From 36a40c37389c7a1bef3f1024c55c056304acf439 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 Jun 2022 18:25:25 +0300 Subject: nvdimm/namespace: return uuid_null only once in nd_dev_to_uuid() Refactor nd_dev_to_uuid() in order to make code shorter and cleaner by joining conditions and hence returning uuid_null only once. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220607152525.33468-1-andriy.shevchenko@linux.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/namespace_devs.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index bf4f5c09d9b1..3dae17c90e8c 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -170,15 +170,12 @@ EXPORT_SYMBOL(nvdimm_namespace_disk_name); const uuid_t *nd_dev_to_uuid(struct device *dev) { - if (!dev) - return &uuid_null; - - if (is_namespace_pmem(dev)) { + if (dev && is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); return nspm->uuid; - } else - return &uuid_null; + } + return &uuid_null; } EXPORT_SYMBOL(nd_dev_to_uuid); -- cgit From 53fc59511fc4c567342b2ef3f7b99a086430e0b4 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 7 Jun 2022 18:37:50 +0300 Subject: nvdimm/namespace: drop unneeded temporary variable in size_store() Refactor size_store() in order to remove temporary variable on stack by joining conditionals. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220607153750.33639-1-andriy.shevchenko@linux.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/namespace_devs.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 3dae17c90e8c..0f863fda56e6 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -836,7 +836,6 @@ static ssize_t size_store(struct device *dev, { struct nd_region *nd_region = to_nd_region(dev->parent); unsigned long long val; - uuid_t **uuid = NULL; int rc; rc = kstrtoull(buf, 0, &val); @@ -850,16 +849,12 @@ static ssize_t size_store(struct device *dev, if (rc >= 0) rc = nd_namespace_label_update(nd_region, dev); - if (is_namespace_pmem(dev)) { + /* setting size zero == 'delete namespace' */ + if (rc == 0 && val == 0 && is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); - uuid = &nspm->uuid; - } - - if (rc == 0 && val == 0 && uuid) { - /* setting size zero == 'delete namespace' */ - kfree(*uuid); - *uuid = NULL; + kfree(nspm->uuid); + nspm->uuid = NULL; } dev_dbg(dev, "%llx %s (%d)\n", val, rc < 0 ? "fail" : "success", rc); -- cgit From 7eac0081a8e958106ed3aea402c8105f30fad6d9 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Wed, 10 Aug 2022 09:59:15 +0100 Subject: riscv: dts: microchip: add qspi compatible fallback The "hard" QSPI peripheral on PolarFire SoC is derived from version 2 of the FPGA IP core. The original binding had no fallback etc, so this device tree is valid as is. There was also no functional driver for the QSPI IP, so no device with a devicetree from a previous mainline release will regress. Link: https://lore.kernel.org/linux-spi/7c9f0d96-2882-964a-cd1f-916ddb3f0410@linaro.org/ Signed-off-by: Conor Dooley Acked-by: Krzysztof Kozlowski --- arch/riscv/boot/dts/microchip/mpfs.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 499c2e63ad35..45e3cc659882 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -330,7 +330,7 @@ }; qspi: spi@21000000 { - compatible = "microchip,mpfs-qspi"; + compatible = "microchip,mpfs-qspi", "microchip,coreqspi-rtl-v2"; #address-cells = <1>; #size-cells = <0>; reg = <0x0 0x21000000 0x0 0x1000>; -- cgit From 07ae9278b423500f93e10869b1a50276d82050ec Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 16 Aug 2022 16:18:25 +0200 Subject: rtc: mpfs: Remove printing of stray CR During boot, the driver prints out a stray carriage return character. Remove it, together with the preceding space character. While at it, change prescaler to "unsigned long", as returned by clk_get_rate(), to avoid truncating very large clock rates, and update the format specifiers. Fixes: 0b31d703598dc199 ("rtc: Add driver for Microchip PolarFire SoC") Signed-off-by: Geert Uytterhoeven Reviewed-by: Conor Dooley Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/bce2ca405ef96b1363fd1370887409d9e8468422.1660659437.git.geert+renesas@glider.be --- drivers/rtc/rtc-mpfs.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-mpfs.c b/drivers/rtc/rtc-mpfs.c index f14d1925e0c9..944ad1036516 100644 --- a/drivers/rtc/rtc-mpfs.c +++ b/drivers/rtc/rtc-mpfs.c @@ -233,7 +233,7 @@ static int mpfs_rtc_probe(struct platform_device *pdev) { struct mpfs_rtc_dev *rtcdev; struct clk *clk; - u32 prescaler; + unsigned long prescaler; int wakeup_irq, ret; rtcdev = devm_kzalloc(&pdev->dev, sizeof(struct mpfs_rtc_dev), GFP_KERNEL); @@ -275,14 +275,13 @@ static int mpfs_rtc_probe(struct platform_device *pdev) /* prescaler hardware adds 1 to reg value */ prescaler = clk_get_rate(devm_clk_get(&pdev->dev, "rtcref")) - 1; - if (prescaler > MAX_PRESCALER_COUNT) { - dev_dbg(&pdev->dev, "invalid prescaler %d\n", prescaler); + dev_dbg(&pdev->dev, "invalid prescaler %lu\n", prescaler); return -EINVAL; } writel(prescaler, rtcdev->base + PRESCALER_REG); - dev_info(&pdev->dev, "prescaler set to: 0x%X \r\n", prescaler); + dev_info(&pdev->dev, "prescaler set to: %lu\n", prescaler); device_init_wakeup(&pdev->dev, true); ret = dev_pm_set_wake_irq(&pdev->dev, wakeup_irq); -- cgit From f2c5671a64d2a79341e8ee45d5933f6a76960189 Mon Sep 17 00:00:00 2001 From: Bryan Brattlof Date: Tue, 16 Aug 2022 12:33:11 -0500 Subject: rtc: k3: wait until the unlock field is not zero After writing the magic words to the KICK0 and KICK1 registers, we must wait for a 1 in the unlock field of the general control register to signify when the rtc device is in an unlocked state. Signed-off-by: Bryan Brattlof Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220816173312.23243-1-bb@ti.com --- drivers/rtc/rtc-ti-k3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ti-k3.c b/drivers/rtc/rtc-ti-k3.c index 7a0f181d3fef..fd26be7868d2 100644 --- a/drivers/rtc/rtc-ti-k3.c +++ b/drivers/rtc/rtc-ti-k3.c @@ -190,7 +190,7 @@ static int k3rtc_unlock_rtc(struct ti_k3_rtc *priv) /* Skip fence since we are going to check the unlock bit as fence */ ret = regmap_field_read_poll_timeout(priv->r_fields[K3RTC_UNLOCK], ret, - !ret, 2, priv->sync_timeout_us); + ret, 2, priv->sync_timeout_us); return ret; } -- cgit From 1e2585b49d849196f359bbf86677943fe2d80afe Mon Sep 17 00:00:00 2001 From: Bryan Brattlof Date: Tue, 16 Aug 2022 12:33:12 -0500 Subject: rtc: k3: detect SoC to determine erratum fix To allow new SoCs to use this device without a new compatible string, use a soc_device_attribute list to define all SoCs affected by the TI i2327 erratum and require help from their bootloaders to unlock this device. Signed-off-by: Bryan Brattlof Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220816173312.23243-2-bb@ti.com --- drivers/rtc/rtc-ti-k3.c | 32 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 18 deletions(-) diff --git a/drivers/rtc/rtc-ti-k3.c b/drivers/rtc/rtc-ti-k3.c index fd26be7868d2..68e50c6a72f1 100644 --- a/drivers/rtc/rtc-ti-k3.c +++ b/drivers/rtc/rtc-ti-k3.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -45,14 +46,6 @@ #define K3RTC_MIN_OFFSET (-277761) #define K3RTC_MAX_OFFSET (277778) -/** - * struct ti_k3_rtc_soc_data - Private of compatible data for ti-k3-rtc - * @unlock_irq_erratum: Has erratum for unlock infinite IRQs (erratum i2327) - */ -struct ti_k3_rtc_soc_data { - const bool unlock_irq_erratum; -}; - static const struct regmap_config ti_k3_rtc_regmap_config = { .name = "peripheral-registers", .reg_bits = 32, @@ -118,7 +111,6 @@ static const struct reg_field ti_rtc_reg_fields[] = { * @rtc_dev: rtc device * @regmap: rtc mmio regmap * @r_fields: rtc register fields - * @soc: SoC compatible match data */ struct ti_k3_rtc { unsigned int irq; @@ -127,7 +119,6 @@ struct ti_k3_rtc { struct rtc_device *rtc_dev; struct regmap *regmap; struct regmap_field *r_fields[K3_RTC_MAX_FIELDS]; - const struct ti_k3_rtc_soc_data *soc; }; static int k3rtc_field_read(struct ti_k3_rtc *priv, enum ti_k3_rtc_fields f) @@ -195,6 +186,17 @@ static int k3rtc_unlock_rtc(struct ti_k3_rtc *priv) return ret; } +/* + * This is the list of SoCs affected by TI's i2327 errata causing the RTC + * state-machine to break if not unlocked fast enough during boot. These + * SoCs must have the bootloader unlock this device very early in the + * boot-flow before we (Linux) can use this device. + */ +static const struct soc_device_attribute has_erratum_i2327[] = { + { .family = "AM62X", .revision = "SR1.0" }, + { /* sentinel */ } +}; + static int k3rtc_configure(struct device *dev) { int ret; @@ -208,7 +210,7 @@ static int k3rtc_configure(struct device *dev) * * In such occurrence, it is assumed that the RTC module is unusable */ - if (priv->soc->unlock_irq_erratum) { + if (soc_device_match(has_erratum_i2327)) { ret = k3rtc_check_unlocked(priv); /* If there is an error OR if we are locked, return error */ if (ret) { @@ -602,8 +604,6 @@ static int ti_k3_rtc_probe(struct platform_device *pdev) if (IS_ERR(priv->rtc_dev)) return PTR_ERR(priv->rtc_dev); - priv->soc = of_device_get_match_data(dev); - priv->rtc_dev->ops = &ti_k3_rtc_ops; priv->rtc_dev->range_max = (1ULL << 48) - 1; /* 48Bit seconds */ ti_k3_rtc_nvmem_config.priv = priv; @@ -635,12 +635,8 @@ static int ti_k3_rtc_probe(struct platform_device *pdev) return devm_rtc_nvmem_register(priv->rtc_dev, &ti_k3_rtc_nvmem_config); } -static const struct ti_k3_rtc_soc_data ti_k3_am62_data = { - .unlock_irq_erratum = true, -}; - static const struct of_device_id ti_k3_rtc_of_match_table[] = { - {.compatible = "ti,am62-rtc", .data = &ti_k3_am62_data}, + {.compatible = "ti,am62-rtc" }, {} }; MODULE_DEVICE_TABLE(of, ti_k3_rtc_of_match_table); -- cgit From 509451ac03eb3afa4c4a32d4c11b1938f08de8e4 Mon Sep 17 00:00:00 2001 From: Emmanuel Gil Peyrot Date: Tue, 23 Aug 2022 15:07:02 +0200 Subject: rtc: gamecube: Always reset HW_SRNPROT after read This register would fail to be reset if reading the RTC bias failed for whichever reason. This commit reorganises the code around to unconditionally write it back to its previous value, unmap it, and return the result of regmap_read(), which makes it both simpler and more correct in the error case. Signed-off-by: Emmanuel Gil Peyrot Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220823130702.1046-1-linkmauve@linkmauve.fr --- drivers/rtc/rtc-gamecube.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/rtc/rtc-gamecube.c b/drivers/rtc/rtc-gamecube.c index c2717bb52b2b..c828bc8e05b9 100644 --- a/drivers/rtc/rtc-gamecube.c +++ b/drivers/rtc/rtc-gamecube.c @@ -265,18 +265,17 @@ static int gamecube_rtc_read_offset_from_sram(struct priv *d) * SRAM address as on previous consoles. */ ret = regmap_read(d->regmap, RTC_SRAM_BIAS, &d->rtc_bias); - if (ret) { - pr_err("failed to get the RTC bias\n"); - iounmap(hw_srnprot); - return -1; - } /* Reset SRAM access to how it was before, our job here is done. */ if (old != 0x7bf) iowrite32be(old, hw_srnprot); + iounmap(hw_srnprot); - return 0; + if (ret) + pr_err("failed to get the RTC bias\n"); + + return ret; } static const struct regmap_range rtc_rd_ranges[] = { -- cgit From 25bcfaad5ec4e82aede4270d4925967f8520d4cf Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 15 Aug 2022 18:59:23 +0200 Subject: rtc: mxc: Use devm_clk_get_enabled() helper The devm_clk_get_enabled() helper: - calls devm_clk_get() - calls clk_prepare_enable() and registers what is needed in order to call clk_disable_unprepare() when needed, as a managed resource. This simplifies the code, the error handling paths and avoid the need of a dedicated function used with devm_add_action_or_reset(). Based on my test with allyesconfig, this reduces the .o size from: text data bss dec hex filename 6705 1968 0 8673 21e1 drivers/rtc/rtc-mxc.o down to: 6212 1968 0 8180 1ff4 drivers/rtc/rtc-mxc.o Signed-off-by: Christophe JAILLET Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/1b5ad1877304b01ddbba73ca615274a52f781aa2.1660582728.git.christophe.jaillet@wanadoo.fr --- drivers/rtc/rtc-mxc.c | 27 ++------------------------- 1 file changed, 2 insertions(+), 25 deletions(-) diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c index 53d4e253e81f..762cf03345f1 100644 --- a/drivers/rtc/rtc-mxc.c +++ b/drivers/rtc/rtc-mxc.c @@ -291,14 +291,6 @@ static const struct rtc_class_ops mxc_rtc_ops = { .alarm_irq_enable = mxc_rtc_alarm_irq_enable, }; -static void mxc_rtc_action(void *p) -{ - struct rtc_plat_data *pdata = p; - - clk_disable_unprepare(pdata->clk_ref); - clk_disable_unprepare(pdata->clk_ipg); -} - static int mxc_rtc_probe(struct platform_device *pdev) { struct rtc_device *rtc; @@ -341,33 +333,18 @@ static int mxc_rtc_probe(struct platform_device *pdev) rtc->range_max = (1 << 16) * 86400ULL - 1; } - pdata->clk_ipg = devm_clk_get(&pdev->dev, "ipg"); + pdata->clk_ipg = devm_clk_get_enabled(&pdev->dev, "ipg"); if (IS_ERR(pdata->clk_ipg)) { dev_err(&pdev->dev, "unable to get ipg clock!\n"); return PTR_ERR(pdata->clk_ipg); } - ret = clk_prepare_enable(pdata->clk_ipg); - if (ret) - return ret; - - pdata->clk_ref = devm_clk_get(&pdev->dev, "ref"); + pdata->clk_ref = devm_clk_get_enabled(&pdev->dev, "ref"); if (IS_ERR(pdata->clk_ref)) { - clk_disable_unprepare(pdata->clk_ipg); dev_err(&pdev->dev, "unable to get ref clock!\n"); return PTR_ERR(pdata->clk_ref); } - ret = clk_prepare_enable(pdata->clk_ref); - if (ret) { - clk_disable_unprepare(pdata->clk_ipg); - return ret; - } - - ret = devm_add_action_or_reset(&pdev->dev, mxc_rtc_action, pdata); - if (ret) - return ret; - rate = clk_get_rate(pdata->clk_ref); if (rate == 32768) -- cgit From c530a3c716b963625e43aa915e0de6b4d1ce8ad9 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:02 +0800 Subject: sched/psi: Fix periodic aggregation shut off We don't want to wake periodic aggregation work back up if the task change is the aggregation worker itself going to sleep, or we'll ping-pong forever. Previously, we would use psi_task_change() in psi_dequeue() when task going to sleep, so this check was put in psi_task_change(). But commit 4117cebf1a9f ("psi: Optimize task switch inside shared cgroups") defer task sleep handling to psi_task_switch(), won't go through psi_task_change() anymore. So this patch move this check to psi_task_switch(). Fixes: 4117cebf1a9f ("psi: Optimize task switch inside shared cgroups") Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-2-zhouchengming@bytedance.com --- kernel/sched/psi.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ecb4b4ff4ce0..39463dcc16bb 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -796,7 +796,6 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; - bool wake_clock = true; void *iter = NULL; u64 now; @@ -806,19 +805,9 @@ void psi_task_change(struct task_struct *task, int clear, int set) psi_flags_change(task, clear, set); now = cpu_clock(cpu); - /* - * Periodic aggregation shuts off if there is a period of no - * task changes, so we wake it back up if necessary. However, - * don't do this if the task change is the aggregation worker - * itself going to sleep, or we'll ping-pong forever. - */ - if (unlikely((clear & TSK_RUNNING) && - (task->flags & PF_WQ_WORKER) && - wq_worker_last_func(task) == psi_avgs_work)) - wake_clock = false; while ((group = iterate_groups(task, &iter))) - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, now, true); } void psi_task_switch(struct task_struct *prev, struct task_struct *next, @@ -854,6 +843,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, if (prev->pid) { int clear = TSK_ONCPU, set = 0; + bool wake_clock = true; /* * When we're going to sleep, psi_dequeue() lets us @@ -867,13 +857,23 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, clear |= TSK_MEMSTALL_RUNNING; if (prev->in_iowait) set |= TSK_IOWAIT; + + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((prev->flags & PF_WQ_WORKER) && + wq_worker_last_func(prev) == psi_avgs_work)) + wake_clock = false; } psi_flags_change(prev, clear, set); iter = NULL; while ((group = iterate_groups(prev, &iter)) && group != common) - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, now, wake_clock); /* * TSK_ONCPU is handled up to the common ancestor. If we're tasked @@ -882,7 +882,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, if (sleep) { clear &= ~TSK_ONCPU; for (; group; group = iterate_groups(prev, &iter)) - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, now, wake_clock); } } } -- cgit From 58d8c2586cedb8a67f6f0dffa5eaed0f89135b39 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:03 +0800 Subject: sched/psi: Don't create cgroup PSI files when psi_disabled commit 3958e2d0c34e ("cgroup: make per-cgroup pressure stall tracking configurable") make PSI can be configured to skip per-cgroup stall accounting. And doesn't expose PSI files in cgroup hierarchy. This patch do the same thing when psi_disabled. Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-3-zhouchengming@bytedance.com --- kernel/cgroup/cgroup.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 718a70c01c04..96aefdb064bb 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3780,6 +3780,9 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) bool cgroup_psi_enabled(void) { + if (static_branch_likely(&psi_disabled)) + return false; + return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0; } -- cgit From e2ad8ab04c5cdfc8dc2f382c45d248ab01dee991 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:04 +0800 Subject: sched/psi: Save percpu memory when !psi_cgroups_enabled We won't use cgroup psi_group when !psi_cgroups_enabled, so don't bother to alloc percpu memory and init for it. Also don't need to migrate task PSI stats between cgroups in cgroup_move_task(). Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-4-zhouchengming@bytedance.com --- kernel/sched/psi.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 39463dcc16bb..77d53c03a76f 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -201,6 +201,7 @@ void __init psi_init(void) { if (!psi_enable) { static_branch_enable(&psi_disabled); + static_branch_disable(&psi_cgroups_enabled); return; } @@ -950,7 +951,7 @@ void psi_memstall_leave(unsigned long *flags) #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) { - if (static_branch_likely(&psi_disabled)) + if (!static_branch_likely(&psi_cgroups_enabled)) return 0; cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL); @@ -968,7 +969,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) void psi_cgroup_free(struct cgroup *cgroup) { - if (static_branch_likely(&psi_disabled)) + if (!static_branch_likely(&psi_cgroups_enabled)) return; cancel_delayed_work_sync(&cgroup->psi->avgs_work); @@ -996,7 +997,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) struct rq_flags rf; struct rq *rq; - if (static_branch_likely(&psi_disabled)) { + if (!static_branch_likely(&psi_cgroups_enabled)) { /* * Lame to do this here, but the scheduler cannot be locked * from the outside, so we move cgroups from inside sched/. -- cgit From d79ddb069c5257a924456eb99b53fc1ea715c0a3 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:05 +0800 Subject: sched/psi: Move private helpers to sched/stats.h This patch move psi_task_change/psi_task_switch declarations out of PSI public header, since they are only needed for implementing the PSI stats tracking in sched/stats.h psi_task_switch is obvious, psi_task_change can't be public helper since it doesn't check psi_disabled static key. And there is no any user now, so put it in sched/stats.h too. Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-5-zhouchengming@bytedance.com --- include/linux/psi.h | 4 ---- kernel/sched/stats.h | 4 ++++ 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/psi.h b/include/linux/psi.h index dd74411ac21d..fffd229fbf19 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -18,10 +18,6 @@ extern struct psi_group psi_system; void psi_init(void); -void psi_task_change(struct task_struct *task, int clear, int set); -void psi_task_switch(struct task_struct *prev, struct task_struct *next, - bool sleep); - void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index baa839c1ba96..c39b467ece43 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -107,6 +107,10 @@ __schedstats_from_se(struct sched_entity *se) } #ifdef CONFIG_PSI +void psi_task_change(struct task_struct *task, int clear, int set); +void psi_task_switch(struct task_struct *prev, struct task_struct *next, + bool sleep); + /* * PSI tracks state that persists across sleeps, such as iowaits and * memory stalls. As a result, it has to distinguish between sleeps, -- cgit From 65176f59a18d888684525658a1d0b8bf749d24f3 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:06 +0800 Subject: sched/psi: Optimize task switch inside shared cgroups again Way back when PSI_MEM_FULL was accounted from the timer tick, task switching could simply iterate next and prev to the common ancestor to update TSK_ONCPU and be done. Then memstall ticks were replaced with checking curr->in_memstall directly in psi_group_change(). That meant that now if the task switch was between a memstall and a !memstall task, we had to iterate through the common ancestors at least ONCE to fix up their state_masks. We added the identical_state filter to make sure the common ancestor elimination was skipped in that case. It seems that was always a little too eager, because it caused us to walk the common ancestors *twice* instead of the required once: the iteration for next could have stopped at the common ancestor; prev could have updated TSK_ONCPU up to the common ancestor, then finish to the root without changing any flags, just to get the new curr->in_memstall into the state_masks. This patch recognizes this and makes it so that we walk to the root exactly once if state_mask needs updating, which is simply catching up on a missed optimization that could have been done in commit 7fae6c8171d2 ("psi: Use ONCPU state tracking machinery to detect reclaim") directly. Apart from this, it's also necessary for the next patch "sched/psi: remove NR_ONCPU task accounting". Suppose we walk the common ancestors twice: (1) psi_group_change(.clear = 0, .set = TSK_ONCPU) (2) psi_group_change(.clear = TSK_ONCPU, .set = 0) We previously used tasks[NR_ONCPU] to record TSK_ONCPU, tasks[NR_ONCPU]++ in (1) then tasks[NR_ONCPU]-- in (2), so tasks[NR_ONCPU] still be correct. The next patch change to use one bit in state mask to record TSK_ONCPU, PSI_ONCPU bit will be set in (1), but then be cleared in (2), which cause the psi_group_cpu has task running on CPU but without PSI_ONCPU bit set! With this patch, we will never walk the common ancestors twice, so won't have above problem. Suggested-by: Johannes Weiner Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-6-zhouchengming@bytedance.com --- kernel/sched/psi.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 77d53c03a76f..d71dbc2356ff 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -820,20 +820,15 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, u64 now = cpu_clock(cpu); if (next->pid) { - bool identical_state; - psi_flags_change(next, 0, TSK_ONCPU); /* - * When switching between tasks that have an identical - * runtime state, the cgroup that contains both tasks - * we reach the first common ancestor. Iterate @next's - * ancestors only until we encounter @prev's ONCPU. + * Set TSK_ONCPU on @next's cgroups. If @next shares any + * ancestors with @prev, those will already have @prev's + * TSK_ONCPU bit set, and we can stop the iteration there. */ - identical_state = prev->psi_flags == next->psi_flags; iter = NULL; while ((group = iterate_groups(next, &iter))) { - if (identical_state && - per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) { + if (per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) { common = group; break; } @@ -877,10 +872,12 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, psi_group_change(group, cpu, clear, set, now, wake_clock); /* - * TSK_ONCPU is handled up to the common ancestor. If we're tasked - * with dequeuing too, finish that for the rest of the hierarchy. + * TSK_ONCPU is handled up to the common ancestor. If there are + * any other differences between the two tasks (e.g. prev goes + * to sleep, or only one task is memstall), finish propagating + * those differences all the way up to the root. */ - if (sleep) { + if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) { clear &= ~TSK_ONCPU; for (; group; group = iterate_groups(prev, &iter)) psi_group_change(group, cpu, clear, set, now, wake_clock); -- cgit From 71dbdde7914d32e86f01ac1f6e54e964c9dfdbd9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Aug 2022 00:41:07 +0800 Subject: sched/psi: Remove NR_ONCPU task accounting We put all fields updated by the scheduler in the first cacheline of struct psi_group_cpu for performance. Since we want add another PSI_IRQ_FULL to track IRQ/SOFTIRQ pressure, we need to reclaim space first. This patch remove NR_ONCPU task accounting in struct psi_group_cpu, use one bit in state_mask to track instead. Signed-off-by: Johannes Weiner Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Chengming Zhou Tested-by: Chengming Zhou Link: https://lore.kernel.org/r/20220825164111.29534-7-zhouchengming@bytedance.com --- include/linux/psi_types.h | 16 +++++++--------- kernel/sched/psi.c | 41 ++++++++++++++++++++++++++++++----------- 2 files changed, 37 insertions(+), 20 deletions(-) diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index c7fe7c089718..54cb74946db4 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -15,13 +15,6 @@ enum psi_task_count { NR_IOWAIT, NR_MEMSTALL, NR_RUNNING, - /* - * This can't have values other than 0 or 1 and could be - * implemented as a bit flag. But for now we still have room - * in the first cacheline of psi_group_cpu, and this way we - * don't have to special case any state tracking for it. - */ - NR_ONCPU, /* * For IO and CPU stalls the presence of running/oncpu tasks * in the domain means a partial rather than a full stall. @@ -32,16 +25,18 @@ enum psi_task_count { * threads and memstall ones. */ NR_MEMSTALL_RUNNING, - NR_PSI_TASK_COUNTS = 5, + NR_PSI_TASK_COUNTS = 4, }; /* Task state bitmasks */ #define TSK_IOWAIT (1 << NR_IOWAIT) #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) -#define TSK_ONCPU (1 << NR_ONCPU) #define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) +/* Only one task can be scheduled, no corresponding task count */ +#define TSK_ONCPU (1 << NR_PSI_TASK_COUNTS) + /* Resources that workloads could be stalled on */ enum psi_res { PSI_IO, @@ -68,6 +63,9 @@ enum psi_states { NR_PSI_STATES = 7, }; +/* Use one bit in the state mask to track TSK_ONCPU */ +#define PSI_ONCPU (1 << NR_PSI_STATES) + enum psi_aggregators { PSI_AVGS = 0, PSI_POLL, diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index d71dbc2356ff..4702a770e272 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -212,7 +212,7 @@ void __init psi_init(void) group_init(&psi_system); } -static bool test_state(unsigned int *tasks, enum psi_states state) +static bool test_state(unsigned int *tasks, enum psi_states state, bool oncpu) { switch (state) { case PSI_IO_SOME: @@ -225,9 +225,9 @@ static bool test_state(unsigned int *tasks, enum psi_states state) return unlikely(tasks[NR_MEMSTALL] && tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]); case PSI_CPU_SOME: - return unlikely(tasks[NR_RUNNING] > tasks[NR_ONCPU]); + return unlikely(tasks[NR_RUNNING] > oncpu); case PSI_CPU_FULL: - return unlikely(tasks[NR_RUNNING] && !tasks[NR_ONCPU]); + return unlikely(tasks[NR_RUNNING] && !oncpu); case PSI_NONIDLE: return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || tasks[NR_RUNNING]; @@ -689,9 +689,9 @@ static void psi_group_change(struct psi_group *group, int cpu, bool wake_clock) { struct psi_group_cpu *groupc; - u32 state_mask = 0; unsigned int t, m; enum psi_states s; + u32 state_mask; groupc = per_cpu_ptr(group->pcpu, cpu); @@ -707,17 +707,36 @@ static void psi_group_change(struct psi_group *group, int cpu, record_times(groupc, now); + /* + * Start with TSK_ONCPU, which doesn't have a corresponding + * task count - it's just a boolean flag directly encoded in + * the state mask. Clear, set, or carry the current state if + * no changes are requested. + */ + if (unlikely(clear & TSK_ONCPU)) { + state_mask = 0; + clear &= ~TSK_ONCPU; + } else if (unlikely(set & TSK_ONCPU)) { + state_mask = PSI_ONCPU; + set &= ~TSK_ONCPU; + } else { + state_mask = groupc->state_mask & PSI_ONCPU; + } + + /* + * The rest of the state mask is calculated based on the task + * counts. Update those first, then construct the mask. + */ for (t = 0, m = clear; m; m &= ~(1 << t), t++) { if (!(m & (1 << t))) continue; if (groupc->tasks[t]) { groupc->tasks[t]--; } else if (!psi_bug) { - printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u %u] clear=%x set=%x\n", + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n", cpu, t, groupc->tasks[0], groupc->tasks[1], groupc->tasks[2], - groupc->tasks[3], groupc->tasks[4], - clear, set); + groupc->tasks[3], clear, set); psi_bug = 1; } } @@ -726,9 +745,8 @@ static void psi_group_change(struct psi_group *group, int cpu, if (set & (1 << t)) groupc->tasks[t]++; - /* Calculate state mask representing active states */ for (s = 0; s < NR_PSI_STATES; s++) { - if (test_state(groupc->tasks, s)) + if (test_state(groupc->tasks, s, state_mask & PSI_ONCPU)) state_mask |= (1 << s); } @@ -740,7 +758,7 @@ static void psi_group_change(struct psi_group *group, int cpu, * task in a cgroup is in_memstall, the corresponding groupc * on that cpu is in PSI_MEM_FULL state. */ - if (unlikely(groupc->tasks[NR_ONCPU] && cpu_curr(cpu)->in_memstall)) + if (unlikely((state_mask & PSI_ONCPU) && cpu_curr(cpu)->in_memstall)) state_mask |= (1 << PSI_MEM_FULL); groupc->state_mask = state_mask; @@ -828,7 +846,8 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, */ iter = NULL; while ((group = iterate_groups(next, &iter))) { - if (per_cpu_ptr(group->pcpu, cpu)->tasks[NR_ONCPU]) { + if (per_cpu_ptr(group->pcpu, cpu)->state_mask & + PSI_ONCPU) { common = group; break; } -- cgit From 52b1364ba0b105122d6de0e719b36db705011ac1 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:08 +0800 Subject: sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure Now PSI already tracked workload pressure stall information for CPU, memory and IO. Apart from these, IRQ/SOFTIRQ could have obvious impact on some workload productivity, such as web service workload. When CONFIG_IRQ_TIME_ACCOUNTING, we can get IRQ/SOFTIRQ delta time from update_rq_clock_task(), in which we can record that delta to CPU curr task's cgroups as PSI_IRQ_FULL status. Note we don't use PSI_IRQ_SOME since IRQ/SOFTIRQ always happen in the current task on the CPU, make nothing productive could run even if it were runnable, so we only use PSI_IRQ_FULL. Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-8-zhouchengming@bytedance.com --- Documentation/admin-guide/cgroup-v2.rst | 6 +++ include/linux/psi_types.h | 10 ++++- kernel/cgroup/cgroup.c | 27 ++++++++++++ kernel/sched/core.c | 1 + kernel/sched/psi.c | 74 ++++++++++++++++++++++++++++++++- kernel/sched/stats.h | 2 + 6 files changed, 116 insertions(+), 4 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index be4a77baf784..971c418bc778 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -976,6 +976,12 @@ All cgroup core files are prefixed with "cgroup." killing cgroups is a process directed operation, i.e. it affects the whole thread-group. + irq.pressure + A read-write nested-keyed file. + + Shows pressure stall information for IRQ/SOFTIRQ. See + :ref:`Documentation/accounting/psi.rst ` for details. + Controllers =========== diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 54cb74946db4..40c28171cd91 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -42,7 +42,10 @@ enum psi_res { PSI_IO, PSI_MEM, PSI_CPU, - NR_PSI_RESOURCES = 3, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ, +#endif + NR_PSI_RESOURCES, }; /* @@ -58,9 +61,12 @@ enum psi_states { PSI_MEM_FULL, PSI_CPU_SOME, PSI_CPU_FULL, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + PSI_IRQ_FULL, +#endif /* Only per-CPU, to weigh the CPU in the global average: */ PSI_NONIDLE, - NR_PSI_STATES = 7, + NR_PSI_STATES, }; /* Use one bit in the state mask to track TSK_ONCPU */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 96aefdb064bb..b46d39b66214 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3763,6 +3763,23 @@ static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, return cgroup_pressure_write(of, buf, nbytes, PSI_CPU); } +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + + return psi_show(seq, psi, PSI_IRQ); +} + +static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cgroup_pressure_write(of, buf, nbytes, PSI_IRQ); +} +#endif + static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { @@ -5179,6 +5196,16 @@ static struct cftype cgroup_base_files[] = { .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + { + .name = "irq.pressure", + .flags = CFTYPE_PRESSURE, + .seq_show = cgroup_irq_pressure_show, + .write = cgroup_irq_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, +#endif #endif /* CONFIG_PSI */ { } /* terminate */ }; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ee28253c9ac0..7d1ea9240af0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -708,6 +708,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->prev_irq_time += irq_delta; delta -= irq_delta; + psi_account_irqtime(rq->curr, irq_delta); #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((¶virt_steal_rq_enabled))) { diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 4702a770e272..2545a78f82d8 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -904,6 +904,36 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, } } +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +void psi_account_irqtime(struct task_struct *task, u32 delta) +{ + int cpu = task_cpu(task); + void *iter = NULL; + struct psi_group *group; + struct psi_group_cpu *groupc; + u64 now; + + if (!task->pid) + return; + + now = cpu_clock(cpu); + + while ((group = iterate_groups(task, &iter))) { + groupc = per_cpu_ptr(group->pcpu, cpu); + + write_seqcount_begin(&groupc->seq); + + record_times(groupc, now); + groupc->times[PSI_IRQ_FULL] += delta; + + write_seqcount_end(&groupc->seq); + + if (group->poll_states & (1 << PSI_IRQ_FULL)) + psi_schedule_poll_work(group, 1); + } +} +#endif + /** * psi_memstall_enter - mark the beginning of a memory stall section * @flags: flags to handle nested sections @@ -1065,6 +1095,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { + bool only_full = false; int full; u64 now; @@ -1079,7 +1110,11 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) group->avg_next_update = update_averages(group, now); mutex_unlock(&group->avgs_lock); - for (full = 0; full < 2; full++) { +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + only_full = res == PSI_IRQ; +#endif + + for (full = 0; full < 2 - only_full; full++) { unsigned long avg[3] = { 0, }; u64 total = 0; int w; @@ -1093,7 +1128,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) } seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", - full ? "full" : "some", + full || only_full ? "full" : "some", LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), @@ -1121,6 +1156,11 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, else return ERR_PTR(-EINVAL); +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + if (res == PSI_IRQ && --state != PSI_IRQ_FULL) + return ERR_PTR(-EINVAL); +#endif + if (state >= PSI_NONIDLE) return ERR_PTR(-EINVAL); @@ -1405,6 +1445,33 @@ static const struct proc_ops psi_cpu_proc_ops = { .proc_release = psi_fop_release, }; +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +static int psi_irq_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IRQ); +} + +static int psi_irq_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_irq_show); +} + +static ssize_t psi_irq_write(struct file *file, const char __user *user_buf, + size_t nbytes, loff_t *ppos) +{ + return psi_write(file, user_buf, nbytes, PSI_IRQ); +} + +static const struct proc_ops psi_irq_proc_ops = { + .proc_open = psi_irq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = psi_irq_write, + .proc_poll = psi_fop_poll, + .proc_release = psi_fop_release, +}; +#endif + static int __init psi_proc_init(void) { if (psi_enable) { @@ -1412,6 +1479,9 @@ static int __init psi_proc_init(void) proc_create("pressure/io", 0666, NULL, &psi_io_proc_ops); proc_create("pressure/memory", 0666, NULL, &psi_memory_proc_ops); proc_create("pressure/cpu", 0666, NULL, &psi_cpu_proc_ops); +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + proc_create("pressure/irq", 0666, NULL, &psi_irq_proc_ops); +#endif } return 0; } diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index c39b467ece43..84a188913cc9 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -110,6 +110,7 @@ __schedstats_from_se(struct sched_entity *se) void psi_task_change(struct task_struct *task, int clear, int set); void psi_task_switch(struct task_struct *prev, struct task_struct *next, bool sleep); +void psi_account_irqtime(struct task_struct *task, u32 delta); /* * PSI tracks state that persists across sleeps, such as iowaits and @@ -205,6 +206,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) {} static inline void psi_sched_switch(struct task_struct *prev, struct task_struct *next, bool sleep) {} +static inline void psi_account_irqtime(struct task_struct *task, u32 delta) {} #endif /* CONFIG_PSI */ #ifdef CONFIG_SCHED_INFO -- cgit From 57899a6610e67ba26fa3251ebbef4a5ed21efc5d Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:09 +0800 Subject: sched/psi: Consolidate cgroup_psi() cgroup_psi() can't return psi_group for root cgroup, so we have many open code "psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi". This patch move cgroup_psi() definition to , in which we can return psi_system for root cgroup, so can handle all cgroups. Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-9-zhouchengming@bytedance.com --- include/linux/cgroup.h | 5 ----- include/linux/psi.h | 6 ++++++ kernel/cgroup/cgroup.c | 10 +++++----- 3 files changed, 11 insertions(+), 10 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b0914aa26506..80cb970257be 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -673,11 +673,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) -{ - return cgrp->psi; -} - bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) diff --git a/include/linux/psi.h b/include/linux/psi.h index fffd229fbf19..362a74ca1d3b 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -7,6 +7,7 @@ #include #include #include +#include struct seq_file; struct css_set; @@ -30,6 +31,11 @@ __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); #ifdef CONFIG_CGROUPS +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; +} + int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index b46d39b66214..772b35d65d1f 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3689,21 +3689,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v) static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_CPU); } @@ -3729,7 +3729,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return -EBUSY; } - psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res); if (IS_ERR(new)) { cgroup_put(cgrp); @@ -3767,7 +3767,7 @@ static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; + struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IRQ); } -- cgit From dc86aba751e2867244411adda1562f6664747019 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Fri, 26 Aug 2022 00:41:10 +0800 Subject: sched/psi: Cache parent psi_group to speed up group iteration We use iterate_groups() to iterate each level psi_group to update PSI stats, which is a very hot path. In current code, iterate_groups() have to use multiple branches and cgroup_parent() to get parent psi_group for each level, which is not very efficient. This patch cache parent psi_group in struct psi_group, only need to get psi_group of task itself first, then just use group->parent to iterate. Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20220825164111.29534-10-zhouchengming@bytedance.com --- include/linux/psi_types.h | 2 ++ kernel/sched/psi.c | 49 ++++++++++++++++++----------------------------- 2 files changed, 21 insertions(+), 30 deletions(-) diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 40c28171cd91..a0b746258c68 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -151,6 +151,8 @@ struct psi_trigger { }; struct psi_group { + struct psi_group *parent; + /* Protects data used by the aggregator */ struct mutex avgs_lock; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 2545a78f82d8..9a8aee80a087 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -772,27 +772,12 @@ static void psi_group_change(struct psi_group *group, int cpu, schedule_delayed_work(&group->avgs_work, PSI_FREQ); } -static struct psi_group *iterate_groups(struct task_struct *task, void **iter) +static inline struct psi_group *task_psi_group(struct task_struct *task) { - if (*iter == &psi_system) - return NULL; - #ifdef CONFIG_CGROUPS - if (static_branch_likely(&psi_cgroups_enabled)) { - struct cgroup *cgroup = NULL; - - if (!*iter) - cgroup = task->cgroups->dfl_cgrp; - else - cgroup = cgroup_parent(*iter); - - if (cgroup && cgroup_parent(cgroup)) { - *iter = cgroup; - return cgroup_psi(cgroup); - } - } + if (static_branch_likely(&psi_cgroups_enabled)) + return cgroup_psi(task_dfl_cgroup(task)); #endif - *iter = &psi_system; return &psi_system; } @@ -815,7 +800,6 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; - void *iter = NULL; u64 now; if (!task->pid) @@ -825,8 +809,10 @@ void psi_task_change(struct task_struct *task, int clear, int set) now = cpu_clock(cpu); - while ((group = iterate_groups(task, &iter))) + group = task_psi_group(task); + do { psi_group_change(group, cpu, clear, set, now, true); + } while ((group = group->parent)); } void psi_task_switch(struct task_struct *prev, struct task_struct *next, @@ -834,7 +820,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, { struct psi_group *group, *common = NULL; int cpu = task_cpu(prev); - void *iter; u64 now = cpu_clock(cpu); if (next->pid) { @@ -844,8 +829,8 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, * ancestors with @prev, those will already have @prev's * TSK_ONCPU bit set, and we can stop the iteration there. */ - iter = NULL; - while ((group = iterate_groups(next, &iter))) { + group = task_psi_group(next); + do { if (per_cpu_ptr(group->pcpu, cpu)->state_mask & PSI_ONCPU) { common = group; @@ -853,7 +838,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, } psi_group_change(group, cpu, 0, TSK_ONCPU, now, true); - } + } while ((group = group->parent)); } if (prev->pid) { @@ -886,9 +871,12 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, psi_flags_change(prev, clear, set); - iter = NULL; - while ((group = iterate_groups(prev, &iter)) && group != common) + group = task_psi_group(prev); + do { + if (group == common) + break; psi_group_change(group, cpu, clear, set, now, wake_clock); + } while ((group = group->parent)); /* * TSK_ONCPU is handled up to the common ancestor. If there are @@ -898,7 +886,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, */ if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) { clear &= ~TSK_ONCPU; - for (; group; group = iterate_groups(prev, &iter)) + for (; group; group = group->parent) psi_group_change(group, cpu, clear, set, now, wake_clock); } } @@ -908,7 +896,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, void psi_account_irqtime(struct task_struct *task, u32 delta) { int cpu = task_cpu(task); - void *iter = NULL; struct psi_group *group; struct psi_group_cpu *groupc; u64 now; @@ -918,7 +905,8 @@ void psi_account_irqtime(struct task_struct *task, u32 delta) now = cpu_clock(cpu); - while ((group = iterate_groups(task, &iter))) { + group = task_psi_group(task); + do { groupc = per_cpu_ptr(group->pcpu, cpu); write_seqcount_begin(&groupc->seq); @@ -930,7 +918,7 @@ void psi_account_irqtime(struct task_struct *task, u32 delta) if (group->poll_states & (1 << PSI_IRQ_FULL)) psi_schedule_poll_work(group, 1); - } + } while ((group = group->parent)); } #endif @@ -1010,6 +998,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) return -ENOMEM; } group_init(cgroup->psi); + cgroup->psi->parent = cgroup_psi(cgroup_parent(cgroup)); return 0; } -- cgit From 34f26a15611afb03c33df6819359d36f5b382589 Mon Sep 17 00:00:00 2001 From: Chengming Zhou Date: Wed, 7 Sep 2022 17:03:32 +0800 Subject: sched/psi: Per-cgroup PSI accounting disable/re-enable interface PSI accounts stalls for each cgroup separately and aggregates it at each level of the hierarchy. This may cause non-negligible overhead for some workloads when under deep level of the hierarchy. commit 3958e2d0c34e ("cgroup: make per-cgroup pressure stall tracking configurable") make PSI to skip per-cgroup stall accounting, only account system-wide to avoid this each level overhead. But for our use case, we also want leaf cgroup PSI stats accounted for userspace adjustment on that cgroup, apart from only system-wide adjustment. So this patch introduce a per-cgroup PSI accounting disable/re-enable interface "cgroup.pressure", which is a read-write single value file that allowed values are "0" and "1", the defaults is "1" so per-cgroup PSI stats is enabled by default. Implementation details: It should be relatively straight-forward to disable and re-enable state aggregation, time tracking, averaging on a per-cgroup level, if we can live with losing history from while it was disabled. I.e. the avgs will restart from 0, total= will have gaps. But it's hard or complex to stop/restart groupc->tasks[] updates, which is not implemented in this patch. So we always update groupc->tasks[] and PSI_ONCPU bit in psi_group_change() even when the cgroup PSI stats is disabled. Suggested-by: Johannes Weiner Suggested-by: Tejun Heo Signed-off-by: Chengming Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lkml.kernel.org/r/20220907090332.2078-1-zhouchengming@bytedance.com --- Documentation/admin-guide/cgroup-v2.rst | 17 ++++++++ include/linux/cgroup-defs.h | 3 ++ include/linux/psi.h | 2 + include/linux/psi_types.h | 3 ++ kernel/cgroup/cgroup.c | 70 ++++++++++++++++++++++++++++++--- kernel/sched/psi.c | 70 +++++++++++++++++++++++++++++---- 6 files changed, 152 insertions(+), 13 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 971c418bc778..4cad4e2b31ec 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -976,6 +976,23 @@ All cgroup core files are prefixed with "cgroup." killing cgroups is a process directed operation, i.e. it affects the whole thread-group. + cgroup.pressure + A read-write single value file that allowed values are "0" and "1". + The default is "1". + + Writing "0" to the file will disable the cgroup PSI accounting. + Writing "1" to the file will re-enable the cgroup PSI accounting. + + This control attribute is not hierarchical, so disable or enable PSI + accounting in a cgroup does not affect PSI accounting in descendants + and doesn't need pass enablement via ancestors from root. + + The reason this control attribute exists is that PSI accounts stalls for + each cgroup separately and aggregates it at each level of the hierarchy. + This may cause non-negligible overhead for some workloads when under + deep level of the hierarchy, in which case this control attribute can + be used to disable PSI accounting in the non-leaf cgroups. + irq.pressure A read-write nested-keyed file. diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4bcf56b3491c..7df76b318245 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -428,6 +428,9 @@ struct cgroup { struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ + /* handles for "{cpu,memory,io,irq}.pressure" */ + struct cgroup_file psi_files[NR_PSI_RESOURCES]; + /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through diff --git a/include/linux/psi.h b/include/linux/psi.h index 362a74ca1d3b..b029a847def1 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -39,6 +39,7 @@ static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) int psi_cgroup_alloc(struct cgroup *cgrp); void psi_cgroup_free(struct cgroup *cgrp); void cgroup_move_task(struct task_struct *p, struct css_set *to); +void psi_cgroup_restart(struct psi_group *group); #endif #else /* CONFIG_PSI */ @@ -60,6 +61,7 @@ static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) { rcu_assign_pointer(p->cgroups, to); } +static inline void psi_cgroup_restart(struct psi_group *group) {} #endif #endif /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index a0b746258c68..6e4372735068 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -152,6 +152,7 @@ struct psi_trigger { struct psi_group { struct psi_group *parent; + bool enabled; /* Protects data used by the aggregator */ struct mutex avgs_lock; @@ -194,6 +195,8 @@ struct psi_group { #else /* CONFIG_PSI */ +#define NR_PSI_RESOURCES 0 + struct psi_group { }; #endif /* CONFIG_PSI */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 772b35d65d1f..fa1cf836b66a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3708,8 +3708,8 @@ static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) return psi_show(seq, psi, PSI_CPU); } -static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, - size_t nbytes, enum psi_res res) +static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, enum psi_res res) { struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; @@ -3746,21 +3746,21 @@ static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_IO); + return pressure_write(of, buf, nbytes, PSI_IO); } static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_MEM); + return pressure_write(of, buf, nbytes, PSI_MEM); } static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_CPU); + return pressure_write(of, buf, nbytes, PSI_CPU); } #ifdef CONFIG_IRQ_TIME_ACCOUNTING @@ -3776,10 +3776,58 @@ static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - return cgroup_pressure_write(of, buf, nbytes, PSI_IRQ); + return pressure_write(of, buf, nbytes, PSI_IRQ); } #endif +static int cgroup_pressure_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + struct psi_group *psi = cgroup_psi(cgrp); + + seq_printf(seq, "%d\n", psi->enabled); + + return 0; +} + +static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + ssize_t ret; + int enable; + struct cgroup *cgrp; + struct psi_group *psi; + + ret = kstrtoint(strstrip(buf), 0, &enable); + if (ret) + return ret; + + if (enable < 0 || enable > 1) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + psi = cgroup_psi(cgrp); + if (psi->enabled != enable) { + int i; + + /* show or hide {cpu,memory,io,irq}.pressure files */ + for (i = 0; i < NR_PSI_RESOURCES; i++) + cgroup_file_show(&cgrp->psi_files[i], enable); + + psi->enabled = enable; + if (enable) + psi_cgroup_restart(psi); + } + + cgroup_kn_unlock(of->kn); + + return nbytes; +} + static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { @@ -5175,6 +5223,7 @@ static struct cftype cgroup_base_files[] = { { .name = "io.pressure", .flags = CFTYPE_PRESSURE, + .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, @@ -5183,6 +5232,7 @@ static struct cftype cgroup_base_files[] = { { .name = "memory.pressure", .flags = CFTYPE_PRESSURE, + .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, @@ -5191,6 +5241,7 @@ static struct cftype cgroup_base_files[] = { { .name = "cpu.pressure", .flags = CFTYPE_PRESSURE, + .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, @@ -5200,12 +5251,19 @@ static struct cftype cgroup_base_files[] = { { .name = "irq.pressure", .flags = CFTYPE_PRESSURE, + .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #endif + { + .name = "cgroup.pressure", + .flags = CFTYPE_PRESSURE, + .seq_show = cgroup_pressure_show, + .write = cgroup_pressure_write, + }, #endif /* CONFIG_PSI */ { } /* terminate */ }; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 9a8aee80a087..9711827e31e5 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -181,6 +181,7 @@ static void group_init(struct psi_group *group) { int cpu; + group->enabled = true; for_each_possible_cpu(cpu) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); group->avg_last_update = sched_clock(); @@ -696,17 +697,16 @@ static void psi_group_change(struct psi_group *group, int cpu, groupc = per_cpu_ptr(group->pcpu, cpu); /* - * First we assess the aggregate resource states this CPU's - * tasks have been in since the last change, and account any - * SOME and FULL time these may have resulted in. - * - * Then we update the task counts according to the state + * First we update the task counts according to the state * change requested through the @clear and @set bits. + * + * Then if the cgroup PSI stats accounting enabled, we + * assess the aggregate resource states this CPU's tasks + * have been in since the last change, and account any + * SOME and FULL time these may have resulted in. */ write_seqcount_begin(&groupc->seq); - record_times(groupc, now); - /* * Start with TSK_ONCPU, which doesn't have a corresponding * task count - it's just a boolean flag directly encoded in @@ -745,6 +745,23 @@ static void psi_group_change(struct psi_group *group, int cpu, if (set & (1 << t)) groupc->tasks[t]++; + if (!group->enabled) { + /* + * On the first group change after disabling PSI, conclude + * the current state and flush its time. This is unlikely + * to matter to the user, but aggregation (get_recent_times) + * may have already incorporated the live state into times_prev; + * avoid a delta sample underflow when PSI is later re-enabled. + */ + if (unlikely(groupc->state_mask & (1 << PSI_NONIDLE))) + record_times(groupc, now); + + groupc->state_mask = state_mask; + + write_seqcount_end(&groupc->seq); + return; + } + for (s = 0; s < NR_PSI_STATES; s++) { if (test_state(groupc->tasks, s, state_mask & PSI_ONCPU)) state_mask |= (1 << s); @@ -761,6 +778,8 @@ static void psi_group_change(struct psi_group *group, int cpu, if (unlikely((state_mask & PSI_ONCPU) && cpu_curr(cpu)->in_memstall)) state_mask |= (1 << PSI_MEM_FULL); + record_times(groupc, now); + groupc->state_mask = state_mask; write_seqcount_end(&groupc->seq); @@ -907,6 +926,9 @@ void psi_account_irqtime(struct task_struct *task, u32 delta) group = task_psi_group(task); do { + if (!group->enabled) + continue; + groupc = per_cpu_ptr(group->pcpu, cpu); write_seqcount_begin(&groupc->seq); @@ -1080,6 +1102,40 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) task_rq_unlock(rq, task, &rf); } + +void psi_cgroup_restart(struct psi_group *group) +{ + int cpu; + + /* + * After we disable psi_group->enabled, we don't actually + * stop percpu tasks accounting in each psi_group_cpu, + * instead only stop test_state() loop, record_times() + * and averaging worker, see psi_group_change() for details. + * + * When disable cgroup PSI, this function has nothing to sync + * since cgroup pressure files are hidden and percpu psi_group_cpu + * would see !psi_group->enabled and only do task accounting. + * + * When re-enable cgroup PSI, this function use psi_group_change() + * to get correct state mask from test_state() loop on tasks[], + * and restart groupc->state_start from now, use .clear = .set = 0 + * here since no task status really changed. + */ + if (!group->enabled) + return; + + for_each_possible_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + struct rq_flags rf; + u64 now; + + rq_lock_irq(rq, &rf); + now = cpu_clock(cpu); + psi_group_change(group, cpu, 0, 0, now, true); + rq_unlock_irq(rq, &rf); + } +} #endif /* CONFIG_CGROUPS */ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) -- cgit From aac00c7fa1149fd5b5a5110096ffa78dcb120b79 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:06 +0200 Subject: clk: test: Switch to clk_hw_get_clk Following the clk_hw->clk pointer is equivalent to calling clk_hw_get_clk(), but will make the job harder if we need to rework that part in the future. Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-2-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk_test.c | 74 +++++++++++++++++++++++++++++++++++++------------- 1 file changed, 55 insertions(+), 19 deletions(-) diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 6731a822f4e3..7646356f30cb 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -160,12 +160,14 @@ static void clk_test_get_rate(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, ctx->rate); + + clk_put(clk); } /* @@ -179,7 +181,7 @@ static void clk_test_set_get_rate(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -189,6 +191,8 @@ static void clk_test_set_get_rate(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(clk); } /* @@ -202,7 +206,7 @@ static void clk_test_set_set_get_rate(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -216,6 +220,8 @@ static void clk_test_set_set_get_rate(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -226,7 +232,7 @@ static void clk_test_round_set_get_rate(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rounded_rate, set_rate; rounded_rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1); @@ -240,6 +246,8 @@ static void clk_test_round_set_get_rate(struct kunit *test) set_rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, set_rate, 0); KUNIT_EXPECT_EQ(test, rounded_rate, set_rate); + + clk_put(clk); } static struct kunit_case clk_test_cases[] = { @@ -314,7 +322,7 @@ static void clk_test_orphan_transparent_parent_mux_set_range(struct kunit *test) { struct clk_single_parent_ctx *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate, new_rate; rate = clk_get_rate(clk); @@ -329,6 +337,8 @@ static void clk_test_orphan_transparent_parent_mux_set_range(struct kunit *test) new_rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, new_rate, 0); KUNIT_EXPECT_EQ(test, rate, new_rate); + + clk_put(clk); } static struct kunit_case clk_orphan_transparent_single_parent_mux_test_cases[] = { @@ -352,7 +362,7 @@ static void clk_range_test_set_range(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -365,6 +375,8 @@ static void clk_range_test_set_range(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -375,13 +387,15 @@ static void clk_range_test_set_range_invalid(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); KUNIT_EXPECT_LT(test, clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1 + 1000, DUMMY_CLOCK_RATE_1), 0); + + clk_put(clk); } /* @@ -420,7 +434,7 @@ static void clk_range_test_set_range_round_rate_lower(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); long rate; KUNIT_ASSERT_EQ(test, @@ -433,6 +447,8 @@ static void clk_range_test_set_range_round_rate_lower(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -443,7 +459,7 @@ static void clk_range_test_set_range_set_rate_lower(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -460,6 +476,8 @@ static void clk_range_test_set_range_set_rate_lower(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -472,7 +490,7 @@ static void clk_range_test_set_range_set_round_rate_consistent_lower(struct kuni { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); long rounded; KUNIT_ASSERT_EQ(test, @@ -489,6 +507,8 @@ static void clk_range_test_set_range_set_round_rate_consistent_lower(struct kuni 0); KUNIT_EXPECT_EQ(test, rounded, clk_get_rate(clk)); + + clk_put(clk); } /* @@ -499,7 +519,7 @@ static void clk_range_test_set_range_round_rate_higher(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); long rate; KUNIT_ASSERT_EQ(test, @@ -512,6 +532,8 @@ static void clk_range_test_set_range_round_rate_higher(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -522,7 +544,7 @@ static void clk_range_test_set_range_set_rate_higher(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -539,6 +561,8 @@ static void clk_range_test_set_range_set_rate_higher(struct kunit *test) KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -551,7 +575,7 @@ static void clk_range_test_set_range_set_round_rate_consistent_higher(struct kun { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); long rounded; KUNIT_ASSERT_EQ(test, @@ -568,6 +592,8 @@ static void clk_range_test_set_range_set_round_rate_consistent_higher(struct kun 0); KUNIT_EXPECT_EQ(test, rounded, clk_get_rate(clk)); + + clk_put(clk); } /* @@ -582,7 +608,7 @@ static void clk_range_test_set_range_get_rate_raised(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -598,6 +624,8 @@ static void clk_range_test_set_range_get_rate_raised(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(clk); } /* @@ -612,7 +640,7 @@ static void clk_range_test_set_range_get_rate_lowered(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -628,6 +656,8 @@ static void clk_range_test_set_range_get_rate_lowered(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } static struct kunit_case clk_range_test_cases[] = { @@ -664,7 +694,7 @@ static void clk_range_test_set_range_rate_maximized(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -700,6 +730,8 @@ static void clk_range_test_set_range_rate_maximized(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); } /* @@ -714,7 +746,7 @@ static void clk_range_test_multiple_set_range_rate_maximized(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); struct clk *user1, *user2; unsigned long rate; @@ -758,6 +790,7 @@ static void clk_range_test_multiple_set_range_rate_maximized(struct kunit *test) clk_put(user2); clk_put(user1); + clk_put(clk); } static struct kunit_case clk_range_maximize_test_cases[] = { @@ -785,7 +818,7 @@ static void clk_range_test_set_range_rate_minimized(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); unsigned long rate; KUNIT_ASSERT_EQ(test, @@ -821,6 +854,8 @@ static void clk_range_test_set_range_rate_minimized(struct kunit *test) rate = clk_get_rate(clk); KUNIT_ASSERT_GT(test, rate, 0); KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(clk); } /* @@ -835,7 +870,7 @@ static void clk_range_test_multiple_set_range_rate_minimized(struct kunit *test) { struct clk_dummy_context *ctx = test->priv; struct clk_hw *hw = &ctx->hw; - struct clk *clk = hw->clk; + struct clk *clk = clk_hw_get_clk(hw, NULL); struct clk *user1, *user2; unsigned long rate; @@ -875,6 +910,7 @@ static void clk_range_test_multiple_set_range_rate_minimized(struct kunit *test) clk_put(user2); clk_put(user1); + clk_put(clk); } static struct kunit_case clk_range_minimize_test_cases[] = { -- cgit From d77388223240884b918b8d85f88f132916afbf06 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:07 +0200 Subject: clk: Drop the rate range on clk_put() When clk_put() is called we don't make another clk_set_rate() call to re-evaluate the rate boundaries. This is unlike clk_set_rate_range() that evaluates the rate again each time it is called. However, clk_put() is essentially equivalent to clk_set_rate_range() since after clk_put() completes the consumer's boundaries shouldn't be enforced anymore. Let's add a call to clk_set_rate_range() in clk_put() to make sure those rate boundaries are dropped and the clock provider drivers can react. In order to be as non-intrusive as possible, we'll just make that call if the clock had non-default boundaries. Also add a few tests to make sure this case is covered. Fixes: c80ac50cbb37 ("clk: Always set the rate on clk_set_range_rate") Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-3-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 45 +++++++++++++------- drivers/clk/clk_test.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 141 insertions(+), 14 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 7fc191c15507..a5e0ab8bd6be 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -2325,19 +2325,15 @@ int clk_set_rate_exclusive(struct clk *clk, unsigned long rate) } EXPORT_SYMBOL_GPL(clk_set_rate_exclusive); -/** - * clk_set_rate_range - set a rate range for a clock source - * @clk: clock source - * @min: desired minimum clock rate in Hz, inclusive - * @max: desired maximum clock rate in Hz, inclusive - * - * Returns success (0) or negative errno. - */ -int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) +static int clk_set_rate_range_nolock(struct clk *clk, + unsigned long min, + unsigned long max) { int ret = 0; unsigned long old_min, old_max, rate; + lockdep_assert_held(&prepare_lock); + if (!clk) return 0; @@ -2350,8 +2346,6 @@ int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) return -EINVAL; } - clk_prepare_lock(); - if (clk->exclusive_count) clk_core_rate_unprotect(clk->core); @@ -2395,6 +2389,28 @@ out: if (clk->exclusive_count) clk_core_rate_protect(clk->core); + return ret; +} + +/** + * clk_set_rate_range - set a rate range for a clock source + * @clk: clock source + * @min: desired minimum clock rate in Hz, inclusive + * @max: desired maximum clock rate in Hz, inclusive + * + * Return: 0 for success or negative errno on failure. + */ +int clk_set_rate_range(struct clk *clk, unsigned long min, unsigned long max) +{ + int ret; + + if (!clk) + return 0; + + clk_prepare_lock(); + + ret = clk_set_rate_range_nolock(clk, min, max); + clk_prepare_unlock(); return ret; @@ -4348,9 +4364,10 @@ void __clk_put(struct clk *clk) } hlist_del(&clk->clks_node); - if (clk->min_rate > clk->core->req_rate || - clk->max_rate < clk->core->req_rate) - clk_core_set_rate_nolock(clk->core, clk->core->req_rate); + + /* If we had any boundaries on that clock, let's drop them. */ + if (clk->min_rate > 0 || clk->max_rate < ULONG_MAX) + clk_set_rate_range_nolock(clk, 0, ULONG_MAX); owner = clk->core->owner; kref_put(&clk->core->ref, __clk_release); diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 7646356f30cb..7d9da88c39ee 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -793,9 +793,66 @@ static void clk_range_test_multiple_set_range_rate_maximized(struct kunit *test) clk_put(clk); } +/* + * Test that if we have several subsequent calls to + * clk_set_rate_range(), across multiple users, the core will reevaluate + * whether a new rate is needed, including when a user drop its clock. + * + * With clk_dummy_maximize_rate_ops, this means that the rate will + * trail along the maximum as it evolves. + */ +static void clk_range_test_multiple_set_range_rate_put_maximized(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *user1, *user2; + unsigned long rate; + + user1 = clk_hw_get_clk(hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user1); + + user2 = clk_hw_get_clk(hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user2); + + KUNIT_ASSERT_EQ(test, + clk_set_rate(clk, DUMMY_CLOCK_RATE_2 + 1000), + 0); + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(user1, + 0, + DUMMY_CLOCK_RATE_2), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(user2, + 0, + DUMMY_CLOCK_RATE_1), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(user2); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(user1); + clk_put(clk); +} + static struct kunit_case clk_range_maximize_test_cases[] = { KUNIT_CASE(clk_range_test_set_range_rate_maximized), KUNIT_CASE(clk_range_test_multiple_set_range_rate_maximized), + KUNIT_CASE(clk_range_test_multiple_set_range_rate_put_maximized), {} }; @@ -913,9 +970,62 @@ static void clk_range_test_multiple_set_range_rate_minimized(struct kunit *test) clk_put(clk); } +/* + * Test that if we have several subsequent calls to + * clk_set_rate_range(), across multiple users, the core will reevaluate + * whether a new rate is needed, including when a user drop its clock. + * + * With clk_dummy_minimize_rate_ops, this means that the rate will + * trail along the minimum as it evolves. + */ +static void clk_range_test_multiple_set_range_rate_put_minimized(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *user1, *user2; + unsigned long rate; + + user1 = clk_hw_get_clk(hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user1); + + user2 = clk_hw_get_clk(hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, user2); + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(user1, + DUMMY_CLOCK_RATE_1, + ULONG_MAX), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(user2, + DUMMY_CLOCK_RATE_2, + ULONG_MAX), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(user2); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(user1); + clk_put(clk); +} + static struct kunit_case clk_range_minimize_test_cases[] = { KUNIT_CASE(clk_range_test_set_range_rate_minimized), KUNIT_CASE(clk_range_test_multiple_set_range_rate_minimized), + KUNIT_CASE(clk_range_test_multiple_set_range_rate_put_minimized), {} }; -- cgit From facf949b2e6934d381050417bf4e34b20c93be09 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:08 +0200 Subject: clk: Skip clamping when rounding if there's no boundaries Commit 948fb0969eae ("clk: Always clamp the rounded rate") recently started to clamp the request rate in the clk_rate_request passed as an argument of clk_core_determine_round_nolock() with the min_rate and max_rate fields of that same request. While the clk_rate_requests created by the framework itself always have those fields set, some drivers will create it themselves and don't always fill min_rate and max_rate. In such a case, we end up clamping the rate with a minimum and maximum of 0, thus always rounding the rate to 0. Let's skip the clamping if both min_rate and max_rate are set to 0 and complain so that it gets fixed. Fixes: 948fb0969eae ("clk: Always clamp the rounded rate") Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-4-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index a5e0ab8bd6be..9d63163244d4 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1341,7 +1341,19 @@ static int clk_core_determine_round_nolock(struct clk_core *core, if (!core) return 0; - req->rate = clamp(req->rate, req->min_rate, req->max_rate); + /* + * Some clock providers hand-craft their clk_rate_requests and + * might not fill min_rate and max_rate. + * + * If it's the case, clamping the rate is equivalent to setting + * the rate to 0 which is bad. Skip the clamping but complain so + * that it gets fixed, hopefully. + */ + if (!req->min_rate && !req->max_rate) + pr_warn("%s: %s: clk_rate_request has initialized min or max rate.\n", + __func__, core->name); + else + req->rate = clamp(req->rate, req->min_rate, req->max_rate); /* * At this point, core protection will be disabled -- cgit From f24a0b1c22c2e90abb4ee1f7a3b0f0d8fc2ede5f Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:09 +0200 Subject: clk: Mention that .recalc_rate can return 0 on error Multiple platforms (amlogic, imx8) return 0 when the clock rate cannot be determined properly by the recalc_rate hook. Mention in the documentation that the framework is ok with that. Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-5-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 1615010aa0ec..9a14cfa0d201 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -118,8 +118,9 @@ struct clk_duty { * * @recalc_rate Recalculate the rate of this clock, by querying hardware. The * parent rate is an input parameter. It is up to the caller to - * ensure that the prepare_mutex is held across this call. - * Returns the calculated rate. Optional, but recommended - if + * ensure that the prepare_mutex is held across this call. If the + * driver cannot figure out a rate for this clock, it must return + * 0. Returns the calculated rate. Optional, but recommended - if * this op is not set then clock rate will be initialized to 0. * * @round_rate: Given a target rate as input, returns the closest rate actually -- cgit From bde8870cd8c3a3913ddbc19f8422a21828e14d99 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:10 +0200 Subject: clk: Clarify clk_get_rate() expectations As shown by a number of clock users already, clk_get_rate() can be called whether or not the clock is enabled. Similarly, a number of clock drivers will return a rate of 0 whenever the rate cannot be figured out. Since it was a bit ambiguous before, let's make it clear in the clk_get_rate() documentation. Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-6-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 9d63163244d4..caa2eb640441 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1672,8 +1672,9 @@ static unsigned long clk_core_get_rate_recalc(struct clk_core *core) * @clk: the clk whose rate is being returned * * Simply returns the cached rate of the clk, unless CLK_GET_RATE_NOCACHE flag - * is set, which means a recalc_rate will be issued. - * If clk is NULL then returns 0. + * is set, which means a recalc_rate will be issued. Can be called regardless of + * the clock enabledness. If clk is NULL, or if an error occurred, then returns + * 0. */ unsigned long clk_get_rate(struct clk *clk) { -- cgit From 090962b6a90a2bf81142f6d5da9492380d5fba08 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:11 +0200 Subject: clk: tests: Add test suites description We start to have a few test suites, and we'll add more, so it will get pretty confusing to figure out what is supposed to be tested in what suite. Let's add some comments to explain what setup they create, and what we should be testing in every suite. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-7-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk_test.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 7d9da88c39ee..1a7cb482ec58 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -258,6 +258,11 @@ static struct kunit_case clk_test_cases[] = { {} }; +/* + * Test suite for a basic rate clock, without any parent. + * + * These tests exercise the rate API with simple scenarios + */ static struct kunit_suite clk_test_suite = { .name = "clk-test", .init = clk_test_init, @@ -346,6 +351,14 @@ static struct kunit_case clk_orphan_transparent_single_parent_mux_test_cases[] = {} }; +/* + * Test suite for a basic mux clock with one parent. The parent is + * registered after its child. The clock will thus be an orphan when + * registered, but will no longer be when the tests run. + * + * These tests make sure a clock that used to be orphan has a sane, + * consistent, behaviour. + */ static struct kunit_suite clk_orphan_transparent_single_parent_test_suite = { .name = "clk-orphan-transparent-single-parent-test", .init = clk_orphan_transparent_single_parent_mux_test_init, @@ -675,6 +688,12 @@ static struct kunit_case clk_range_test_cases[] = { {} }; +/* + * Test suite for a basic rate clock, without any parent. + * + * These tests exercise the rate range API: clk_set_rate_range(), + * clk_set_min_rate(), clk_set_max_rate(), clk_drop_range(). + */ static struct kunit_suite clk_range_test_suite = { .name = "clk-range-test", .init = clk_test_init, @@ -856,6 +875,13 @@ static struct kunit_case clk_range_maximize_test_cases[] = { {} }; +/* + * Test suite for a basic rate clock, without any parent. + * + * These tests exercise the rate range API: clk_set_rate_range(), + * clk_set_min_rate(), clk_set_max_rate(), clk_drop_range(), with a + * driver that will always try to run at the highest possible rate. + */ static struct kunit_suite clk_range_maximize_test_suite = { .name = "clk-range-maximize-test", .init = clk_maximize_test_init, @@ -1029,6 +1055,13 @@ static struct kunit_case clk_range_minimize_test_cases[] = { {} }; +/* + * Test suite for a basic rate clock, without any parent. + * + * These tests exercise the rate range API: clk_set_rate_range(), + * clk_set_min_rate(), clk_set_max_rate(), clk_drop_range(), with a + * driver that will always try to run at the lowest possible rate. + */ static struct kunit_suite clk_range_minimize_test_suite = { .name = "clk-range-minimize-test", .init = clk_minimize_test_init, -- cgit From 7d79c26b60e623a9a089d771f81c5997bda577cd Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:12 +0200 Subject: clk: tests: Add reference to the orphan mux bug report Some more context might be useful for unit-tests covering a previously reported bug, so let's add a link to the discussion for that bug. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-8-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk_test.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 1a7cb482ec58..b8e32406a6e4 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -322,6 +322,9 @@ static void clk_orphan_transparent_single_parent_mux_test_exit(struct kunit *tes /* * Test that a mux-only clock, with an initial rate within a range, * will still have the same rate after the range has been enforced. + * + * See: + * https://lore.kernel.org/linux-clk/7720158d-10a7-a17b-73a4-a8615c9c6d5c@collabora.com/ */ static void clk_test_orphan_transparent_parent_mux_set_range(struct kunit *test) { -- cgit From 350575abec48ef5363abd832386cb5a33861cb10 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:13 +0200 Subject: clk: tests: Add tests for uncached clock The clock framework supports clocks that can have their rate changed without the kernel knowing about it using the CLK_GET_RATE_NOCACHE flag. As its name suggests, this flag turns off the rate caching in the clock framework, reading out the rate from the hardware any time we need to read it. Let's add a couple of tests to make sure it works as intended. