned long flags; if (!handler || !node) return; - spin_lock_irqsave(&handler->lock, flags); __mmu_rb_remove(handler, node, NULL); - spin_unlock_irqrestore(&handler->lock, flags); } static struct mmu_rb_handler *find_mmu_handler(struct rb_root *root) @@ -289,8 +292,11 @@ static void mmu_notifier_mem_invalidate(struct mmu_notifier *mn, ptr = __mmu_int_rb_iter_next(node, start, end - 1); hfi1_cdbg(MMU, "Invalidating node addr 0x%llx, len %u", node->addr, node->len); - if (handler->ops->invalidate(root, node)) + if (handler->ops->invalidate(root, node)) { + spin_unlock_irqrestore(&handler->lock, flags); __mmu_rb_remove(handler, node, mm); + spin_lock_irqsave(&handler->lock, flags); + } } spin_unlock_irqrestore(&handler->lock, flags); } From 849e3e9398608c26a7c54bf9fbf3288f7ced6bfb Mon Sep 17 00:00:00 2001 From: Mitko Haralanov Date: Tue, 12 Apr 2016 10:46:16 -0700 Subject: [PATCH 147/181] IB/hfi1: Prevent unpinning of wrong pages The routine used by the SDMA cache to handle already cached nodes can extend an already existing node. In its error handling code, the routine will unpin pages when not all pages of the buffer extension were pinned. There was a bug in that part of the routine, which would mistakenly unpin pages from the original set rather than the newly pinned pages. This commit fixes that bug by offsetting the page array to the proper place pointing at the beginning of the newly pinned pages. Reviewed-by: Dean Luick Signed-off-by: Mitko Haralanov Signed-off-by: Doug Ledford --- drivers/staging/rdma/hfi1/user_sdma.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/staging/rdma/hfi1/user_sdma.c b/drivers/staging/rdma/hfi1/user_sdma.c index e08c74fe4c6b..d53a659548e0 100644 --- a/drivers/staging/rdma/hfi1/user_sdma.c +++ b/drivers/staging/rdma/hfi1/user_sdma.c @@ -278,7 +278,8 @@ static inline void pq_update(struct hfi1_user_sdma_pkt_q *); static void user_sdma_free_request(struct user_sdma_request *, bool); static int pin_vector_pages(struct user_sdma_request *, struct user_sdma_iovec *); -static void unpin_vector_pages(struct mm_struct *, struct page **, unsigned); +static void unpin_vector_pages(struct mm_struct *, struct page **, unsigned, + unsigned); static int check_header_template(struct user_sdma_request *, struct hfi1_pkt_header *, u32, u32); static int set_txreq_header(struct user_sdma_request *, @@ -1110,7 +1111,8 @@ retry: goto bail; } if (pinned != npages) { - unpin_vector_pages(current->mm, pages, pinned); + unpin_vector_pages(current->mm, pages, node->npages, + pinned); ret = -EFAULT; goto bail; } @@ -1150,9 +1152,9 @@ bail: } static void unpin_vector_pages(struct mm_struct *mm, struct page **pages, - unsigned npages) + unsigned start, unsigned npages) { - hfi1_release_user_pages(mm, pages, npages, 0); + hfi1_release_user_pages(mm, pages + start, npages, 0); kfree(pages); } @@ -1566,7 +1568,8 @@ static void sdma_rb_remove(struct rb_root *root, struct mmu_rb_node *mnode, * prevent a deadlock when hfi1_release_user_pages() attempts to * take the mmap_sem, which the MMU notifier has already taken. */ - unpin_vector_pages(mm ? NULL : current->mm, node->pages, node->npages); + unpin_vector_pages(mm ? NULL : current->mm, node->pages, 0, + node->npages); /* * If called by the MMU notifier, we have to adjust the pinned * page count ourselves. From e6d2e0176e1f3c1e1534851b66c0b972f03ff069 Mon Sep 17 00:00:00 2001 From: Jubin John Date: Tue, 12 Apr 2016 10:47:00 -0700 Subject: [PATCH 148/181] IB/rdmavt: Fix send scheduling call_send is used to determine whether to send immediately or schedule a send for later. The current logic in rdmavt is inverted and has a negative impact on the latency of the hfi1 and qib drivers. Fix this regression by correctly calling send immediately when call_send is set. Reviewed-by: Dennis Dalessandro Reviewed-by: Mike Marciniszyn Signed-off-by: Jubin John Signed-off-by: Doug Ledford --- drivers/infiniband/sw/rdmavt/qp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index bd82a6948dc8..a9e3bcc522c4 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1637,9 +1637,9 @@ bail: spin_unlock_irqrestore(&qp->s_hlock, flags); if (nreq) { if (call_send) - rdi->driver_f.schedule_send_no_lock(qp); - else rdi->driver_f.do_send(qp); + else + rdi->driver_f.schedule_send_no_lock(qp); } return err; } From b9b06cb6fedab10665a2d527464b45f332d17465 Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Wed, 20 Apr 2016 06:05:30 -0700 Subject: [PATCH 149/181] IB/hfi1: Fix missing lock/unlock in verbs drain callback The iowait_sdma_drained() callback lacked locking to protect the qp s_flags field. This causes the s_flags to be out of sync on multiple CPUs, potentially corrupting the s_flags. Fixes: a545f5308b6c ("staging/rdma/hfi: fix CQ completion order issue") Reviewed-by: Sebastian Sanchez Signed-off-by: Mike Marciniszyn Reviewed-by: Leon Romanovsky Signed-off-by: Doug Ledford --- drivers/staging/rdma/hfi1/qp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/staging/rdma/hfi1/qp.c b/drivers/staging/rdma/hfi1/qp.c index 29a5ad28019b..dc9119e1b458 100644 --- a/drivers/staging/rdma/hfi1/qp.c +++ b/drivers/staging/rdma/hfi1/qp.c @@ -519,10 +519,12 @@ static void iowait_sdma_drained(struct iowait *wait) * do the flush work until that QP's * sdma work has finished. */ + spin_lock(&qp->s_lock); if (qp->s_flags & RVT_S_WAIT_DMA) { qp->s_flags &= ~RVT_S_WAIT_DMA; hfi1_schedule_send(qp); } + spin_unlock(&qp->s_lock); } /** From 94158442eb0c66bbb0b733999e108fa26a7673ef Mon Sep 17 00:00:00 2001 From: Mitko Haralanov Date: Wed, 20 Apr 2016 06:05:36 -0700 Subject: [PATCH 150/181] IB/hfi1: Don't attempt to free resources if initialization failed Attempting to free resources which have not been allocated and initialized properly led to the following kernel backtrace: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [] unlock_exp_tids.isra.8+0x2e/0x120 [hfi1] PGD 852a43067 PUD 85d4a6067 PMD 0 Oops: 0000 [#1] SMP CPU: 0 PID: 2831 Comm: osu_bw Tainted: G IO 3.12.18-wfr+ #1 task: ffff88085b15b540 ti: ffff8808588fe000 task.ti: ffff8808588fe000 RIP: 0010:[] [] unlock_exp_tids.isra.8+0x2e/0x120 [hfi1] RSP: 0018:ffff8808588ffde0 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff880858a31800 RCX: 0000000000000000 RDX: ffff88085d971bc0 RSI: ffff880858a318f8 RDI: ffff880858a318c0 RBP: ffff8808588ffe20 R08: 0000000000000000 R09: 0000000000000000 R10: ffff88087ffd6f40 R11: 0000000001100348 R12: ffff880852900000 R13: ffff880858a318c0 R14: 0000000000000000 R15: ffff88085d971be8 FS: 00007f4674e83740(0000) GS:ffff88087f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000085c377000 CR4: 00000000001407f0 Stack: ffffffffa0941a71 ffff880858a318f8 ffff88085d971bc0 ffff880858a31800 ffff880852900000 ffff880858a31800 00000000003ffff7 ffff88085d971bc0 ffff8808588ffe60 ffffffffa09663fc ffff8808588ffe60 ffff880858a31800 Call Trace: [] ? find_mmu_handler+0x51/0x70 [hfi1] [] hfi1_user_exp_rcv_free+0x6c/0x120 [hfi1] [] hfi1_file_close+0x1a9/0x340 [hfi1] [] __fput+0xe9/0x270 [] ____fput+0xe/0x10 [] task_work_run+0xa7/0xe0 [] do_notify_resume+0x59/0x80 [] int_signal+0x12/0x17 This commit re-arranges the context initialization code in a way that would allow for context event flags to be used to determine whether the context has been successfully initialized. In turn, this can be used to skip the resource de-allocation if they were never allocated in the first place. Fixes: 3abb33ac6521 ("staging/hfi1: Add TID cache receive init and free funcs") Reviewed-by: Dennis Dalessandro Signed-off-by: Mitko Haralanov Reviewed-by: Leon Romanovsky --- drivers/staging/rdma/hfi1/file_ops.c | 60 +++++++++++------------- drivers/staging/rdma/hfi1/user_exp_rcv.c | 2 + 2 files changed, 29 insertions(+), 33 deletions(-) diff --git a/drivers/staging/rdma/hfi1/file_ops.c b/drivers/staging/rdma/hfi1/file_ops.c index 8396dc5fb6c1..ec6c2269d739 100644 --- a/drivers/staging/rdma/hfi1/file_ops.c +++ b/drivers/staging/rdma/hfi1/file_ops.c @@ -791,15 +791,16 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) spin_unlock_irqrestore(&dd->uctxt_lock, flags); dd->rcd[uctxt->ctxt] = NULL; + + hfi1_user_exp_rcv_free(fdata); + hfi1_clear_ctxt_pkey(dd, uctxt->ctxt); + uctxt->rcvwait_to = 0; uctxt->piowait_to = 0; uctxt->rcvnowait = 0; uctxt->pionowait = 0; uctxt->event_flags = 0; - hfi1_user_exp_rcv_free(fdata); - hfi1_clear_ctxt_pkey(dd, uctxt->ctxt); - hfi1_stats.sps_ctxts--; if (++dd->freectxts == dd->num_user_contexts) aspm_enable_all(dd); @@ -1127,27 +1128,13 @@ bail: static int user_init(struct file *fp) { - int ret; unsigned int rcvctrl_ops = 0; struct hfi1_filedata *fd = fp->private_data; struct hfi1_ctxtdata *uctxt = fd->uctxt; /* make sure that the context has already been setup */ - if (!test_bit(HFI1_CTXT_SETUP_DONE, &uctxt->event_flags)) { - ret = -EFAULT; - goto done; - } - - /* - * Subctxts don't need to initialize anything since master - * has done it. - */ - if (fd->subctxt) { - ret = wait_event_interruptible(uctxt->wait, !test_bit( - HFI1_CTXT_MASTER_UNINIT, - &uctxt->event_flags)); - goto expected; - } + if (!test_bit(HFI1_CTXT_SETUP_DONE, &uctxt->event_flags)) + return -EFAULT; /* initialize poll variables... */ uctxt->urgent = 0; @@ -1202,19 +1189,7 @@ static int user_init(struct file *fp) wake_up(&uctxt->wait); } -expected: - /* - * Expected receive has to be setup for all processes (including - * shared contexts). However, it has to be done after the master - * context has been fully configured as it depends on the - * eager/expected split of the RcvArray entries. - * Setting it up here ensures that the subcontexts will be waiting - * (due to the above wait_event_interruptible() until the master - * is setup. - */ - ret = hfi1_user_exp_rcv_init(fp); -done: - return ret; + return 0; } static int get_ctxt_info(struct file *fp, void __user *ubase, __u32 len) @@ -1261,7 +1236,7 @@ static int setup_ctxt(struct file *fp) int ret = 0; /* - * Context should be set up only once (including allocation and + * Context should be set up only once, including allocation and * programming of eager buffers. This is done if context sharing * is not requested or by the master process. */ @@ -1282,8 +1257,27 @@ static int setup_ctxt(struct file *fp) if (ret) goto done; } + } else { + ret = wait_event_interruptible(uctxt->wait, !test_bit( + HFI1_CTXT_MASTER_UNINIT, + &uctxt->event_flags)); + if (ret) + goto done; } + ret = hfi1_user_sdma_alloc_queues(uctxt, fp); + if (ret) + goto done; + /* + * Expected receive has to be setup for all processes (including + * shared contexts). However, it has to be done after the master + * context has been fully configured as it depends on the + * eager/expected split of the RcvArray entries. + * Setting it up here ensures that the subcontexts will be waiting + * (due to the above wait_event_interruptible() until the master + * is setup. + */ + ret = hfi1_user_exp_rcv_init(fp); if (ret) goto done; diff --git a/drivers/staging/rdma/hfi1/user_exp_rcv.c b/drivers/staging/rdma/hfi1/user_exp_rcv.c index 5b72849bbd71..8bd56d5c783d 100644 --- a/drivers/staging/rdma/hfi1/user_exp_rcv.c +++ b/drivers/staging/rdma/hfi1/user_exp_rcv.c @@ -255,6 +255,8 @@ int hfi1_user_exp_rcv_free(struct hfi1_filedata *fd) struct hfi1_ctxtdata *uctxt = fd->uctxt; struct tid_group *grp, *gptr; + if (!test_bit(HFI1_CTXT_SETUP_DONE, &uctxt->event_flags)) + return 0; /* * The notifier would have been removed when the process'es mm * was freed. From 7723d8c2445c4dfa91f8df42703b56f8ade59af7 Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Fri, 22 Apr 2016 11:17:03 -0700 Subject: [PATCH 151/181] IB/hfi1: Use kernel default llseek for ui device The ui device llseek had a mistake with SEEK_END and did not fully follow seek semantics. Correct all this by using a kernel supplied function for fixed size devices. Cc: Al Viro Reviewed-by: Dennis Dalessandro Signed-off-by: Dean Luick Signed-off-by: Doug Ledford --- drivers/staging/rdma/hfi1/file_ops.c | 25 ++----------------------- 1 file changed, 2 insertions(+), 23 deletions(-) diff --git a/drivers/staging/rdma/hfi1/file_ops.c b/drivers/staging/rdma/hfi1/file_ops.c index ec6c2269d739..541529589736 100644 --- a/drivers/staging/rdma/hfi1/file_ops.c +++ b/drivers/staging/rdma/hfi1/file_ops.c @@ -1559,29 +1559,8 @@ static loff_t ui_lseek(struct file *filp, loff_t offset, int whence) { struct hfi1_devdata *dd = filp->private_data; - switch (whence) { - case SEEK_SET: - break; - case SEEK_CUR: - offset += filp->f_pos; - break; - case SEEK_END: - offset = ((dd->kregend - dd->kregbase) + DC8051_DATA_MEM_SIZE) - - offset; - break; - default: - return -EINVAL; - } - - if (offset < 0) - return -EINVAL; - - if (offset >= (dd->kregend - dd->kregbase) + DC8051_DATA_MEM_SIZE) - return -EINVAL; - - filp->f_pos = offset; - - return filp->f_pos; + return fixed_size_llseek(filp, offset, whence, + (dd->kregend - dd->kregbase) + DC8051_DATA_MEM_SIZE); } /* NOTE: assumes unsigned long is 8 bytes */ From e6bd18f57aad1a2d1ef40e646d03ed0f2515c9e3 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Sun, 10 Apr 2016 19:13:13 -0600 Subject: [PATCH 152/181] IB/security: Restrict use of the write() interface The drivers/infiniband stack uses write() as a replacement for bi-directional ioctl(). This is not safe. There are ways to trigger write calls that result in the return structure that is normally written to user space being shunted off to user specified kernel memory instead. For the immediate repair, detect and deny suspicious accesses to the write API. For long term, update the user space libraries and the kernel API to something that doesn't present the same security vulnerabilities (likely a structured ioctl() interface). The impacted uAPI interfaces are generally only available if hardware from drivers/infiniband is installed in the system. Reported-by: Jann Horn Signed-off-by: Linus Torvalds Signed-off-by: Jason Gunthorpe [ Expanded check to all known write() entry points ] Cc: stable@vger.kernel.org Signed-off-by: Doug Ledford --- drivers/infiniband/core/ucm.c | 4 ++++ drivers/infiniband/core/ucma.c | 3 +++ drivers/infiniband/core/uverbs_main.c | 5 +++++ drivers/infiniband/hw/qib/qib_file_ops.c | 5 +++++ drivers/staging/rdma/hfi1/TODO | 2 +- drivers/staging/rdma/hfi1/file_ops.c | 6 ++++++ include/rdma/ib.h | 16 ++++++++++++++++ 7 files changed, 40 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 4a9aa0433b07..7713ef089c3c 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -48,6 +48,7 @@ #include +#include #include #include #include @@ -1103,6 +1104,9 @@ static ssize_t ib_ucm_write(struct file *filp, const char __user *buf, struct ib_ucm_cmd_hdr hdr; ssize_t result; + if (WARN_ON_ONCE(!ib_safe_file_access(filp))) + return -EACCES; + if (len < sizeof(hdr)) return -EINVAL; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index dd3bcceadfde..c0f3826abb30 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1574,6 +1574,9 @@ static ssize_t ucma_write(struct file *filp, const char __user *buf, struct rdma_ucm_cmd_hdr hdr; ssize_t ret; + if (WARN_ON_ONCE(!ib_safe_file_access(filp))) + return -EACCES; + if (len < sizeof(hdr)) return -EINVAL; diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 28ba2cc81535..31f422a70623 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -48,6 +48,8 @@ #include +#include + #include "uverbs.h" MODULE_AUTHOR("Roland Dreier"); @@ -709,6 +711,9 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, int srcu_key; ssize_t ret; + if (WARN_ON_ONCE(!ib_safe_file_access(filp))) + return -EACCES; + if (count < sizeof hdr) return -EINVAL; diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index e449e394963f..24f4a782e0f4 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -45,6 +45,8 @@ #include #include +#include + #include "qib.h" #include "qib_common.h" #include "qib_user_sdma.h" @@ -2067,6 +2069,9 @@ static ssize_t qib_write(struct file *fp, const char __user *data, ssize_t ret = 0; void *dest; + if (WARN_ON_ONCE(!ib_safe_file_access(fp))) + return -EACCES; + if (count < sizeof(cmd.type)) { ret = -EINVAL; goto bail; diff --git a/drivers/staging/rdma/hfi1/TODO b/drivers/staging/rdma/hfi1/TODO index 05de0dad8762..4c6f1d7d2eaf 100644 --- a/drivers/staging/rdma/hfi1/TODO +++ b/drivers/staging/rdma/hfi1/TODO @@ -3,4 +3,4 @@ July, 2015 - Remove unneeded file entries in sysfs - Remove software processing of IB protocol and place in library for use by qib, ipath (if still present), hfi1, and eventually soft-roce - +- Replace incorrect uAPI diff --git a/drivers/staging/rdma/hfi1/file_ops.c b/drivers/staging/rdma/hfi1/file_ops.c index 541529589736..c1c5bf82addb 100644 --- a/drivers/staging/rdma/hfi1/file_ops.c +++ b/drivers/staging/rdma/hfi1/file_ops.c @@ -49,6 +49,8 @@ #include #include +#include + #include "hfi.h" #include "pio.h" #include "device.h" @@ -190,6 +192,10 @@ static ssize_t hfi1_file_write(struct file *fp, const char __user *data, int uctxt_required = 1; int must_be_root = 0; + /* FIXME: This interface cannot continue out of staging */ + if (WARN_ON_ONCE(!ib_safe_file_access(fp))) + return -EACCES; + if (count < sizeof(cmd)) { ret = -EINVAL; goto bail; diff --git a/include/rdma/ib.h b/include/rdma/ib.h index cf8f9e700e48..a6b93706b0fc 100644 --- a/include/rdma/ib.h +++ b/include/rdma/ib.h @@ -34,6 +34,7 @@ #define _RDMA_IB_H #include +#include struct ib_addr { union { @@ -86,4 +87,19 @@ struct sockaddr_ib { __u64 sib_scope_id; }; +/* + * The IB interfaces that use write() as bi-directional ioctl() are + * fundamentally unsafe, since there are lots of ways to trigger "write()" + * calls from various contexts with elevated privileges. That includes the + * traditional suid executable error message writes, but also various kernel + * interfaces that can write to file descriptors. + * + * This function provides protection for the legacy API by restricting the + * calling context. + */ +static inline bool ib_safe_file_access(struct file *filp) +{ + return filp->f_cred == current_cred() && segment_eq(get_fs(), USER_DS); +} + #endif /* _RDMA_IB_H */ From 1883598d4201361a6d2ce785095695f58071ee11 Mon Sep 17 00:00:00 2001 From: Charmaine Lee Date: Tue, 12 Apr 2016 08:14:23 -0700 Subject: [PATCH 153/181] drm/vmwgfx: Enable SVGA_3D_CMD_DX_SET_PREDICATION Fixes piglit tests nv_conditional_render-* crashes. Signed-off-by: Charmaine Lee Reviewed-by: Brian Paul Reviewed-by: Sinclair Yeh --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 723ba16c6084..541b34077de2 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3305,7 +3305,7 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = { true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_READBACK_QUERY, &vmw_cmd_invalid, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_PREDICATION, &vmw_cmd_invalid, + VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_PREDICATION, &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_VIEWPORTS, &vmw_cmd_dx_cid_check, true, false, true), From e02e58843153ce80a9fe7588def89b2638d40e64 Mon Sep 17 00:00:00 2001 From: Charmaine Lee Date: Tue, 12 Apr 2016 08:19:08 -0700 Subject: [PATCH 154/181] drm/vmwgfx: use vmw_cmd_dx_cid_check for query commands. Instead of calling vmw_cmd_ok, call vmw_cmd_dx_cid_check to validate the context id for query commands. Signed-off-by: Charmaine Lee Reviewed-by: Sinclair Yeh --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 541b34077de2..1a1a87cbf109 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3293,15 +3293,15 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = { &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_DEFINE_QUERY, &vmw_cmd_dx_define_query, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_DESTROY_QUERY, &vmw_cmd_ok, + VMW_CMD_DEF(SVGA_3D_CMD_DX_DESTROY_QUERY, &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_BIND_QUERY, &vmw_cmd_dx_bind_query, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_QUERY_OFFSET, - &vmw_cmd_ok, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_BEGIN_QUERY, &vmw_cmd_ok, + &vmw_cmd_dx_cid_check, true, false, true), + VMW_CMD_DEF(SVGA_3D_CMD_DX_BEGIN_QUERY, &vmw_cmd_dx_cid_check, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_END_QUERY, &vmw_cmd_ok, + VMW_CMD_DEF(SVGA_3D_CMD_DX_END_QUERY, &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_READBACK_QUERY, &vmw_cmd_invalid, true, false, true), From 7851496a32319237456919575e5f4ba62f74cc7d Mon Sep 17 00:00:00 2001 From: Sinclair Yeh Date: Thu, 21 Apr 2016 11:29:31 -0700 Subject: [PATCH 155/181] drm/vmwgfx: Fix order of operation mode->hdisplay * (var->bits_per_pixel + 7) gets evaluated before the division, potentially making the pitch larger than it should be. Since the original intention is to do a div-round-up, just use the macro instead. Signed-off-by: Sinclair Yeh Reviewed-by: Thomas Hellstrom --- drivers/gpu/drm/vmwgfx/vmwgfx_fb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 3b1faf7862a5..679a4cb98ee3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -573,9 +573,9 @@ static int vmw_fb_set_par(struct fb_info *info) mode = old_mode; old_mode = NULL; } else if (!vmw_kms_validate_mode_vram(vmw_priv, - mode->hdisplay * - (var->bits_per_pixel + 7) / 8, - mode->vdisplay)) { + mode->hdisplay * + DIV_ROUND_UP(var->bits_per_pixel, 8), + mode->vdisplay)) { drm_mode_destroy(vmw_priv->dev, mode); return -EINVAL; } From 4c8bb95921e9ac01b9dd0c3abbaf6514ce88af92 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 24 Apr 2016 22:18:59 +0200 Subject: [PATCH 156/181] RDMA/nes: don't leak skb if carrier down Alternatively one could free the skb, OTOH I don't think this test is useful so just remove it. Cc: Signed-off-by: Florian Westphal Signed-off-by: Doug Ledford --- drivers/infiniband/hw/nes/nes_nic.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c index 3ea9e055fdd3..92914539edc7 100644 --- a/drivers/infiniband/hw/nes/nes_nic.c +++ b/drivers/infiniband/hw/nes/nes_nic.c @@ -500,9 +500,6 @@ static int nes_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev) * skb_shinfo(skb)->nr_frags, skb_is_gso(skb)); */ - if (!netif_carrier_ok(netdev)) - return NETDEV_TX_OK; - if (netif_queue_stopped(netdev)) return NETDEV_TX_BUSY; From 8639a847b0e11f8d2daa3eafe15a9609c91fd357 Mon Sep 17 00:00:00 2001 From: Atsushi Kumagai Date: Thu, 28 Apr 2016 16:18:18 -0700 Subject: [PATCH 157/181] kexec: update VMCOREINFO for compound_order/dtor makedumpfile refers page.lru.next to get the order of compound pages for page filtering. However, now the order is stored in page.compound_order, hence VMCOREINFO should be updated to export the offset of page.compound_order. The fact is, page.compound_order was introduced already in kernel 4.0, but the offset of it was the same as page.lru.next until kernel 4.3, so this was not actual problem. The above can be said also for page.lru.prev and page.compound_dtor, it's necessary to detect hugetlbfs pages. Further, the content was changed from direct address to the ID which means dtor. The problem is that unnecessary hugepages won't be removed from a dump file in kernels 4.4.x and later. This means that extra disk space would be consumed. It's a problem, but not critical. Signed-off-by: Atsushi Kumagai Acked-by: Dave Young Cc: "Eric W. Biederman" Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec_core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 8d34308ea449..cbbb4c724149 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1415,6 +1415,8 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(page, lru); VMCOREINFO_OFFSET(page, _mapcount); VMCOREINFO_OFFSET(page, private); + VMCOREINFO_OFFSET(page, compound_dtor); + VMCOREINFO_OFFSET(page, compound_order); VMCOREINFO_OFFSET(pglist_data, node_zones); VMCOREINFO_OFFSET(pglist_data, nr_zones); #ifdef CONFIG_FLAT_NODE_MEM_MAP @@ -1447,8 +1449,8 @@ static int __init crash_save_vmcoreinfo_init(void) #ifdef CONFIG_X86 VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); #endif -#ifdef CONFIG_HUGETLBFS - VMCOREINFO_SYMBOL(free_huge_page); +#ifdef CONFIG_HUGETLB_PAGE + VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR); #endif arch_crash_save_vmcoreinfo(); From d7f53518f713d3d9bf5ed150f943853fb94e7473 Mon Sep 17 00:00:00 2001 From: Atsushi Kumagai Date: Thu, 28 Apr 2016 16:18:21 -0700 Subject: [PATCH 158/181] kexec: export OFFSET(page.compound_head) to find out compound tail page PageAnon() always look at head page to check PAGE_MAPPING_ANON and tail page's page->mapping has just a poisoned data since commit 1c290f642101 ("mm: sanitize page->mapping for tail pages"). If makedumpfile checks page->mapping of a compound tail page to distinguish anonymous page as usual, it must fail in newer kernel. So it's necessary to export OFFSET(page.compound_head) to avoid checking compound tail pages. The problem is that unnecessary hugepages won't be removed from a dump file in kernels 4.5.x and later. This means that extra disk space would be consumed. It's a problem, but not critical. Signed-off-by: Atsushi Kumagai Acked-by: Dave Young Cc: "Eric W. Biederman" Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kexec_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index cbbb4c724149..1391d3ee3b86 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1417,6 +1417,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(page, private); VMCOREINFO_OFFSET(page, compound_dtor); VMCOREINFO_OFFSET(page, compound_order); + VMCOREINFO_OFFSET(page, compound_head); VMCOREINFO_OFFSET(pglist_data, node_zones); VMCOREINFO_OFFSET(pglist_data, nr_zones); #ifdef CONFIG_FLAT_NODE_MEM_MAP From 66ee95d16a7f1b7b4f1dd74a2d81c6e19dc29a14 Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Thu, 28 Apr 2016 16:18:24 -0700 Subject: [PATCH 159/181] mm: exclude HugeTLB pages from THP page_mapped() logic HugeTLB pages cannot be split, so we use the compound_mapcount to track rmaps. Currently page_mapped() will check the compound_mapcount, but will also go through the constituent pages of a THP compound page and query the individual _mapcount's too. Unfortunately, page_mapped() does not distinguish between HugeTLB and THP compound pages and assumes that a compound page always needs to have HPAGE_PMD_NR pages querying. For most cases when dealing with HugeTLB this is just inefficient, but for scenarios where the HugeTLB page size is less than the pmd block size (e.g. when using contiguous bit on ARM) this can lead to crashes. This patch adjusts the page_mapped function such that we skip the unnecessary THP reference checks for HugeTLB pages. Fixes: e1534ae95004 ("mm: differentiate page_mapped() from page_mapcount() for compound pages") Signed-off-by: Steve Capper Acked-by: Kirill A. Shutemov Cc: Will Deacon Cc: Catalin Marinas Cc: Michal Hocko Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index a55e5be0894f..79b6c18d0a38 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1031,6 +1031,8 @@ static inline bool page_mapped(struct page *page) page = compound_head(page); if (atomic_read(compound_mapcount_ptr(page)) >= 0) return true; + if (PageHuge(page)) + return false; for (i = 0; i < hpage_nr_pages(page); i++) { if (atomic_read(&page[i]._mapcount) >= 0) return true; From aa88b68c3b1dce8bc3fd54c8a7372a777ff265cd Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 28 Apr 2016 16:18:27 -0700 Subject: [PATCH 160/181] thp: keep huge zero page pinned until tlb flush Andrea has found[1] a race condition on MMU-gather based TLB flush vs split_huge_page() or shrinker which frees huge zero under us (patch 1/2 and 2/2 respectively). With new THP refcounting, we don't need patch 1/2: mmu_gather keeps the page pinned until flush is complete and the pin prevents the page from being split under us. We still need patch 2/2. This is simplified version of Andrea's patch. We don't need fancy encoding. [1] http://lkml.kernel.org/r/1447938052-22165-1-git-send-email-aarcange@redhat.com Signed-off-by: Kirill A. Shutemov Reported-by: Andrea Arcangeli Reviewed-by: Andrea Arcangeli Cc: "Aneesh Kumar K.V" Cc: Mel Gorman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Dave Hansen Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 5 +++++ mm/huge_memory.c | 6 +++--- mm/swap.c | 5 +++++ 3 files changed, 13 insertions(+), 3 deletions(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 7008623e24b1..d7b9e5346fba 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -152,6 +152,7 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) } struct page *get_huge_zero_page(void); +void put_huge_zero_page(void); #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) @@ -208,6 +209,10 @@ static inline bool is_huge_zero_page(struct page *page) return false; } +static inline void put_huge_zero_page(void) +{ + BUILD_BUG(); +} static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 86f9f8b82f8e..5346de05f471 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -232,7 +232,7 @@ retry: return READ_ONCE(huge_zero_page); } -static void put_huge_zero_page(void) +void put_huge_zero_page(void) { /* * Counter should never go to zero here. Only shrinker can put @@ -1684,12 +1684,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (vma_is_dax(vma)) { spin_unlock(ptl); if (is_huge_zero_pmd(orig_pmd)) - put_huge_zero_page(); + tlb_remove_page(tlb, pmd_page(orig_pmd)); } else if (is_huge_zero_pmd(orig_pmd)) { pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd)); atomic_long_dec(&tlb->mm->nr_ptes); spin_unlock(ptl); - put_huge_zero_page(); + tlb_remove_page(tlb, pmd_page(orig_pmd)); } else { struct page *page = pmd_page(orig_pmd); page_remove_rmap(page, true); diff --git a/mm/swap.c b/mm/swap.c index a0bc206b4ac6..03aacbcb013f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -728,6 +728,11 @@ void release_pages(struct page **pages, int nr, bool cold) zone = NULL; } + if (is_huge_zero_page(page)) { + put_huge_zero_page(); + continue; + } + page = compound_head(page); if (!put_page_testzero(page)) continue; From 314e9b75b3f673a61ecbf0bba401830bc7dfe121 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 28 Apr 2016 16:18:30 -0700 Subject: [PATCH 161/181] mailmap: fix Krzysztof Kozlowski's misspelled name Patchwork introduced a garbled Polish character in commit 1e3012d0fdc5 ("crypto: s5p-sss - Use memcpy_toio for iomem annotated memory") so fix the mail mapping. Additionally prefer to use kernel.org account for personal work, instead of my gmail address. Signed-off-by: Krzysztof Kozlowski Cc: Herbert Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index 90c0aefc276d..c45e71f551cd 100644 --- a/.mailmap +++ b/.mailmap @@ -79,6 +79,7 @@ Kay Sievers Kenneth W Chen Konstantin Khlebnikov Koushik +Krzysztof Kozlowski Kuninori Morimoto Leonid I Ananiev Linas Vepstas From 3486b85a29c1741db99d0c522211c82d2b7a56d0 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 28 Apr 2016 16:18:32 -0700 Subject: [PATCH 162/181] mm/huge_memory: replace VM_NO_THP VM_BUG_ON with actual VMA check Khugepaged detects own VMAs by checking vm_file and vm_ops but this way it cannot distinguish private /dev/zero mappings from other special mappings like /dev/hpet which has no vm_ops and popultes PTEs in mmap. This fixes false-positive VM_BUG_ON and prevents installing THP where they are not expected. Link: http://lkml.kernel.org/r/CACT4Y+ZmuZMV5CjSFOeXviwQdABAgT7T+StKfTqan9YDtgEi5g@mail.gmail.com Fixes: 78f11a255749 ("mm: thp: fix /dev/zero MAP_PRIVATE and vm_flags cleanups") Signed-off-by: Konstantin Khlebnikov Reported-by: Dmitry Vyukov Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Dmitry Vyukov Cc: Andrea Arcangeli Cc: stable Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5346de05f471..df67b53ae3c5 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1960,10 +1960,9 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma, * page fault if needed. */ return 0; - if (vma->vm_ops) + if (vma->vm_ops || (vm_flags & VM_NO_THP)) /* khugepaged not yet working on file or special mappings */ return 0; - VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma); hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart < hend) @@ -2352,8 +2351,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma) return false; if (is_vma_temporary_stack(vma)) return false; - VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma); - return true; + return !(vma->vm_flags & VM_NO_THP); } static void collapse_huge_page(struct mm_struct *mm, From 28093f9f34cedeaea0f481c58446d9dac6dd620f Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Thu, 28 Apr 2016 16:18:35 -0700 Subject: [PATCH 163/181] numa: fix /proc//numa_maps for THP In gather_pte_stats() a THP pmd is cast into a pte, which is wrong because the layouts may differ depending on the architecture. On s390 this will lead to inaccurate numa_maps accounting in /proc because of misguided pte_present() and pte_dirty() checks on the fake pte. On other architectures pte_present() and pte_dirty() may work by chance, but there may be an issue with direct-access (dax) mappings w/o underlying struct pages when HAVE_PTE_SPECIAL is set and THP is available. In vm_normal_page() the fake pte will be checked with pte_special() and because there is no "special" bit in a pmd, this will always return false and the VM_PFNMAP | VM_MIXEDMAP checking will be skipped. On dax mappings w/o struct pages, an invalid struct page pointer would then be returned that can crash the kernel. This patch fixes the numa_maps THP handling by introducing new "_pmd" variants of the can_gather_numa_stats() and vm_normal_page() functions. Signed-off-by: Gerald Schaefer Cc: Naoya Horiguchi Cc: "Kirill A . Shutemov" Cc: Konstantin Khlebnikov Cc: Michal Hocko Cc: Vlastimil Babka Cc: Jerome Marchand Cc: Johannes Weiner Cc: Dave Hansen Cc: Mel Gorman Cc: Dan Williams Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Michael Holzheu Cc: [4.3+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 33 ++++++++++++++++++++++++++++++--- include/linux/mm.h | 2 ++ mm/memory.c | 40 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 72 insertions(+), 3 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 229cb546bee0..541583510cfb 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1518,6 +1518,32 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return page; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static struct page *can_gather_numa_stats_pmd(pmd_t pmd, + struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *page; + int nid; + + if (!pmd_present(pmd)) + return NULL; + + page = vm_normal_page_pmd(vma, addr, pmd); + if (!page) + return NULL; + + if (PageReserved(page)) + return NULL; + + nid = page_to_nid(page); + if (!node_isset(nid, node_states[N_MEMORY])) + return NULL; + + return page; +} +#endif + static int gather_pte_stats(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -1527,14 +1553,14 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, pte_t *orig_pte; pte_t *pte; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { - pte_t huge_pte = *(pte_t *)pmd; struct page *page; - page = can_gather_numa_stats(huge_pte, vma, addr); + page = can_gather_numa_stats_pmd(*pmd, vma, addr); if (page) - gather_stats(page, md, pte_dirty(huge_pte), + gather_stats(page, md, pmd_dirty(*pmd), HPAGE_PMD_SIZE/PAGE_SIZE); spin_unlock(ptl); return 0; @@ -1542,6 +1568,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0; +#endif orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); do { struct page *page = can_gather_numa_stats(*pte, vma, addr); diff --git a/include/linux/mm.h b/include/linux/mm.h index 79b6c18d0a38..864d7221de84 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1140,6 +1140,8 @@ struct zap_details { struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd); int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); diff --git a/mm/memory.c b/mm/memory.c index 93897f23cc11..305537fc8640 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -789,6 +789,46 @@ out: return pfn_to_page(pfn); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd) +{ + unsigned long pfn = pmd_pfn(pmd); + + /* + * There is no pmd_special() but there may be special pmds, e.g. + * in a direct-access (dax) mapping, so let's just replicate the + * !HAVE_PTE_SPECIAL case from vm_normal_page() here. + */ + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + + if (is_zero_pfn(pfn)) + return NULL; + if (unlikely(pfn > highest_memmap_pfn)) + return NULL; + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); +} +#endif + /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range From 7bf52fb891b64b8d61caf0b82060adb9db761aec Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 28 Apr 2016 16:18:38 -0700 Subject: [PATCH 164/181] mm: vmscan: reclaim highmem zone if buffer_heads is over limit We have been reclaimed highmem zone if buffer_heads is over limit but commit 6b4f7799c6a5 ("mm: vmscan: invoke slab shrinkers from shrink_zone()") changed the behavior so it doesn't reclaim highmem zone although buffer_heads is over the limit. This patch restores the logic. Fixes: 6b4f7799c6a5 ("mm: vmscan: invoke slab shrinkers from shrink_zone()") Signed-off-by: Minchan Kim Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index b934223eaa45..c638b28310fc 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2553,7 +2553,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) sc->gfp_mask |= __GFP_HIGHMEM; for_each_zone_zonelist_nodemask(zone, z, zonelist, - requested_highidx, sc->nodemask) { + gfp_zone(sc->gfp_mask), sc->nodemask) { enum zone_type classzone_idx; if (!populated_zone(zone)) From b06bad17c7435b600a1d7a35b56eff25e1d3dbc0 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 28 Apr 2016 16:18:41 -0700 Subject: [PATCH 165/181] mm: call swap_slot_free_notify() with page lock held Kyeongdon reported below error which is BUG_ON(!PageSwapCache(page)) in page_swap_info. The reason is that page_endio in rw_page unlocks the page if read I/O is completed so we need to hold a PG_lock again to check PageSwapCache. Otherwise, the page can be removed from swapcache. Kernel BUG at c00f9040 [verbose debug info unavailable] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM Modules linked in: CPU: 4 PID: 13446 Comm: RenderThread Tainted: G W 3.10.84-g9f14aec-dirty #73 task: c3b73200 ti: dd192000 task.ti: dd192000 PC is at page_swap_info+0x10/0x2c LR is at swap_slot_free_notify+0x18/0x6c pc : [] lr : [] psr: 400f0113 sp : dd193d78 ip : c2deb1e4 fp : da015180 r10: 00000000 r9 : 000200da r8 : c120fe08 r7 : 00000000 r6 : 00000000 r5 : c249a6c0 r4 : = c249a6c0 r3 : 00000000 r2 : 40080009 r1 : 200f0113 r0 : = c249a6c0 .. .. Call Trace: page_swap_info+0x10/0x2c swap_slot_free_notify+0x18/0x6c swap_readpage+0x90/0x11c read_swap_cache_async+0x134/0x1ac swapin_readahead+0x70/0xb0 handle_pte_fault+0x320/0x6fc handle_mm_fault+0xc0/0xf0 do_page_fault+0x11c/0x36c do_DataAbort+0x34/0x118 Fixes: 3f2b1a04f44933f2 ("zram: revive swap_slot_free_notify") Signed-off-by: Minchan Kim Tested-by: Kyeongdon Kim Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_io.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/mm/page_io.c b/mm/page_io.c index cd92e3d67a32..985f23cfa79b 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -353,7 +353,11 @@ int swap_readpage(struct page *page) ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); if (!ret) { - swap_slot_free_notify(page); + if (trylock_page(page)) { + swap_slot_free_notify(page); + unlock_page(page); + } + count_vm_event(PSWPIN); return 0; } From d7e69488bd04de165667f6bc741c1c0ec6042ab9 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 28 Apr 2016 16:18:44 -0700 Subject: [PATCH 166/181] mm/hwpoison: fix wrong num_poisoned_pages accounting Currently, migration code increses num_poisoned_pages on *failed* migration page as well as successfully migrated one at the trial of memory-failure. It will make the stat wrong. As well, it marks the page as PG_HWPoison even if the migration trial failed. It would mean we cannot recover the corrupted page using memory-failure facility. This patches fixes it. Signed-off-by: Minchan Kim Reported-by: Vlastimil Babka Acked-by: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/mm/migrate.c b/mm/migrate.c index 6c822a7b27e0..f9dfb18a4eba 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -975,7 +975,13 @@ out: dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); /* Soft-offlined page shouldn't go through lru cache list */ - if (reason == MR_MEMORY_FAILURE) { + if (reason == MR_MEMORY_FAILURE && rc == MIGRATEPAGE_SUCCESS) { + /* + * With this release, we free successfully migrated + * page and set PG_HWPoison on just freed page + * intentionally. Although it's rather weird, it's how + * HWPoison flag works at the moment. + */ put_page(page); if (!test_set_page_hwpoison(page)) num_poisoned_pages_inc(); From eeb68d1d2d48b5bfe9d79d8eac35df576bb79a99 Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Thu, 28 Apr 2016 16:18:47 -0700 Subject: [PATCH 167/181] .mailmap: add Frank Rowand Set current email address to replace obsolete email addresses. Signed-off-by: Frank Rowand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .mailmap | 3 +++ 1 file changed, 3 insertions(+) diff --git a/.mailmap b/.mailmap index c45e71f551cd..c156a8b4d845 100644 --- a/.mailmap +++ b/.mailmap @@ -48,6 +48,9 @@ Felix Kuhling Felix Moeller Filipe Lautert Franck Bui-Huu +Frank Rowand +Frank Rowand +Frank Rowand Frank Zago Greg Kroah-Hartman Greg Kroah-Hartman From fd901c95388b3bd5a6f749ed1d677a672b992298 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 28 Apr 2016 16:18:49 -0700 Subject: [PATCH 168/181] mm: wake kcompactd before kswapd's short sleep When kswapd goes to sleep it checks if the node is balanced and at first it sleeps only for HZ/10 time, then rechecks if the node is still balanced and nobody has woken it during the initial sleep. Only then it goes fully sleep until an allocation slowpath wakes it up again. For higher-order allocations, waking up kcompactd is done only before the full sleep. This turns out to be an issue