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-9-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk_test.c | 93 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 92 insertions(+), 1 deletion(-) diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index b8e32406a6e4..b269420dafcc 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -270,6 +270,96 @@ static struct kunit_suite clk_test_suite = { .test_cases = clk_test_cases, }; +static int clk_uncached_test_init(struct kunit *test) +{ + struct clk_dummy_context *ctx; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->rate = DUMMY_CLOCK_INIT_RATE; + ctx->hw.init = CLK_HW_INIT_NO_PARENT("test-clk", + &clk_dummy_rate_ops, + CLK_GET_RATE_NOCACHE); + + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +/* + * Test that for an uncached clock, the clock framework doesn't cache + * the rate and clk_get_rate() will return the underlying clock rate + * even if it changed. + */ +static void clk_test_uncached_get_rate(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_INIT_RATE); + + /* We change the rate behind the clock framework's back */ + ctx->rate = DUMMY_CLOCK_RATE_1; + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_put(clk); +} + +/* + * Test that for an uncached clock, clk_set_rate_range() will work + * properly if the rate hasn't changed. + */ +static void clk_test_uncached_set_range(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(clk, + DUMMY_CLOCK_RATE_1, + DUMMY_CLOCK_RATE_2), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); +} + +static struct kunit_case clk_uncached_test_cases[] = { + KUNIT_CASE(clk_test_uncached_get_rate), + KUNIT_CASE(clk_test_uncached_set_range), + {} +}; + +/* + * Test suite for a basic, uncached, rate clock, without any parent. + * + * These tests exercise the rate API with simple scenarios + */ +static struct kunit_suite clk_uncached_test_suite = { + .name = "clk-uncached-test", + .init = clk_uncached_test_init, + .exit = clk_test_exit, + .test_cases = clk_uncached_test_cases, +}; + struct clk_single_parent_ctx { struct clk_dummy_context parent_ctx; struct clk_hw hw; @@ -1077,6 +1167,7 @@ kunit_test_suites( &clk_orphan_transparent_single_parent_test_suite, &clk_range_test_suite, &clk_range_maximize_test_suite, - &clk_range_minimize_test_suite + &clk_range_minimize_test_suite, + &clk_uncached_test_suite ); MODULE_LICENSE("GPL v2"); -- cgit From 02cdeace1e1ed210eb9fc2ce562d93580b1dcfe5 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:14 +0200 Subject: clk: tests: Add tests for single parent mux We have a few tests for a mux with a single parent, testing the case where it used to be orphan. Let's leverage most of the code but register the clock properly to test a few trivial things. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-10-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk_test.c | 194 ++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 185 insertions(+), 9 deletions(-) diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index b269420dafcc..06c9220873bb 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -365,6 +365,189 @@ struct clk_single_parent_ctx { struct clk_hw hw; }; +static int clk_single_parent_mux_test_init(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->parent_ctx.rate = DUMMY_CLOCK_INIT_RATE; + ctx->parent_ctx.hw.init = + CLK_HW_INIT_NO_PARENT("parent-clk", + &clk_dummy_rate_ops, + 0); + + ret = clk_hw_register(NULL, &ctx->parent_ctx.hw); + if (ret) + return ret; + + ctx->hw.init = CLK_HW_INIT("test-clk", "parent-clk", + &clk_dummy_single_parent_ops, + CLK_SET_RATE_PARENT); + + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +static void +clk_single_parent_mux_test_exit(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->parent_ctx.hw); +} + +/* + * Test that for a clock with a single parent, clk_get_parent() actually + * returns the parent. + */ +static void +clk_test_single_parent_mux_get_parent(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent = clk_hw_get_clk(&ctx->parent_ctx.hw, NULL); + + KUNIT_EXPECT_TRUE(test, clk_is_match(clk_get_parent(clk), parent)); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set disjoints range on the parent and then the child, + * the second will return an error. + * + * FIXME: clk_set_rate_range() only considers the current clock when + * evaluating whether ranges are disjoints and not the upstream clocks + * ranges. + */ +static void +clk_test_single_parent_mux_set_range_disjoint_child_last(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + int ret; + + kunit_skip(test, "This needs to be fixed in the core."); + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(parent, 1000, 2000); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, 3000, 4000); + KUNIT_EXPECT_LT(test, ret, 0); + + clk_put(clk); +} + +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set disjoints range on the child and then the parent, + * the second will return an error. + * + * FIXME: clk_set_rate_range() only considers the current clock when + * evaluating whether ranges are disjoints and not the downstream clocks + * ranges. + */ +static void +clk_test_single_parent_mux_set_range_disjoint_parent_last(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + int ret; + + kunit_skip(test, "This needs to be fixed in the core."); + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(clk, 1000, 2000); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(parent, 3000, 4000); + KUNIT_EXPECT_LT(test, ret, 0); + + clk_put(clk); +} + +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set a range on the parent and a more restrictive one on + * the child, and then call clk_round_rate(), the boundaries of the + * two clocks are taken into account. + */ +static void +clk_test_single_parent_mux_set_range_round_rate_child_smaller(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(parent, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1 + 1000, DUMMY_CLOCK_RATE_2 - 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2 - 1000); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_2 + 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2 - 1000); + + clk_put(clk); +} + +static struct kunit_case clk_single_parent_mux_test_cases[] = { + KUNIT_CASE(clk_test_single_parent_mux_get_parent), + KUNIT_CASE(clk_test_single_parent_mux_set_range_disjoint_child_last), + KUNIT_CASE(clk_test_single_parent_mux_set_range_disjoint_parent_last), + KUNIT_CASE(clk_test_single_parent_mux_set_range_round_rate_child_smaller), + {} +}; + +/* + * Test suite for a basic mux clock with one parent, with + * CLK_SET_RATE_PARENT on the child. + * + * These tests exercise the consumer API and check that the state of the + * child and parent are sane and consistent. + */ +static struct kunit_suite +clk_single_parent_mux_test_suite = { + .name = "clk-single-parent-mux-test", + .init = clk_single_parent_mux_test_init, + .exit = clk_single_parent_mux_test_exit, + .test_cases = clk_single_parent_mux_test_cases, +}; + static int clk_orphan_transparent_single_parent_mux_test_init(struct kunit *test) { struct clk_single_parent_ctx *ctx; @@ -401,14 +584,6 @@ static int clk_orphan_transparent_single_parent_mux_test_init(struct kunit *test return 0; } -static void clk_orphan_transparent_single_parent_mux_test_exit(struct kunit *test) -{ - struct clk_single_parent_ctx *ctx = test->priv; - - clk_hw_unregister(&ctx->hw); - clk_hw_unregister(&ctx->parent_ctx.hw); -} - /* * Test that a mux-only clock, with an initial rate within a range, * will still have the same rate after the range has been enforced. @@ -455,7 +630,7 @@ static struct kunit_case clk_orphan_transparent_single_parent_mux_test_cases[] = static struct kunit_suite clk_orphan_transparent_single_parent_test_suite = { .name = "clk-orphan-transparent-single-parent-test", .init = clk_orphan_transparent_single_parent_mux_test_init, - .exit = clk_orphan_transparent_single_parent_mux_test_exit, + .exit = clk_single_parent_mux_test_exit, .test_cases = clk_orphan_transparent_single_parent_mux_test_cases, }; @@ -1168,6 +1343,7 @@ kunit_test_suites( &clk_range_test_suite, &clk_range_maximize_test_suite, &clk_range_minimize_test_suite, + &clk_single_parent_mux_test_suite, &clk_uncached_test_suite ); MODULE_LICENSE("GPL v2"); -- cgit From 74933ef22c1c3d3d1456c2f949f1910ce2aab1f1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:15 +0200 Subject: clk: tests: Add tests for mux with multiple parents We'll need to test a few corner cases that occur when we have a mux clock whose default parent is missing. For now, let's create the context structure and the trivial ops, along with a test suite that just tests trivial things for now, without considering the orphan case. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-11-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk_test.c | 121 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 06c9220873bb..1ccafd4fabff 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -108,6 +108,39 @@ static const struct clk_ops clk_dummy_single_parent_ops = { .get_parent = clk_dummy_single_get_parent, }; +struct clk_multiple_parent_ctx { + struct clk_dummy_context parents_ctx[2]; + struct clk_hw hw; + u8 current_parent; +}; + +static int clk_multiple_parents_mux_set_parent(struct clk_hw *hw, u8 index) +{ + struct clk_multiple_parent_ctx *ctx = + container_of(hw, struct clk_multiple_parent_ctx, hw); + + if (index >= clk_hw_get_num_parents(hw)) + return -EINVAL; + + ctx->current_parent = index; + + return 0; +} + +static u8 clk_multiple_parents_mux_get_parent(struct clk_hw *hw) +{ + struct clk_multiple_parent_ctx *ctx = + container_of(hw, struct clk_multiple_parent_ctx, hw); + + return ctx->current_parent; +} + +static const struct clk_ops clk_multiple_parents_mux_ops = { + .get_parent = clk_multiple_parents_mux_get_parent, + .set_parent = clk_multiple_parents_mux_set_parent, + .determine_rate = __clk_mux_determine_rate_closest, +}; + static int clk_test_init_with_ops(struct kunit *test, const struct clk_ops *ops) { struct clk_dummy_context *ctx; @@ -360,6 +393,93 @@ static struct kunit_suite clk_uncached_test_suite = { .test_cases = clk_uncached_test_cases, }; +static int +clk_multiple_parents_mux_test_init(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx; + const char *parents[2] = { "parent-0", "parent-1"}; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->parents_ctx[0].hw.init = CLK_HW_INIT_NO_PARENT("parent-0", + &clk_dummy_rate_ops, + 0); + ctx->parents_ctx[0].rate = DUMMY_CLOCK_RATE_1; + ret = clk_hw_register(NULL, &ctx->parents_ctx[0].hw); + if (ret) + return ret; + + ctx->parents_ctx[1].hw.init = CLK_HW_INIT_NO_PARENT("parent-1", + &clk_dummy_rate_ops, + 0); + ctx->parents_ctx[1].rate = DUMMY_CLOCK_RATE_2; + ret = clk_hw_register(NULL, &ctx->parents_ctx[1].hw); + if (ret) + return ret; + + ctx->current_parent = 0; + ctx->hw.init = CLK_HW_INIT_PARENTS("test-mux", parents, + &clk_multiple_parents_mux_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +static void +clk_multiple_parents_mux_test_exit(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->parents_ctx[0].hw); + clk_hw_unregister(&ctx->parents_ctx[1].hw); +} + +/* + * Test that for a clock with multiple parents, clk_get_parent() + * actually returns the current one. + */ +static void +clk_test_multiple_parents_mux_get_parent(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent = clk_hw_get_clk(&ctx->parents_ctx[0].hw, NULL); + + KUNIT_EXPECT_TRUE(test, clk_is_match(clk_get_parent(clk), parent)); + + clk_put(parent); + clk_put(clk); +} + +static struct kunit_case clk_multiple_parents_mux_test_cases[] = { + KUNIT_CASE(clk_test_multiple_parents_mux_get_parent), + {} +}; + +/* + * Test suite for a basic mux clock with two parents, with + * CLK_SET_RATE_PARENT on the child. + * + * These tests exercise the consumer API and check that the state of the + * child and parents are sane and consistent. + */ +static struct kunit_suite +clk_multiple_parents_mux_test_suite = { + .name = "clk-multiple-parents-mux-test", + .init = clk_multiple_parents_mux_test_init, + .exit = clk_multiple_parents_mux_test_exit, + .test_cases = clk_multiple_parents_mux_test_cases, +}; + struct clk_single_parent_ctx { struct clk_dummy_context parent_ctx; struct clk_hw hw; @@ -1339,6 +1459,7 @@ static struct kunit_suite clk_range_minimize_test_suite = { kunit_test_suites( &clk_test_suite, + &clk_multiple_parents_mux_test_suite, &clk_orphan_transparent_single_parent_test_suite, &clk_range_test_suite, &clk_range_maximize_test_suite, -- cgit From 2e9cad1abc7149c5e6aeee7e76a6c363d392da8b Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:16 +0200 Subject: clk: tests: Add some tests for orphan with multiple parents Let's leverage the dummy mux with multiple parents we have to create a mux whose default parent will never be registered, and thus will always be orphan by default. We can then create some tests to make sure that the clock API behaves properly in such a case, and that the transition to a non-orphan clock when we change the parent is done properly. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-12-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk_test.c | 237 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 237 insertions(+) diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 1ccafd4fabff..ceed49c5a88b 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -480,6 +480,242 @@ clk_multiple_parents_mux_test_suite = { .test_cases = clk_multiple_parents_mux_test_cases, }; +static int +clk_orphan_transparent_multiple_parent_mux_test_init(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx; + const char *parents[2] = { "missing-parent", "proper-parent"}; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->parents_ctx[1].hw.init = CLK_HW_INIT_NO_PARENT("proper-parent", + &clk_dummy_rate_ops, + 0); + ctx->parents_ctx[1].rate = DUMMY_CLOCK_INIT_RATE; + ret = clk_hw_register(NULL, &ctx->parents_ctx[1].hw); + if (ret) + return ret; + + ctx->hw.init = CLK_HW_INIT_PARENTS("test-orphan-mux", parents, + &clk_multiple_parents_mux_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +static void +clk_orphan_transparent_multiple_parent_mux_test_exit(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->parents_ctx[1].hw); +} + +/* + * Test that, for a mux whose current parent hasn't been registered yet and is + * thus orphan, clk_get_parent() will return NULL. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_get_parent(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + + KUNIT_EXPECT_PTR_EQ(test, clk_get_parent(clk), NULL); + + clk_put(clk); +} + +/* + * Test that, for a mux whose current parent hasn't been registered yet, + * calling clk_set_parent() to a valid parent will properly update the + * mux parent and its orphan status. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent, *new_parent; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + new_parent = clk_get_parent(clk); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + KUNIT_EXPECT_TRUE(test, clk_is_match(parent, new_parent)); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, the rate of the mux and its new parent are consistent. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_get_rate(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long parent_rate, rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, parent_rate, 0); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, parent_rate, rate); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, calling clk_set_rate_range() will affect the parent state if + * its rate is out of range. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_modified(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(parent); + clk_put(clk); +} + +/* + * Test that, for a mux whose current parent hasn't been registered yet, + * calling clk_set_rate_range() will succeed, and will be taken into + * account when rounding a rate. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_range_round_rate(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + int ret; + + ret = clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); +} + +/* + * Test that, for a mux that started orphan, was assigned and rate and + * then got switched to a valid parent, its rate is eventually within + * range. + * + * FIXME: Even though we update the rate as part of clk_set_parent(), we + * don't evaluate whether that new rate is within range and needs to be + * adjusted. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_range_set_parent_get_rate(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + kunit_skip(test, "This needs to be fixed in the core."); + + clk_hw_set_rate_range(hw, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(parent); + clk_put(clk); +} + +static struct kunit_case clk_orphan_transparent_multiple_parent_mux_test_cases[] = { + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_get_parent), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_get_rate), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_modified), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_range_round_rate), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_range_set_parent_get_rate), + {} +}; + +/* + * Test suite for a basic mux clock with two parents. The default parent + * isn't registered, only the second parent is. By default, the clock + * will thus be orphan. + * + * These tests exercise the behaviour of the consumer API when dealing + * with an orphan clock, and how we deal with the transition to a valid + * parent. + */ +static struct kunit_suite clk_orphan_transparent_multiple_parent_mux_test_suite = { + .name = "clk-orphan-transparent-multiple-parent-mux-test", + .init = clk_orphan_transparent_multiple_parent_mux_test_init, + .exit = clk_orphan_transparent_multiple_parent_mux_test_exit, + .test_cases = clk_orphan_transparent_multiple_parent_mux_test_cases, +}; + struct clk_single_parent_ctx { struct clk_dummy_context parent_ctx; struct clk_hw hw; @@ -1460,6 +1696,7 @@ static struct kunit_suite clk_range_minimize_test_suite = { kunit_test_suites( &clk_test_suite, &clk_multiple_parents_mux_test_suite, + &clk_orphan_transparent_multiple_parent_mux_test_suite, &clk_orphan_transparent_single_parent_test_suite, &clk_range_test_suite, &clk_range_maximize_test_suite, -- cgit From 3afb07231d603d51dca6a5d5e16d9d8f422f9b5f Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:17 +0200 Subject: clk: Take into account uncached clocks in clk_set_rate_range() clk_set_rate_range() will use the last requested rate for the clock when it calls into the driver set_rate hook. However, if CLK_GET_RATE_NOCACHE is set on that clock, the last requested rate might not be matching the current rate of the clock. In such a case, let's read out the rate from the hardware and use that in our set_rate instead. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-13-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 6 +++++- drivers/clk/clk_test.