in case another high-order allocation fails during the initial sleep. It will wake kswapd up, however kswapd considers the zone balanced from the order-0 perspective, and will just quickly try to sleep again. So if there's a longer stream of high-order allocations hitting the slowpath and waking up kswapd, it might never actually wake up kcompactd, which may be considered a regression from kswapd-based compaction. In the worst case, it might be that a single allocation that cannot direct reclaim/compact itself is waking kswapd in the retry loop and preventing kcompactd from being woken up and unblocking it. This patch makes sure kcompactd is woken up in such situations by simply moving the wakeup before the short initial sleep. More efficient solution would be to wake kcompactd immediately instead of kswapd if the node is already order-0 balanced, but in that case we should also move reset_isolation_suitable() call to kcompactd so it's not adding to the allocator's latency. Since it's late in the 4.6 cycle, let's go with the simpler change for now. Fixes: accf62422b3a ("mm, kswapd: replace kswapd compaction with waking up kcompactd") Signed-off-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: "Kirill A. Shutemov" Cc: Rik van Riel Cc: Joonsoo Kim Cc: Mel Gorman Cc: David Rientjes Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index c638b28310fc..142cb61f4822 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3318,6 +3318,20 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, /* Try to sleep for a short interval */ if (prepare_kswapd_sleep(pgdat, order, remaining, balanced_classzone_idx)) { + /* + * Compaction records what page blocks it recently failed to + * isolate pages from and skips them in the future scanning. + * When kswapd is going to sleep, it is reasonable to assume + * that pages and compaction may succeed so reset the cache. + */ + reset_isolation_suitable(pgdat); + + /* + * We have freed the memory, now we should compact it to make + * allocation of the requested order possible. + */ + wakeup_kcompactd(pgdat, order, classzone_idx); + remaining = schedule_timeout(HZ/10); finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); @@ -3341,20 +3355,6 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - /* - * Compaction records what page blocks it recently failed to - * isolate pages from and skips them in the future scanning. - * When kswapd is going to sleep, it is reasonable to assume - * that pages and compaction may succeed so reset the cache. - */ - reset_isolation_suitable(pgdat); - - /* - * We have freed the memory, now we should compact it to make - * allocation of the requested order possible. - */ - wakeup_kcompactd(pgdat, order, classzone_idx); - if (!kthread_should_stop()) schedule(); From bdab42dfc974d15303afbf259f340f374a453974 Mon Sep 17 00:00:00 2001 From: James Morse Date: Thu, 28 Apr 2016 16:18:52 -0700 Subject: [PATCH 169/181] kcov: don't trace the code coverage code Kcov causes the compiler to add a call to __sanitizer_cov_trace_pc() in every basic block. Ftrace patches in a call to _mcount() to each function it has annotated. Letting these mechanisms annotate each other is a bad thing. Break the loop by adding 'notrace' to __sanitizer_cov_trace_pc() so that ftrace won't try to patch this code. This patch lets arm64 with KCOV and STACK_TRACER boot. Signed-off-by: James Morse Acked-by: Dmitry Vyukov Cc: Alexander Potapenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kcov.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/kcov.c b/kernel/kcov.c index 3efbee0834a8..78bed7125515 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -43,7 +43,7 @@ struct kcov { * Entry point from instrumented code. * This is called once per basic-block/edge. */ -void __sanitizer_cov_trace_pc(void) +void notrace __sanitizer_cov_trace_pc(void) { struct task_struct *t; enum kcov_mode mode; From 36f05ae8bce904b4c8105363e6227a79d343bda6 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Thu, 28 Apr 2016 16:18:55 -0700 Subject: [PATCH 170/181] kcov: don't profile branches in kcov Profiling 'if' statements in __sanitizer_cov_trace_pc() leads to unbound recursion and crash: __sanitizer_cov_trace_pc() -> ftrace_likely_update -> __sanitizer_cov_trace_pc() ... Define DISABLE_BRANCH_PROFILING to disable this tracer. Signed-off-by: Andrey Ryabinin Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kcov.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/kcov.c b/kernel/kcov.c index 78bed7125515..a02f2dddd1d7 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -1,5 +1,6 @@ #define pr_fmt(fmt) "kcov: " fmt +#define DISABLE_BRANCH_PROFILING #include #include #include From a320817c68e3fa1fc3ddaa709a1ad45cf533693b Mon Sep 17 00:00:00 2001 From: Ananth N Mavinakayanahalli Date: Thu, 28 Apr 2016 16:18:58 -0700 Subject: [PATCH 171/181] Ananth has moved The current ID is going away soon... update email address Signed-off-by: Ananth N Mavinakayanahalli Cc: Masami Hiramatsu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 849133608da7..7f72d54f065d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6400,7 +6400,7 @@ F: mm/kmemleak.c F: mm/kmemleak-test.c KPROBES -M: Ananth N Mavinakayanahalli +M: Ananth N Mavinakayanahalli M: Anil S Keshavamurthy M: "David S. Miller" M: Masami Hiramatsu From b73413647ee36406561618f68d0661d49dc47489 Mon Sep 17 00:00:00 2001 From: xuejiufei Date: Thu, 28 Apr 2016 16:19:01 -0700 Subject: [PATCH 172/181] ocfs2/dlm: return zero if deref_done message is successfully handled dlm_deref_lockres_done_handler() should return zero if the message is successfully handled. Fixes: 60d663cb5273 ("ocfs2/dlm: add DEREF_DONE message"). Signed-off-by: xuejiufei Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/dlm/dlmmaster.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 9aed6e202201..13719d3f35f8 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2455,6 +2455,8 @@ int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data, spin_unlock(&dlm->spinlock); + ret = 0; + done: dlm_put(dlm); return ret; From c2e7e00b715d3c65f301bec8559d6af4ef8098ab Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 28 Apr 2016 16:19:03 -0700 Subject: [PATCH 173/181] mm/memory-failure: fix race with compound page split/merge get_hwpoison_page() must recheck relation between head and tail pages. n-horiguchi said: without this recheck, the race causes kernel to pin an irrelevant page, and finally makes kernel crash for refcount mismatch. Signed-off-by: Konstantin Khlebnikov Acked-by: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 78f5f2641b91..ca5acee53b7a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -888,7 +888,15 @@ int get_hwpoison_page(struct page *page) } } - return get_page_unless_zero(head); + if (get_page_unless_zero(head)) { + if (head == compound_head(page)) + return 1; + + pr_info("MCE: %#lx cannot catch tail\n", page_to_pfn(page)); + put_page(head); + } + + return 0; } EXPORT_SYMBOL_GPL(get_hwpoison_page); From 99f23c2cded85a377325aa9fd374ffa3d55d1088 Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Thu, 28 Apr 2016 16:19:06 -0700 Subject: [PATCH 174/181] rapidio: fix potential NULL pointer dereference The change fixes improper check for a returned error value by class_create() function, which on error returns ERR_PTR() value, thus the original check always results in a dead code on error path. Signed-off-by: Vladimir Zapolskiy Signed-off-by: Alexandre Bounine Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/rapidio/devices/rio_mport_cdev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 5d4d91846357..96168b819044 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -2669,9 +2669,9 @@ static int __init mport_init(void) /* Create device class needed by udev */ dev_class = class_create(THIS_MODULE, DRV_NAME); - if (!dev_class) { + if (IS_ERR(dev_class)) { rmcd_error("Unable to create " DRV_NAME " class"); - return -EINVAL; + return PTR_ERR(dev_class); } ret = alloc_chrdev_region(&dev_number, 0, RIO_MAX_MPORTS, DRV_NAME); From 33334e25769c6ad69b983379578f42581d99a2f9 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 28 Apr 2016 16:19:09 -0700 Subject: [PATCH 175/181] lib/stackdepot.c: allow the stack trace hash to be zero Do not bail out from depot_save_stack() if the stack trace has zero hash. Initially depot_save_stack() silently dropped stack traces with zero hashes, however there's actually no point in reserving this zero value. Reported-by: Joonsoo Kim Signed-off-by: Alexander Potapenko Acked-by: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/stackdepot.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 654c9d87e83a..9e0b0315a724 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -210,10 +210,6 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace, goto fast_exit; hash = hash_stack(trace->entries, trace->nr_entries); - /* Bad luck, we won't store this stack. */ - if (hash == 0) - goto exit; - bucket = &stack_table[hash & STACK_HASH_MASK]; /* From 7c88a292dfcd6979e839493ef18d04770eb3bad0 Mon Sep 17 00:00:00 2001 From: Xishi Qiu Date: Thu, 28 Apr 2016 16:19:11 -0700 Subject: [PATCH 176/181] Documentation/sysctl/vm.txt: update numa_zonelist_order description Commit 3193913ce62c ("mm: page_alloc: default node-ordering on 64-bit NUMA, zone-ordering on 32-bit") changes the default value of numa_zonelist_order. Update the document. Signed-off-by: Xishi Qiu Cc: Mel Gorman Cc: Johannes Weiner Cc: Rik van Riel Cc: David Rientjes Cc: Kamezawa Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index cb0368459da3..34a5fece3121 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -581,15 +581,16 @@ Specify "[Nn]ode" for node order "Zone Order" orders the zonelists by zone type, then by node within each zone. Specify "[Zz]one" for zone order. -Specify "[Dd]efault" to request automatic configuration. Autoconfiguration -will select "node" order in following case. -(1) if the DMA zone does not exist or -(2) if the DMA zone comprises greater than 50% of the available memory or -(3) if any node's DMA zone comprises greater than 70% of its local memory and - the amount of local memory is big enough. +Specify "[Dd]efault" to request automatic configuration. -Otherwise, "zone" order will be selected. Default order is recommended unless -this is causing problems for your system/application. +On 32-bit, the Normal zone needs to be preserved for allocations accessible +by the kernel, so "zone" order will be selected. + +On 64-bit, devices that require DMA32/DMA are relatively rare, so "node" +order will be selected. + +Default order is recommended unless this is causing problems for your +system/application. ============================================================== From c4fc1956fa31003bfbe4f597e359d751568e2954 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Fri, 29 Apr 2016 15:42:25 +0200 Subject: [PATCH 177/181] EDAC: i7core, sb_edac: Don't return NOTIFY_BAD from mce_decoder callback Both of these drivers can return NOTIFY_BAD, but this terminates processing other callbacks that were registered later on the chain. Since the driver did nothing to log the error it seems wrong to prevent other interested parties from seeing it. E.g. neither of them had even bothered to check the type of the error to see if it was a memory error before the return NOTIFY_BAD. Signed-off-by: Tony Luck Acked-by: Aristeu Rozanski Acked-by: Mauro Carvalho Chehab Cc: linux-edac Cc: Link: http://lkml.kernel.org/r/72937355dd92318d2630979666063f8a2853495b.1461864507.git.tony.luck@intel.com Signed-off-by: Borislav Petkov --- drivers/edac/i7core_edac.c | 2 +- drivers/edac/sb_edac.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 01087a38da22..792bdae2b91d 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1866,7 +1866,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val, i7_dev = get_i7core_dev(mce->socketid); if (!i7_dev) - return NOTIFY_BAD; + return NOTIFY_DONE; mci = i7_dev->mci; pvt = mci->pvt_info; diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 468447aff8eb..8bf745d2da7e 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -3168,7 +3168,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, mci = get_mci_for_node_id(mce->socketid); if (!mci) - return NOTIFY_BAD; + return NOTIFY_DONE; pvt = mci->pvt_info; /* From 04974df8049fc4240d22759a91e035082ccd18b4 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 1 May 2016 15:52:31 -0700 Subject: [PATCH 178/181] Linux 4.6-rc6 --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 9496df81b9a8..7466de60ddc7 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ VERSION = 4 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc5 -NAME = Blurry Fish Butt +EXTRAVERSION = -rc6 +NAME = Charred Weasel # *DOCUMENTATION* # To see a list of typical targets execute "make help" From 444f94e9e625f6ec6bbe2cb232a6451c637f35a3 Mon Sep 17 00:00:00 2001 From: Schemmel Hans-Christoph Date: Fri, 29 Apr 2016 08:51:06 +0000 Subject: [PATCH 179/181] USB: serial: option: add support for Cinterion PH8 and AHxx Added support for Gemalto's Cinterion PH8 and AHxx products with 2 RmNet Interfaces and products with 1 RmNet + 1 USB Audio interface. In addition some minor renaming and formatting. Signed-off-by: Hans-Christoph Schemmel [johan: sort current entries and trim trailing whitespace ] Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index c6f497f16526..ab542d3ee2b1 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -375,18 +375,22 @@ static void option_instat_callback(struct urb *urb); #define HAIER_PRODUCT_CE81B 0x10f8 #define HAIER_PRODUCT_CE100 0x2009 -/* Cinterion (formerly Siemens) products */ -#define SIEMENS_VENDOR_ID 0x0681 -#define CINTERION_VENDOR_ID 0x1e2d +/* Gemalto's Cinterion products (formerly Siemens) */ +#define SIEMENS_VENDOR_ID 0x0681 +#define CINTERION_VENDOR_ID 0x1e2d +#define CINTERION_PRODUCT_HC25_MDMNET 0x0040 #define CINTERION_PRODUCT_HC25_MDM 0x0047 -#define CINTERION_PRODUCT_HC25_MDMNET 0x0040 +#define CINTERION_PRODUCT_HC28_MDMNET 0x004A /* same for HC28J */ #define CINTERION_PRODUCT_HC28_MDM 0x004C -#define CINTERION_PRODUCT_HC28_MDMNET 0x004A /* same for HC28J */ #define CINTERION_PRODUCT_EU3_E 0x0051 #define CINTERION_PRODUCT_EU3_P 0x0052 #define CINTERION_PRODUCT_PH8 0x0053 #define CINTERION_PRODUCT_AHXX 0x0055 #define CINTERION_PRODUCT_PLXX 0x0060 +#define CINTERION_PRODUCT_PH8_2RMNET 0x0082 +#define CINTERION_PRODUCT_PH8_AUDIO 0x0083 +#define CINTERION_PRODUCT_AHXX_2RMNET 0x0084 +#define CINTERION_PRODUCT_AHXX_AUDIO 0x0085 /* Olivetti products */ #define OLIVETTI_VENDOR_ID 0x0b3c @@ -633,6 +637,10 @@ static const struct option_blacklist_info telit_le922_blacklist_usbcfg3 = { .reserved = BIT(1) | BIT(2) | BIT(3), }; +static const struct option_blacklist_info cinterion_rmnet2_blacklist = { + .reserved = BIT(4) | BIT(5), +}; + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -1712,7 +1720,13 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX, 0xff) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, - { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8_2RMNET, 0xff), + .driver_info = (kernel_ulong_t)&cinterion_rmnet2_blacklist }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8_AUDIO, 0xff), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX_2RMNET, 0xff) }, + { USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX_AUDIO, 0xff) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) }, { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDM) }, { USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) }, From f0d09463c59c2d764a6c6d492cbe6d2c77f27153 Mon Sep 17 00:00:00 2001 From: lei liu Date: Tue, 3 May 2016 14:44:19 -0700 Subject: [PATCH 180/181] USB: serial: option: add more ZTE device ids More ZTE device ids. Signed-off-by: lei liu Cc: stable [properly sort them - gregkh] Signed-off-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 75 ++++++++++++++++++++++++++++++++++++- 1 file changed, 74 insertions(+), 1 deletion(-) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index ab542d3ee2b1..6ac8630162ca 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1610,7 +1610,79 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&net_intf3_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0178, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&net_intf3_blacklist }, - { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffe9, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff42, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff43, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff44, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff45, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff46, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff47, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff48, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff49, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4a, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4b, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4c, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4d, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4e, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff4f, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff50, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff51, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff52, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff53, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff54, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff55, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff56, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff57, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff58, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff59, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5a, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5b, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5c, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5d, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5e, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff5f, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff60, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff61, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff62, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff63, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff64, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff65, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff66, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff67, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff68, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff69, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6a, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6b, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6c, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6d, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6e, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff6f, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff70, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff71, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff72, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff73, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff74, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff75, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff76, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff77, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff78, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff79, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7a, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7b, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7c, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7d, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7e, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff7f, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff80, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff81, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff82, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff83, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff84, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff85, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff86, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff87, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff88, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff89, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8a, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8b, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8c, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff8d, 0xff, 0xff, 0xff) }, @@ -1621,6 +1693,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff92, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff93, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff94, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffe9, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffec, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffee, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xfff6, 0xff, 0xff, 0xff) }, From 74d2a91aec97ab832790c9398d320413ad185321 Mon Sep 17 00:00:00 2001 From: Lei Liu Date: Wed, 4 May 2016 16:34:22 +0800 Subject: [PATCH 181/181] USB: serial: option: add even more ZTE device ids Add even more ZTE device ids. Signed-off-by: lei liu Cc: stable [johan: rebase and replace commit message ] Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 54 +++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 6ac8630162ca..d96d423d00e6 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1693,6 +1693,60 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff92, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff93, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff94, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff9f, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa0, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa1, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa2, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa3, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa4, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa5, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa6, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa7, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa8, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffa9, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffaa, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffab, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffac, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffae, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffaf, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb0, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb1, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb2, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb3, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb4, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb5, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb6, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb7, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb8, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffb9, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffba, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbb, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbc, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbd, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbe, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffbf, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc0, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc1, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc2, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc3, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc4, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc5, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc6, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc7, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc8, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffc9, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffca, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffcb, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffcc, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffcd, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffce, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffcf, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd0, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd1, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd2, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd3, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd4, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffd5, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffe9, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffec, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xffee, 0xff, 0xff, 0xff) },