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 1 deletion(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index caa2eb640441..53b28e63deae 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -2373,6 +2373,10 @@ static int clk_set_rate_range_nolock(struct clk *clk, goto out; } + rate = clk->core->req_rate; + if (clk->core->flags & CLK_GET_RATE_NOCACHE) + rate = clk_core_get_rate_recalc(clk->core); + /* * Since the boundaries have been changed, let's give the * opportunity to the provider to adjust the clock rate based on @@ -2390,7 +2394,7 @@ static int clk_set_rate_range_nolock(struct clk *clk, * - the determine_rate() callback does not really check for * this corner case when determining the rate */ - rate = clamp(clk->core->req_rate, min, max); + rate = clamp(rate, min, max); ret = clk_core_set_rate_nolock(clk->core, rate); if (ret) { /* rollback the changes */ diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index ceed49c5a88b..d3e121f21ae2 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -375,9 +375,40 @@ static void clk_test_uncached_set_range(struct kunit *test) clk_put(clk); } +/* + * Test that for an uncached clock, clk_set_rate_range() will work + * properly if the rate has changed in hardware. + * + * In this case, it means that if the rate wasn't initially in the range + * we're trying to set, but got changed at some point into the range + * without the kernel knowing about it, its rate shouldn't be affected. + */ +static void clk_test_uncached_updated_rate_set_range(struct kunit *test) +{ + struct clk_dummy_context *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + + /* We change the rate behind the clock framework's back */ + ctx->rate = DUMMY_CLOCK_RATE_1 + 1000; + KUNIT_ASSERT_EQ(test, + clk_set_rate_range(clk, + DUMMY_CLOCK_RATE_1, + DUMMY_CLOCK_RATE_2), + 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + + clk_put(clk); +} + static struct kunit_case clk_uncached_test_cases[] = { KUNIT_CASE(clk_test_uncached_get_rate), KUNIT_CASE(clk_test_uncached_set_range), + KUNIT_CASE(clk_test_uncached_updated_rate_set_range), {} }; -- cgit From cb1b1dd96241f37ea41d241946d5153c48141cd5 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:18 +0200 Subject: clk: Set req_rate on reparenting If a non-rate clock started by default with a parent that never registered, core->req_rate will be 0. The expectation is that whenever the parent will be registered, req_rate will be updated with the new value that has just been computed. However, if that clock is a mux, clk_set_parent() can also make that clock no longer orphan. In this case however, we never update req_rate. The natural solution to this would be to update core->rate and core->req_rate in clk_reparent() by calling clk_recalc(). However, this doesn't work in all cases. Indeed, clk_recalc() is called by __clk_set_parent_before(), __clk_set_parent() and clk_core_reparent(). Both __clk_set_parent_before() and __clk_set_parent will call clk_recalc() with the enable_lock taken through a call to clk_enable_lock(), the underlying locking primitive being a spinlock. clk_recalc() calls the backing driver .recalc_rate hook, and that implementation might sleep if the underlying device uses a bus with accesses that might sleep, such as i2c. In such a situation, we would end up sleeping while holding a spinlock, and thus in an atomic section. In order to work around this, we can move the core->rate and core->req_rate update to the clk_recalc() calling sites, after the enable_lock has been released if it was taken. The only situation that could still be problematic is the clk_core_reparent() -> clk_reparent() case that doesn't have any locking. clk_core_reparent() is itself called by clk_hw_reparent(), which is then called by 4 drivers: * clk-stm32mp1.c, stm32/clk-stm32-core.c and tegra/clk-tegra210-emc.c use it in their set_parent implementation. The set_parent hook is only called by __clk_set_parent() and clk_change_rate(), both of them calling it without the enable_lock taken. * clk/tegra/clk-tegra124-emc.c calls it as part of its set_rate implementation. set_rate is only called by clk_change_rate(), again without the enable_lock taken. In both cases we can't end up in a situation where the clk_hw_reparent() caller would hold a spinlock, so it seems like this is a good workaround. Let's also add some unit tests to make sure we cover the original bug. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-14-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 22 +++++ drivers/clk/clk_test.c | 239 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 261 insertions(+) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 53b28e63deae..91bb1ea0e147 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1765,6 +1765,23 @@ static void clk_core_update_orphan_status(struct clk_core *core, bool is_orphan) clk_core_update_orphan_status(child, is_orphan); } +/* + * Update the orphan rate and req_rate of @core and all its children. + */ +static void clk_core_update_orphan_child_rates(struct clk_core *core) +{ + struct clk_core *child; + unsigned long parent_rate = 0; + + if (core->parent) + parent_rate = core->parent->rate; + + core->rate = core->req_rate = clk_recalc(core, parent_rate); + + hlist_for_each_entry(child, &core->children, child_node) + clk_core_update_orphan_child_rates(child); +} + static void clk_reparent(struct clk_core *core, struct clk_core *new_parent) { bool was_orphan = core->orphan; @@ -1834,6 +1851,8 @@ static struct clk_core *__clk_set_parent_before(struct clk_core *core, clk_reparent(core, parent); clk_enable_unlock(flags); + clk_core_update_orphan_child_rates(core); + return old_parent; } @@ -1878,6 +1897,8 @@ static int __clk_set_parent(struct clk_core *core, struct clk_core *parent, flags = clk_enable_lock(); clk_reparent(core, old_parent); clk_enable_unlock(flags); + + clk_core_update_orphan_child_rates(core); __clk_set_parent_after(core, old_parent, parent); return ret; @@ -2506,6 +2527,7 @@ static void clk_core_reparent(struct clk_core *core, struct clk_core *new_parent) { clk_reparent(core, new_parent); + clk_core_update_orphan_child_rates(core); __clk_recalc_accuracies(core); __clk_recalc_rates(core, POST_RATE_CHANGE); } diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index d3e121f21ae2..d1b1372f7aaa 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -594,6 +594,41 @@ clk_test_orphan_transparent_multiple_parent_mux_set_parent(struct kunit *test) clk_put(clk); } +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, calling clk_drop_range() on the mux won't affect the parent + * rate. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_drop_range(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long parent_rate, new_parent_rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, parent_rate, 0); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_drop_range(clk); + KUNIT_ASSERT_EQ(test, ret, 0); + + new_parent_rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, new_parent_rate, 0); + KUNIT_EXPECT_EQ(test, parent_rate, new_parent_rate); + + clk_put(parent); + clk_put(clk); +} + /* * Test that, for a mux that started orphan but got switched to a valid * parent, the rate of the mux and its new parent are consistent. @@ -625,6 +660,39 @@ clk_test_orphan_transparent_multiple_parent_mux_set_parent_get_rate(struct kunit clk_put(clk); } +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, calling clk_put() on the mux won't affect the parent rate. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_put(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk *clk, *parent; + unsigned long parent_rate, new_parent_rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + clk = clk_hw_get_clk(&ctx->hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, clk); + + parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, parent_rate, 0); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + clk_put(clk); + + new_parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, new_parent_rate, 0); + KUNIT_EXPECT_EQ(test, parent_rate, new_parent_rate); + + clk_put(parent); +} + /* * Test that, for a mux that started orphan but got switched to a valid * parent, calling clk_set_rate_range() will affect the parent state if @@ -658,6 +726,43 @@ clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_modified(st clk_put(clk); } +/* + * Test that, for a mux that started orphan but got switched to a valid + * parent, calling clk_set_rate_range() won't affect the parent state if + * its rate is within range. + */ +static void +clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_untouched(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long parent_rate, new_parent_rate; + int ret; + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent); + + parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, parent_rate, 0); + + ret = clk_set_parent(clk, parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, + DUMMY_CLOCK_INIT_RATE - 1000, + DUMMY_CLOCK_INIT_RATE + 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + new_parent_rate = clk_get_rate(parent); + KUNIT_ASSERT_GT(test, new_parent_rate, 0); + KUNIT_EXPECT_EQ(test, parent_rate, new_parent_rate); + + clk_put(parent); + clk_put(clk); +} + /* * Test that, for a mux whose current parent hasn't been registered yet, * calling clk_set_rate_range() will succeed, and will be taken into @@ -724,8 +829,11 @@ clk_test_orphan_transparent_multiple_parent_mux_set_range_set_parent_get_rate(st static struct kunit_case clk_orphan_transparent_multiple_parent_mux_test_cases[] = { KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_get_parent), KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_drop_range), KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_get_rate), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_put), KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_modified), + KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_parent_set_range_untouched), KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_range_round_rate), KUNIT_CASE(clk_test_orphan_transparent_multiple_parent_mux_set_range_set_parent_get_rate), {} @@ -1021,6 +1129,136 @@ static struct kunit_suite clk_orphan_transparent_single_parent_test_suite = { .test_cases = clk_orphan_transparent_single_parent_mux_test_cases, }; +struct clk_single_parent_two_lvl_ctx { + struct clk_dummy_context parent_parent_ctx; + struct clk_dummy_context parent_ctx; + struct clk_hw hw; +}; + +static int +clk_orphan_two_level_root_last_test_init(struct kunit *test) +{ + struct clk_single_parent_two_lvl_ctx *ctx; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->parent_ctx.hw.init = + CLK_HW_INIT("intermediate-parent", + "root-parent", + &clk_dummy_single_parent_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->parent_ctx.hw); + if (ret) + return ret; + + ctx->hw.init = + CLK_HW_INIT("test-clk", "intermediate-parent", + &clk_dummy_single_parent_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + ctx->parent_parent_ctx.rate = DUMMY_CLOCK_INIT_RATE; + ctx->parent_parent_ctx.hw.init = + CLK_HW_INIT_NO_PARENT("root-parent", + &clk_dummy_rate_ops, + 0); + ret = clk_hw_register(NULL, &ctx->parent_parent_ctx.hw); + if (ret) + return ret; + + return 0; +} + +static void +clk_orphan_two_level_root_last_test_exit(struct kunit *test) +{ + struct clk_single_parent_two_lvl_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->parent_ctx.hw); + clk_hw_unregister(&ctx->parent_parent_ctx.hw); +} + +/* + * Test that, for a clock whose parent used to be orphan, clk_get_rate() + * will return the proper rate. + */ +static void +clk_orphan_two_level_root_last_test_get_rate(struct kunit *test) +{ + struct clk_single_parent_two_lvl_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + + rate = clk_get_rate(clk); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_INIT_RATE); + + clk_put(clk); +} + +/* + * Test that, for a clock whose parent used to be orphan, + * clk_set_rate_range() won't affect its rate if it is already within + * range. + * + * See (for Exynos 4210): + * https://lore.kernel.org/linux-clk/366a0232-bb4a-c357-6aa8-636e398e05eb@samsung.com/ + */ +static void +clk_orphan_two_level_root_last_test_set_range(struct kunit *test) +{ + struct clk_single_parent_two_lvl_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + unsigned long rate; + int ret; + + ret = clk_set_rate_range(clk, + DUMMY_CLOCK_INIT_RATE - 1000, + DUMMY_CLOCK_INIT_RATE + 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_EQ(test, rate, DUMMY_CLOCK_INIT_RATE); + + clk_put(clk); +} + +static struct kunit_case +clk_orphan_two_level_root_last_test_cases[] = { + KUNIT_CASE(clk_orphan_two_level_root_last_test_get_rate), + KUNIT_CASE(clk_orphan_two_level_root_last_test_set_range), + {} +}; + +/* + * Test suite for a basic, transparent, clock with a parent that is also + * such a clock. The parent's parent is registered last, while the + * parent and its child are registered in that order. The intermediate + * and leaf clocks will thus be orphan when registered, but the leaf + * clock itself will always have its parent and will never be + * reparented. Indeed, it's only orphan because its parent is. + * + * These tests exercise the behaviour of the consumer API when dealing + * with an orphan clock, and how we deal with the transition to a valid + * parent. + */ +static struct kunit_suite +clk_orphan_two_level_root_last_test_suite = { + .name = "clk-orphan-two-level-root-last-test", + .init = clk_orphan_two_level_root_last_test_init, + .exit = clk_orphan_two_level_root_last_test_exit, + .test_cases = clk_orphan_two_level_root_last_test_cases, +}; + /* * Test that clk_set_rate_range won't return an error for a valid range * and that it will make sure the rate of the clock is within the @@ -1729,6 +1967,7 @@ kunit_test_suites( &clk_multiple_parents_mux_test_suite, &clk_orphan_transparent_multiple_parent_mux_test_suite, &clk_orphan_transparent_single_parent_test_suite, + &clk_orphan_two_level_root_last_test_suite, &clk_range_test_suite, &clk_range_maximize_test_suite, &clk_range_minimize_test_suite, -- cgit From 718af795d3fd786928506cd5251597fbe29c7fda Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:19 +0200 Subject: clk: Change clk_core_init_rate_req prototype The expectation is that a clk_rate_request structure is supposed to be initialized using clk_core_init_rate_req(), yet the rate we want to request still needs to be set by hand. Let's just pass the rate as a function argument so that callers don't have any extra work to do. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-15-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 91bb1ea0e147..75cfde9f917f 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1380,13 +1380,16 @@ static int clk_core_determine_round_nolock(struct clk_core *core, } static void clk_core_init_rate_req(struct clk_core * const core, - struct clk_rate_request *req) + struct clk_rate_request *req, + unsigned long rate) { struct clk_core *parent; if (WARN_ON(!core || !req)) return; + req->rate = rate; + parent = core->parent; if (parent) { req->best_parent_hw = parent->hw; @@ -1412,7 +1415,7 @@ static int clk_core_round_rate_nolock(struct clk_core *core, return 0; } - clk_core_init_rate_req(core, req); + clk_core_init_rate_req(core, req, req->rate); if (clk_core_can_round(core)) return clk_core_determine_round_nolock(core, req); @@ -2004,11 +2007,10 @@ static struct clk_core *clk_calc_new_rates(struct clk_core *core, if (clk_core_can_round(core)) { struct clk_rate_request req; - req.rate = rate; req.min_rate = min_rate; req.max_rate = max_rate; - clk_core_init_rate_req(core, &req); + clk_core_init_rate_req(core, &req, rate); ret = clk_core_determine_round_nolock(core, &req); if (ret < 0) -- cgit From 8cd9c39dce5b54494f967235f7eeac7c30c08b97 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:20 +0200 Subject: clk: Move clk_core_init_rate_req() from clk_core_round_rate_nolock() to its caller The clk_rate_request structure is used internally as an argument for the clk_core_determine_round_nolock() and clk_core_round_rate_nolock(). In both cases, the clk_core_init_rate_req() function is used to initialize the clk_rate_request structure. However, the expectation on who gets to call that function is inconsistent between those two functions. Indeed, clk_core_determine_round_nolock() will assume the structure is properly initialized and will just use it. On the other hand, clk_core_round_rate_nolock() will call clk_core_init_rate_req() itself, expecting the caller to have filled only a minimal set of parameters (rate, min_rate and max_rate). If we ignore the calling convention inconsistency, this leads to a second inconsistency for drivers: * If they get called by the framework through clk_core_round_rate_nolock(), the rate, min_rate and max_rate fields will be filled by the caller, and the best_parent_rate and best_parent_hw fields will get filled by clk_core_init_rate_req(). * If they get called by a driver through __clk_determine_rate (and thus clk_core_round_rate_nolock), only best_parent_rate and best_parent_hw are being explicitly set by the framework. Even though we can reasonably expect rate to be set, only one of the 6 in-tree users explicitly set min_rate and max_rate. * If they get called by the framework through clk_core_determine_round_nolock(), then we have two callpaths. Either it will be called by clk_core_round_rate_nolock() itself, or it will be called by clk_calc_new_rates(), which will properly initialize rate, min_rate, max_rate itself, and best_parent_rate and best_parent_hw through clk_core_init_rate_req(). Even though the first and third case seems equivalent, they aren't when the clock has CLK_SET_RATE_PARENT. Indeed, in such a case clk_core_round_rate_nolock() will call itself on the current parent clock with the same clk_rate_request structure. The clk_core_init_rate_req() function will then be called on the parent clock, with the child clk_rate_request pointer and will fill the best_parent_rate and best_parent_hw fields with the parent context. When the whole recursion stops and the call returns, the initial caller will end up with a clk_rate_request structure with some information of the child clock (rate, min_rate, max_rate) and some others of the last clock up the tree whose child had CLK_SET_RATE_PARENT (best_parent_hw, best_parent_rate). In the most common case, best_parent_rate is going to be equal on all the parent clocks so it's not a big deal. However, best_parent_hw is going to point to a clock that never has been a valid parent for that clock which is definitely confusing. In order to fix the calling inconsistency, let's move the clk_core_init_rate_req() calls to the callers, which will also help a bit with the clk_core_round_rate_nolock() recursion. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-16-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 75cfde9f917f..553e1e9eb300 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1415,8 +1415,6 @@ static int clk_core_round_rate_nolock(struct clk_core *core, return 0; } - clk_core_init_rate_req(core, req, req->rate); - if (clk_core_can_round(core)) return clk_core_determine_round_nolock(core, req); else if (core->flags & CLK_SET_RATE_PARENT) @@ -1464,8 +1462,8 @@ unsigned long clk_hw_round_rate(struct clk_hw *hw, unsigned long rate) int ret; struct clk_rate_request req; + clk_core_init_rate_req(hw->core, &req, rate); clk_core_get_boundaries(hw->core, &req.min_rate, &req.max_rate); - req.rate = rate; ret = clk_core_round_rate_nolock(hw->core, &req); if (ret) @@ -1497,8 +1495,8 @@ long clk_round_rate(struct clk *clk, unsigned long rate) if (clk->exclusive_count) clk_core_rate_unprotect(clk->core); + clk_core_init_rate_req(clk->core, &req, rate); clk_core_get_boundaries(clk->core, &req.min_rate, &req.max_rate); - req.rate = rate; ret = clk_core_round_rate_nolock(clk->core, &req); @@ -2209,8 +2207,8 @@ static unsigned long clk_core_req_round_rate_nolock(struct clk_core *core, if (cnt < 0) return cnt; + clk_core_init_rate_req(core, &req, req_rate); clk_core_get_boundaries(core, &req.min_rate, &req.max_rate); - req.rate = req_rate; ret = clk_core_round_rate_nolock(core, &req); -- cgit From c35e84b0977617f96fb1dbef3fb8d71a861325c0 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:21 +0200 Subject: clk: Introduce clk_hw_init_rate_request() clk-divider instantiates clk_rate_request internally for its round_rate implementations to share the code with its determine_rate implementations. However, it's missing a few fields (min_rate, max_rate) that would be initialized properly if it was using clk_core_init_rate_req(). Let's create the clk_hw_init_rate_request() function for clock providers to be able to share the code to instation clk_rate_requests with the framework. This will also be useful for some tests introduced in later patches. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-17-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk-divider.c | 20 ++++++++++---------- drivers/clk/clk.c | 20 ++++++++++++++++++++ include/linux/clk-provider.h | 6 ++++++ 3 files changed, 36 insertions(+), 10 deletions(-) diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c index f6b2bf558486..a2c2b5203b0a 100644 --- a/drivers/clk/clk-divider.c +++ b/drivers/clk/clk-divider.c @@ -386,13 +386,13 @@ long divider_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, const struct clk_div_table *table, u8 width, unsigned long flags) { - struct clk_rate_request req = { - .rate = rate, - .best_parent_rate = *prate, - .best_parent_hw = parent, - }; + struct clk_rate_request req; int ret; + clk_hw_init_rate_request(hw, &req, rate); + req.best_parent_rate = *prate; + req.best_parent_hw = parent; + ret = divider_determine_rate(hw, &req, table, width, flags); if (ret) return ret; @@ -408,13 +408,13 @@ long divider_ro_round_rate_parent(struct clk_hw *hw, struct clk_hw *parent, const struct clk_div_table *table, u8 width, unsigned long flags, unsigned int val) { - struct clk_rate_request req = { - .rate = rate, - .best_parent_rate = *prate, - .best_parent_hw = parent, - }; + struct clk_rate_request req; int ret; + clk_hw_init_rate_request(hw, &req, rate); + req.best_parent_rate = *prate; + req.best_parent_hw = parent; + ret = divider_ro_determine_rate(hw, &req, table, width, flags, val); if (ret) return ret; diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 553e1e9eb300..96b372ff23c2 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1400,6 +1400,26 @@ static void clk_core_init_rate_req(struct clk_core * const core, } } +/** + * clk_hw_init_rate_request - Initializes a clk_rate_request + * @hw: the clk for which we want to submit a rate request + * @req: the clk_rate_request structure we want to initialise + * @rate: the rate which is to be requested + * + * Initializes a clk_rate_request structure to submit to + * __clk_determine_rate() or similar functions. + */ +void clk_hw_init_rate_request(const struct clk_hw *hw, + struct clk_rate_request *req, + unsigned long rate) +{ + if (WARN_ON(!hw || !req)) + return; + + clk_core_init_rate_req(hw->core, req, rate); +} +EXPORT_SYMBOL_GPL(clk_hw_init_rate_request); + static bool clk_core_can_round(struct clk_core * const core) { return core->ops->determine_rate || core->ops->round_rate; diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 9a14cfa0d201..d857717aa386 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -42,6 +42,8 @@ struct dentry; * struct clk_rate_request - Structure encoding the clk constraints that * a clock user might require. * + * Should be initialized by calling clk_hw_init_rate_request(). + * * @rate: Requested clock rate. This field will be adjusted by * clock drivers according to hardware capabilities. * @min_rate: Minimum rate imposed by clk users. @@ -60,6 +62,10 @@ struct clk_rate_request { struct clk_hw *best_parent_hw; }; +void clk_hw_init_rate_request(const struct clk_hw *hw, + struct clk_rate_request *req, + unsigned long rate); + /** * struct clk_duty - Struture encoding the duty cycle ratio of a clock * -- cgit From 11c84a38fcff30197f6e8af29e65531a5734ee05 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:22 +0200 Subject: clk: Add our request boundaries in clk_core_init_rate_req The expectation is that a new clk_rate_request is initialized through a call to clk_core_init_rate_req(). However, at the moment it only fills the parent rate and clk_hw pointer, but omits the other fields such as the clock rate boundaries. Some users of that function will update them after calling it, but most don't. As we are passed the clk_core pointer, we have access to those boundaries in clk_core_init_rate_req() however, so let's just fill it there and remove it from the few callers that do it right. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-18-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 96b372ff23c2..2794bd3bef4b 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1389,6 +1389,7 @@ static void clk_core_init_rate_req(struct clk_core * const core, return; req->rate = rate; + clk_core_get_boundaries(core, &req->min_rate, &req->max_rate); parent = core->parent; if (parent) { @@ -1483,7 +1484,6 @@ unsigned long clk_hw_round_rate(struct clk_hw *hw, unsigned long rate) struct clk_rate_request req; clk_core_init_rate_req(hw->core, &req, rate); - clk_core_get_boundaries(hw->core, &req.min_rate, &req.max_rate); ret = clk_core_round_rate_nolock(hw->core, &req); if (ret) @@ -1516,7 +1516,6 @@ long clk_round_rate(struct clk *clk, unsigned long rate) clk_core_rate_unprotect(clk->core); clk_core_init_rate_req(clk->core, &req, rate); - clk_core_get_boundaries(clk->core, &req.min_rate, &req.max_rate); ret = clk_core_round_rate_nolock(clk->core, &req); @@ -2025,9 +2024,6 @@ static struct clk_core *clk_calc_new_rates(struct clk_core *core, if (clk_core_can_round(core)) { struct clk_rate_request req; - req.min_rate = min_rate; - req.max_rate = max_rate; - clk_core_init_rate_req(core, &req, rate); ret = clk_core_determine_round_nolock(core, &req); @@ -2228,7 +2224,6 @@ static unsigned long clk_core_req_round_rate_nolock(struct clk_core *core, return cnt; clk_core_init_rate_req(core, &req, req_rate); - clk_core_get_boundaries(core, &req.min_rate, &req.max_rate); ret = clk_core_round_rate_nolock(core, &req); -- cgit From 666650b25ac43700a1cce96e51a32fc89c973d28 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:23 +0200 Subject: clk: Switch from __clk_determine_rate to clk_core_round_rate_nolock clk_mux_determine_rate_flags() will call into __clk_determine_rate() with a clk_hw pointer, while it has access to the clk_core pointer already. This leads to back and forth between clk_hw and clk_core, while __clk_determine_rate will only call clk_core_round_rate_nolock() with the clk_core pointer it retrieved from the clk_hw. Let's simplify things a bit by calling into clk_core_round_rate_nolock directly. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-19-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 2794bd3bef4b..f8a8bdd552d6 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -536,6 +536,9 @@ static bool mux_is_better_rate(unsigned long rate, unsigned long now, return now <= rate && now > best; } +static int clk_core_round_rate_nolock(struct clk_core *core, + struct clk_rate_request *req); + int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags) @@ -549,8 +552,12 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, if (core->flags & CLK_SET_RATE_NO_REPARENT) { parent = core->parent; if (core->flags & CLK_SET_RATE_PARENT) { - ret = __clk_determine_rate(parent ? parent->hw : NULL, - &parent_req); + if (!parent) { + req->rate = 0; + return 0; + } + + ret = clk_core_round_rate_nolock(parent, &parent_req); if (ret) return ret; @@ -573,7 +580,7 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, if (core->flags & CLK_SET_RATE_PARENT) { parent_req = *req; - ret = __clk_determine_rate(parent->hw, &parent_req); + ret = clk_core_round_rate_nolock(parent, &parent_req); if (ret) continue; } else { -- cgit From 1234a2c40b8cf16041fb9acd730160e6c5b4ba13 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:24 +0200 Subject: clk: Introduce clk_core_has_parent() We will need to know if a clk_core pointer has a given parent in other functions, so let's create a clk_core_has_parent() function that clk_has_parent() will call into. For good measure, let's add some unit tests as well to make sure it works properly. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-20-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju [sboyd@kernel.org: Move tmp declaration, fix conditional to check for current parent] Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 37 ++++++++++++++++++++++--------------- drivers/clk/clk_test.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+), 15 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index f8a8bdd552d6..8e4a8b9aa320 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -539,6 +539,27 @@ static bool mux_is_better_rate(unsigned long rate, unsigned long now, static int clk_core_round_rate_nolock(struct clk_core *core, struct clk_rate_request *req); +static bool clk_core_has_parent(struct clk_core *core, const struct clk_core *parent) +{ + struct clk_core *tmp; + unsigned int i; + + /* Optimize for the case where the parent is already the parent. */ + if (core->parent == parent) + return true; + + for (i = 0; i < core->num_parents; i++) { + tmp = clk_core_get_parent_by_index(core, i); + if (!tmp) + continue; + + if (tmp == parent) + return true; + } + + return false; +} + int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags) @@ -2574,25 +2595,11 @@ void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent) */ bool clk_has_parent(struct clk *clk, struct clk *parent) { - struct clk_core *core, *parent_core; - int i; - /* NULL clocks should be nops, so return success if either is NULL. */ if (!clk || !parent) return true; - core = clk->core; - parent_core = parent->core; - - /* Optimize for the case where the parent is already the parent. */ - if (core->parent == parent_core) - return true; - - for (i = 0; i < core->num_parents; i++) - if (!strcmp(core->parents[i].name, parent_core->name)) - return true; - - return false; + return clk_core_has_parent(clk->core, parent->core); } EXPORT_SYMBOL_GPL(clk_has_parent); diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index d1b1372f7aaa..7068517428e2 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -491,8 +491,32 @@ clk_test_multiple_parents_mux_get_parent(struct kunit *test) clk_put(clk); } +/* + * Test that for a clock with a multiple parents, clk_has_parent() + * actually reports all of them as parents. + */ +static void +clk_test_multiple_parents_mux_has_parent(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + + parent = clk_hw_get_clk(&ctx->parents_ctx[0].hw, NULL); + KUNIT_EXPECT_TRUE(test, clk_has_parent(clk, parent)); + clk_put(parent); + + parent = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_EXPECT_TRUE(test, clk_has_parent(clk, parent)); + clk_put(parent); + + clk_put(clk); +} + static struct kunit_case clk_multiple_parents_mux_test_cases[] = { KUNIT_CASE(clk_test_multiple_parents_mux_get_parent), + KUNIT_CASE(clk_test_multiple_parents_mux_has_parent), {} }; @@ -918,6 +942,24 @@ clk_test_single_parent_mux_get_parent(struct kunit *test) clk_put(clk); } +/* + * Test that for a clock with a single parent, clk_has_parent() actually + * reports it as a parent. + */ +static void +clk_test_single_parent_mux_has_parent(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent = clk_hw_get_clk(&ctx->parent_ctx.hw, NULL); + + KUNIT_EXPECT_TRUE(test, clk_has_parent(clk, parent)); + + clk_put(parent); + clk_put(clk); +} + /* * Test that for a clock that can't modify its rate and with a single * parent, if we set disjoints range on the parent and then the child, @@ -1022,6 +1064,7 @@ clk_test_single_parent_mux_set_range_round_rate_child_smaller(struct kunit *test static struct kunit_case clk_single_parent_mux_test_cases[] = { KUNIT_CASE(clk_test_single_parent_mux_get_parent), + KUNIT_CASE(clk_test_single_parent_mux_has_parent), KUNIT_CASE(clk_test_single_parent_mux_set_range_disjoint_child_last), KUNIT_CASE(clk_test_single_parent_mux_set_range_disjoint_parent_last), KUNIT_CASE(clk_test_single_parent_mux_set_range_round_rate_child_smaller), -- cgit From 22fb0e284fbc3c1b85d24c5a1df8ea3ac82ab1d1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:25 +0200 Subject: clk: Constify clk_has_parent() clk_has_parent() doesn't modify the clocks being passed, so let's make it const. Suggested-by: Stephen Boyd Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-21-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 2 +- include/linux/clk.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 8e4a8b9aa320..3b68a9b8234a 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -2593,7 +2593,7 @@ void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent) * * Returns true if @parent is a possible parent for @clk, false otherwise. */ -bool clk_has_parent(struct clk *clk, struct clk *parent) +bool clk_has_parent(const struct clk *clk, const struct clk *parent) { /* NULL clocks should be nops, so return success if either is NULL. */ if (!clk || !parent) diff --git a/include/linux/clk.h b/include/linux/clk.h index c13061cabdfc..1ef013324237 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -799,7 +799,7 @@ int clk_set_rate_exclusive(struct clk *clk, unsigned long rate); * * Returns true if @parent is a possible parent for @clk, false otherwise. */ -bool clk_has_parent(struct clk *clk, struct clk *parent); +bool clk_has_parent(const struct clk *clk, const struct clk *parent); /** * clk_set_rate_range - set a rate range for a clock source -- cgit From 262ca38f4b6eb418b20b8e1d6d8495c6a98727c1 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:26 +0200 Subject: clk: Stop forwarding clk_rate_requests to the parent If the clock cannot modify its rate and has CLK_SET_RATE_PARENT, clk_mux_determine_rate_flags(), clk_core_round_rate_nolock() and a number of drivers will forward the clk_rate_request to the parent clock. clk_core_round_rate_nolock() will pass the pointer directly, which means that we pass a clk_rate_request to the parent that has the rate, min_rate and max_rate of the child, and the best_parent_rate and best_parent_hw fields will be relative to the child as well, so will point to our current clock and its rate. The most common case for CLK_SET_RATE_PARENT is that the child and parent clock rates will be equal, so the rate field isn't a worry, but the other fields are. Similarly, if the parent clock driver ever modifies the best_parent_rate or best_parent_hw, this will be applied to the child once the call to clk_core_round_rate_nolock() is done. best_parent_hw is probably not going to be a valid parent, and best_parent_rate might lead to a parent rate change different to the one that was initially computed. clk_mux_determine_rate_flags() and the affected drivers will copy the request before forwarding it to the parents, so they won't be affected by the latter issue, but the former is still going to be there and will lead to erroneous data and context being passed to the various clock drivers in the same sub-tree. Let's create two new functions, clk_core_forward_rate_req() and clk_hw_forward_rate_request() for the framework and the clock providers that will copy a request from a child clock and update the context to match the parent's. We also update the relevant call sites in the framework and drivers to use that new function. Let's also add a test to make sure we avoid regressions there. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-22-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/at91/clk-generated.c | 5 +- drivers/clk/at91/clk-master.c | 9 +- drivers/clk/at91/clk-peripheral.c | 4 +- drivers/clk/clk-composite.c | 6 +- drivers/clk/clk.c | 84 ++++++++++++++++-- drivers/clk/clk_test.c | 182 ++++++++++++++++++++++++++++++++++++++ include/linux/clk-provider.h | 5 ++ 7 files changed, 279 insertions(+), 16 deletions(-) diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c index d429ba52a719..943ea67bf135 100644 --- a/drivers/clk/at91/clk-generated.c +++ b/drivers/clk/at91/clk-generated.c @@ -136,7 +136,6 @@ static int clk_generated_determine_rate(struct clk_hw *hw, { struct clk_generated *gck = to_clk_generated(hw); struct clk_hw *parent = NULL; - struct clk_rate_request req_parent = *req; long best_rate = -EINVAL; unsigned long min_rate, parent_rate; int best_diff = -1; @@ -192,7 +191,9 @@ static int clk_generated_determine_rate(struct clk_hw *hw, goto end; for (div = 1; div < GENERATED_MAX_DIV + 2; div++) { - req_parent.rate = req->rate * div; + struct clk_rate_request req_parent; + + clk_hw_forward_rate_request(hw, req, parent, &req_parent, req->rate * div); if (__clk_determine_rate(parent, &req_parent)) continue; clk_generated_best_diff(req, parent, req_parent.rate, div, diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c index 164e2959c7cf..b7cd1924de52 100644 --- a/drivers/clk/at91/clk-master.c +++ b/drivers/clk/at91/clk-master.c @@ -581,7 +581,6 @@ static int clk_sama7g5_master_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { struct clk_master *master = to_clk_master(hw); - struct clk_rate_request req_parent = *req; struct clk_hw *parent; long best_rate = LONG_MIN, best_diff = LONG_MIN; unsigned long parent_rate; @@ -618,11 +617,15 @@ static int clk_sama7g5_master_determine_rate(struct clk_hw *hw, goto end; for (div = 0; div < MASTER_PRES_MAX + 1; div++) { + struct clk_rate_request req_parent; + unsigned long req_rate; + if (div == MASTER_PRES_MAX) - req_parent.rate = req->rate * 3; + req_rate = req->rate * 3; else - req_parent.rate = req->rate << div; + req_rate = req->rate << div; + clk_hw_forward_rate_request(hw, req, parent, &req_parent, req_rate); if (__clk_determine_rate(parent, &req_parent)) continue; diff --git a/drivers/clk/at91/clk-peripheral.c b/drivers/clk/at91/clk-peripheral.c index e14fa5ac734c..5104d4025484 100644 --- a/drivers/clk/at91/clk-peripheral.c +++ b/drivers/clk/at91/clk-peripheral.c @@ -269,7 +269,6 @@ static int clk_sam9x5_peripheral_determine_rate(struct clk_hw *hw, { struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw); struct clk_hw *parent = clk_hw_get_parent(hw); - struct clk_rate_request req_parent = *req; unsigned long parent_rate = clk_hw_get_rate(parent); unsigned long tmp_rate; long best_rate = LONG_MIN; @@ -302,8 +301,9 @@ static int clk_sam9x5_peripheral_determine_rate(struct clk_hw *hw, goto end; for (shift = 0; shift <= PERIPHERAL_MAX_SHIFT; shift++) { - req_parent.rate = req->rate << shift; + struct clk_rate_request req_parent; + clk_hw_forward_rate_request(hw, req, parent, &req_parent, req->rate << shift); if (__clk_determine_rate(parent, &req_parent)) continue; diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c index b9c5f904f535..edfa94641bbf 100644 --- a/drivers/clk/clk-composite.c +++ b/drivers/clk/clk-composite.c @@ -85,10 +85,11 @@ static int clk_composite_determine_rate(struct clk_hw *hw, req->best_parent_hw = NULL; if (clk_hw_get_flags(hw) & CLK_SET_RATE_NO_REPARENT) { - struct clk_rate_request tmp_req = *req; + struct clk_rate_request tmp_req; parent = clk_hw_get_parent(mux_hw); + clk_hw_forward_rate_request(hw, req, parent, &tmp_req, req->rate); ret = clk_composite_determine_rate_for_parent(rate_hw, &tmp_req, parent, @@ -104,12 +105,13 @@ static int clk_composite_determine_rate(struct clk_hw *hw, } for (i = 0; i < clk_hw_get_num_parents(mux_hw); i++) { - struct clk_rate_request tmp_req = *req; + struct clk_rate_request tmp_req; parent = clk_hw_get_parent_by_index(mux_hw, i); if (!parent) continue; + clk_hw_forward_rate_request(hw, req, parent, &tmp_req, req->rate); ret = clk_composite_determine_rate_for_parent(rate_hw, &tmp_req, parent, diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 3b68a9b8234a..3f60eb836980 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -536,6 +536,10 @@ static bool mux_is_better_rate(unsigned long rate, unsigned long now, return now <= rate && now > best; } +static void clk_core_init_rate_req(struct clk_core * const core, + struct clk_rate_request *req, + unsigned long rate); + static int clk_core_round_rate_nolock(struct clk_core *core, struct clk_rate_request *req); @@ -560,6 +564,25 @@ static bool clk_core_has_parent(struct clk_core *core, const struct clk_core *pa return false; } +static void +clk_core_forward_rate_req(struct clk_core *core, + const struct clk_rate_request *old_req, + struct clk_core *parent, + struct clk_rate_request *req, + unsigned long parent_rate) +{ + if (WARN_ON(!clk_core_has_parent(core, parent))) + return; + + clk_core_init_rate_req(parent, req, parent_rate); + + if (req->min_rate < old_req->min_rate) + req->min_rate = old_req->min_rate; + + if (req->max_rate > old_req->max_rate) + req->max_rate = old_req->max_rate; +} + int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags) @@ -567,17 +590,19 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_core *core = hw->core, *parent, *best_parent = NULL; int i, num_parents, ret; unsigned long best = 0; - struct clk_rate_request parent_req = *req; /* if NO_REPARENT flag set, pass through to current parent */ if (core->flags & CLK_SET_RATE_NO_REPARENT) { parent = core->parent; if (core->flags & CLK_SET_RATE_PARENT) { + struct clk_rate_request parent_req; + if (!parent) { req->rate = 0; return 0; } + clk_core_forward_rate_req(core, req, parent, &parent_req, req->rate); ret = clk_core_round_rate_nolock(parent, &parent_req); if (ret) return ret; @@ -595,23 +620,29 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, /* find the parent that can provide the fastest rate <= rate */ num_parents = core->num_parents; for (i = 0; i < num_parents; i++) { + unsigned long parent_rate; + parent = clk_core_get_parent_by_index(core, i); if (!parent) continue; if (core->flags & CLK_SET_RATE_PARENT) { - parent_req = *req; + struct clk_rate_request parent_req; + + clk_core_forward_rate_req(core, req, parent, &parent_req, req->rate); ret = clk_core_round_rate_nolock(parent, &parent_req); if (ret) continue; + + parent_rate = parent_req.rate; } else { - parent_req.rate = clk_core_get_rate_nolock(parent); + parent_rate = clk_core_get_rate_nolock(parent); } - if (mux_is_better_rate(req->rate, parent_req.rate, + if (mux_is_better_rate(req->rate, parent_rate, best, flags)) { best_parent = parent; - best = parent_req.rate; + best = parent_rate; } } @@ -1449,6 +1480,31 @@ void clk_hw_init_rate_request(const struct clk_hw *hw, } EXPORT_SYMBOL_GPL(clk_hw_init_rate_request); +/** + * clk_hw_forward_rate_request - Forwards a clk_rate_request to a clock's parent + * @hw: the original clock that got the rate request + * @old_req: the original clk_rate_request structure we want to forward + * @parent: the clk we want to forward @old_req to + * @req: the clk_rate_request structure we want to initialise + * @parent_rate: The rate which is to be requested to @parent + * + * Initializes a clk_rate_request structure to submit to a clock parent + * in __clk_determine_rate() or similar functions. + */ +void clk_hw_forward_rate_request(const struct clk_hw *hw, + const struct clk_rate_request *old_req, + const struct clk_hw *parent, + struct clk_rate_request *req, + unsigned long parent_rate) +{ + if (WARN_ON(!hw || !old_req || !parent || !req)) + return; + + clk_core_forward_rate_req(hw->core, old_req, + parent->core, req, + parent_rate); +} + static bool clk_core_can_round(struct clk_core * const core) { return core->ops->determine_rate || core->ops->round_rate; @@ -1457,6 +1513,8 @@ static bool clk_core_can_round(struct clk_core * const core) static int clk_core_round_rate_nolock(struct clk_core *core, struct clk_rate_request *req) { + int ret; + lockdep_assert_held(&prepare_lock); if (!core) { @@ -1466,8 +1524,20 @@ static int clk_core_round_rate_nolock(struct clk_core *core, if (clk_core_can_round(core)) return clk_core_determine_round_nolock(core, req); - else if (core->flags & CLK_SET_RATE_PARENT) - return clk_core_round_rate_nolock(core->parent, req); + + if (core->flags & CLK_SET_RATE_PARENT) { + struct clk_rate_request parent_req; + + clk_core_forward_rate_req(core, req, core->parent, &parent_req, req->rate); + ret = clk_core_round_rate_nolock(core->parent, &parent_req); + if (ret) + return ret; + + req->best_parent_rate = parent_req.rate; + req->rate = parent_req.rate; + + return 0; + } req->rate = core->rate; return 0; diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 7068517428e2..3004ef368bd7 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -1024,6 +1024,36 @@ clk_test_single_parent_mux_set_range_disjoint_parent_last(struct kunit *test) clk_put(clk); } +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set a range on the parent and then call + * clk_round_rate(), the boundaries of the parent are taken into + * account. + */ +static void +clk_test_single_parent_mux_set_range_round_rate_parent_only(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(parent, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2); + + clk_put(clk); +} + /* * Test that for a clock that can't modify its rate and with a single * parent, if we set a range on the parent and a more restrictive one on @@ -1062,12 +1092,52 @@ clk_test_single_parent_mux_set_range_round_rate_child_smaller(struct kunit *test clk_put(clk); } +/* + * Test that for a clock that can't modify its rate and with a single + * parent, if we set a range on the child and a more restrictive one on + * the parent, and then call clk_round_rate(), the boundaries of the + * two clocks are taken into account. + */ +static void +clk_test_single_parent_mux_set_range_round_rate_parent_smaller(struct kunit *test) +{ + struct clk_single_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent; + unsigned long rate; + int ret; + + parent = clk_get_parent(clk); + KUNIT_ASSERT_PTR_NE(test, parent, NULL); + + ret = clk_set_rate_range(parent, DUMMY_CLOCK_RATE_1 + 1000, DUMMY_CLOCK_RATE_2 - 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, DUMMY_CLOCK_RATE_1, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2 - 1000); + + rate = clk_round_rate(clk, DUMMY_CLOCK_RATE_2 + 1000); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_2 - 1000); + + clk_put(clk); +} + static struct kunit_case clk_single_parent_mux_test_cases[] = { KUNIT_CASE(clk_test_single_parent_mux_get_parent), KUNIT_CASE(clk_test_single_parent_mux_has_parent), KUNIT_CASE(clk_test_single_parent_mux_set_range_disjoint_child_last), KUNIT_CASE(clk_test_single_parent_mux_set_range_disjoint_parent_last), KUNIT_CASE(clk_test_single_parent_mux_set_range_round_rate_child_smaller), + KUNIT_CASE(clk_test_single_parent_mux_set_range_round_rate_parent_only), + KUNIT_CASE(clk_test_single_parent_mux_set_range_round_rate_parent_smaller), {} }; @@ -2005,7 +2075,119 @@ static struct kunit_suite clk_range_minimize_test_suite = { .test_cases = clk_range_minimize_test_cases, }; +struct clk_leaf_mux_ctx { + struct clk_multiple_parent_ctx mux_ctx; + struct clk_hw hw; +}; + +static int +clk_leaf_mux_set_rate_parent_test_init(struct kunit *test) +{ + struct clk_leaf_mux_ctx *ctx; + const char *top_parents[2] = { "parent-0", "parent-1" }; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + + ctx->mux_ctx.parents_ctx[0].hw.init = CLK_HW_INIT_NO_PARENT("parent-0", + &clk_dummy_rate_ops, + 0); + ctx->mux_ctx.parents_ctx[0].rate = DUMMY_CLOCK_RATE_1; + ret = clk_hw_register(NULL, &ctx->mux_ctx.parents_ctx[0].hw); + if (ret) + return ret; + + ctx->mux_ctx.parents_ctx[1].hw.init = CLK_HW_INIT_NO_PARENT("parent-1", + &clk_dummy_rate_ops, + 0); + ctx->mux_ctx.parents_ctx[1].rate = DUMMY_CLOCK_RATE_2; + ret = clk_hw_register(NULL, &ctx->mux_ctx.parents_ctx[1].hw); + if (ret) + return ret; + + ctx->mux_ctx.current_parent = 0; + ctx->mux_ctx.hw.init = CLK_HW_INIT_PARENTS("test-mux", top_parents, + &clk_multiple_parents_mux_ops, + 0); + ret = clk_hw_register(NULL, &ctx->mux_ctx.hw); + if (ret) + return ret; + + ctx->hw.init = CLK_HW_INIT_HW("test-clock", &ctx->mux_ctx.hw, + &clk_dummy_single_parent_ops, + CLK_SET_RATE_PARENT); + ret = clk_hw_register(NULL, &ctx->hw); + if (ret) + return ret; + + return 0; +} + +static void clk_leaf_mux_set_rate_parent_test_exit(struct kunit *test) +{ + struct clk_leaf_mux_ctx *ctx = test->priv; + + clk_hw_unregister(&ctx->hw); + clk_hw_unregister(&ctx->mux_ctx.hw); + clk_hw_unregister(&ctx->mux_ctx.parents_ctx[0].hw); + clk_hw_unregister(&ctx->mux_ctx.parents_ctx[1].hw); +} + +/* + * Test that, for a clock that will forward any rate request to its + * parent, the rate request structure returned by __clk_determine_rate + * is sane and will be what we expect. + */ +static void clk_leaf_mux_set_rate_parent_determine_rate(struct kunit *test) +{ + struct clk_leaf_mux_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk_rate_request req; + unsigned long rate; + int ret; + + rate = clk_get_rate(clk); + KUNIT_ASSERT_EQ(test, rate, DUMMY_CLOCK_RATE_1); + + clk_hw_init_rate_request(hw, &req, DUMMY_CLOCK_RATE_2); + + ret = __clk_determine_rate(hw, &req); + KUNIT_ASSERT_EQ(test, ret, 0); + + KUNIT_EXPECT_EQ(test, req.rate, DUMMY_CLOCK_RATE_2); + KUNIT_EXPECT_EQ(test, req.best_parent_rate, DUMMY_CLOCK_RATE_2); + KUNIT_EXPECT_PTR_EQ(test, req.best_parent_hw, &ctx->mux_ctx.hw); + + clk_put(clk); +} + +static struct kunit_case clk_leaf_mux_set_rate_parent_test_cases[] = { + KUNIT_CASE(clk_leaf_mux_set_rate_parent_determine_rate), + {} +}; + +/* + * Test suite for a clock whose parent is a mux with multiple parents. + * The leaf clock has CLK_SET_RATE_PARENT, and will forward rate + * requests to the mux, which will then select which parent is the best + * fit for a given rate. + * + * These tests exercise the behaviour of muxes, and the proper selection + * of parents. + */ +static struct kunit_suite clk_leaf_mux_set_rate_parent_test_suite = { + .name = "clk-leaf-mux-set-rate-parent", + .init = clk_leaf_mux_set_rate_parent_test_init, + .exit = clk_leaf_mux_set_rate_parent_test_exit, + .test_cases = clk_leaf_mux_set_rate_parent_test_cases, +}; + kunit_test_suites( + &clk_leaf_mux_set_rate_parent_test_suite, &clk_test_suite, &clk_multiple_parents_mux_test_suite, &clk_orphan_transparent_multiple_parent_mux_test_suite, diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index d857717aa386..8bce6c524f29 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -65,6 +65,11 @@ struct clk_rate_request { void clk_hw_init_rate_request(const struct clk_hw *hw, struct clk_rate_request *req, unsigned long rate); +void clk_hw_forward_rate_request(const struct clk_hw *core, + const struct clk_rate_request *old_req, + const struct clk_hw *parent, + struct clk_rate_request *req, + unsigned long parent_rate); /** * struct clk_duty - Struture encoding the duty cycle ratio of a clock -- cgit From b46fd8dbe8ad3fe6dcd44dcdf01a736c50d90a68 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:27 +0200 Subject: clk: Zero the clk_rate_request structure In order to make sure we don't carry anything over from an already existing clk_rate_request pointer we would pass to clk_core_init_rate_req(), let's zero the entire structure before initializing it. Tested-by: Alexander Stein # imx8mp Tested-by: Marek Szyprowski # exynos4210, meson g12b Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-23-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 3f60eb836980..6b358448885b 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1447,6 +1447,8 @@ static void clk_core_init_rate_req(struct clk_core * const core, if (WARN_ON(!core || !req)) return; + memset(req, 0, sizeof(*req)); + req->rate = rate; clk_core_get_boundaries(core, &req->min_rate, &req->max_rate); -- cgit From 253993253466ba7187730b196174146d5247e97b Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:28 +0200 Subject: clk: Introduce the clk_hw_get_rate_range function Some clock providers are hand-crafting their clk_rate_request, and need to figure out the current boundaries of their clk_hw to fill it properly. Let's create such a function for clock providers. Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-24-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 16 ++++++++++++++++ include/linux/clk-provider.h | 2 ++ 2 files changed, 18 insertions(+) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 6b358448885b..ec518dc5d462 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -684,6 +684,22 @@ static void clk_core_get_boundaries(struct clk_core *core, *max_rate = min(*max_rate, clk_user->max_rate); } +/* + * clk_hw_get_rate_range() - returns the clock rate range for a hw clk + * @hw: the hw clk we want to get the range from + * @min_rate: pointer to the variable that will hold the minimum + * @max_rate: pointer to the variable that will hold the maximum + * + * Fills the @min_rate and @max_rate variables with the minimum and + * maximum that clock can reach. + */ +void clk_hw_get_rate_range(struct clk_hw *hw, unsigned long *min_rate, + unsigned long *max_rate) +{ + clk_core_get_boundaries(hw->core, min_rate, max_rate); +} +EXPORT_SYMBOL_GPL(clk_hw_get_rate_range); + static bool clk_core_check_boundaries(struct clk_core *core, unsigned long min_rate, unsigned long max_rate) diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 8bce6c524f29..8724a3547a79 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1267,6 +1267,8 @@ int clk_mux_determine_rate_flags(struct clk_hw *hw, struct clk_rate_request *req, unsigned long flags); void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent); +void clk_hw_get_rate_range(struct clk_hw *hw, unsigned long *min_rate, + unsigned long *max_rate); void clk_hw_set_rate_range(struct clk_hw *hw, unsigned long min_rate, unsigned long max_rate); -- cgit From af1e62f2ffe2b7fa90653f273efced0e0eabf7cc Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:29 +0200 Subject: clk: qcom: clk-rcg2: Take clock boundaries into consideration for gfx3d The gfx3d clock is hand-crafting its own clk_rate_request in clk_gfx3d_determine_rate to pass to the parent of that clock. However, since the clk_rate_request is zero'd at creation, it will have a max_rate of 0 which will break any code depending on the clock boundaries. That includes the recent commit 948fb0969eae ("clk: Always clamp the rounded rate") which will clamp the rate given to clk_round_rate() to the current clock boundaries. For the gfx3d clock, it means that since both the min_rate and max_rate fields are set at zero, clk_round_rate() now always return 0. Let's initialize the min_rate and max_rate fields properly for that clock. Fixes: 948fb0969eae ("clk: Always clamp the rounded rate") Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-25-maxime@cerno.tech Tested-by: Linux Kernel Functional Testing Tested-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- drivers/clk/qcom/clk-rcg2.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index 28019edd2a50..ee536b457952 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -908,6 +908,15 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, req->best_parent_hw = p2; } + clk_hw_get_rate_range(req->best_parent_hw, + &parent_req.min_rate, &parent_req.max_rate); + + if (req->min_rate > parent_req.min_rate) + parent_req.min_rate = req->min_rate; + + if (req->max_rate < parent_req.max_rate) + parent_req.max_rate = req->max_rate; + ret = __clk_determine_rate(req->best_parent_hw, &parent_req); if (ret) return ret; -- cgit From 433fb8a611ca2a32112668225beabda2302c9634 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 16 Aug 2022 13:25:30 +0200 Subject: clk: tests: Add missing test case for ranges Let's add a test on the rate range after a reparenting. This fails for now, but it's worth having it to document the corner cases we don't support yet. Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20220816112530.1837489-26-maxime@cerno.tech Tested-by: Naresh Kamboju Tested-by: Linux Kernel Functional Testing Signed-off-by: Stephen Boyd --- drivers/clk/clk_test.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 3004ef368bd7..509256c5567a 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -514,9 +514,62 @@ clk_test_multiple_parents_mux_has_parent(struct kunit *test) clk_put(clk); } +/* + * Test that for a clock with a multiple parents, if we set a range on + * that clock and the parent is changed, its rate after the reparenting + * is still within the range we asked for. + * + * FIXME: clk_set_parent() only does the reparenting but doesn't + * reevaluate whether the new clock rate is within its boundaries or + * not. + */ +static void +clk_test_multiple_parents_mux_set_range_set_parent_get_rate(struct kunit *test) +{ + struct clk_multiple_parent_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *parent1, *parent2; + unsigned long rate; + int ret; + + kunit_skip(test, "This needs to be fixed in the core."); + + parent1 = clk_hw_get_clk(&ctx->parents_ctx[0].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent1); + KUNIT_ASSERT_TRUE(test, clk_is_match(clk_get_parent(clk), parent1)); + + parent2 = clk_hw_get_clk(&ctx->parents_ctx[1].hw, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, parent2); + + ret = clk_set_rate(parent1, DUMMY_CLOCK_RATE_1); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate(parent2, DUMMY_CLOCK_RATE_2); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_rate_range(clk, + DUMMY_CLOCK_RATE_1 - 1000, + DUMMY_CLOCK_RATE_1 + 1000); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = clk_set_parent(clk, parent2); + KUNIT_ASSERT_EQ(test, ret, 0); + + rate = clk_get_rate(clk); + KUNIT_ASSERT_GT(test, rate, 0); + KUNIT_EXPECT_GE(test, rate, DUMMY_CLOCK_RATE_1 - 1000); + KUNIT_EXPECT_LE(test, rate, DUMMY_CLOCK_RATE_1 + 1000); + + clk_put(parent2); + clk_put(parent1); + clk_put(clk); +} + static struct kunit_case clk_multiple_parents_mux_test_cases[] = { KUNIT_CASE(clk_test_multiple_parents_mux_get_parent), KUNIT_CASE(clk_test_multiple_parents_mux_has_parent), + KUNIT_CASE(clk_test_multiple_parents_mux_set_range_set_parent_get_rate), {} }; -- cgit From 714e76347a4e0bbd39730ddbb2c7e56971ba7caa Mon Sep 17 00:00:00 2001 From: Benjamin Beichler Date: Tue, 7 Jun 2022 11:27:14 +0000 Subject: um: read multiple msg from virtio slave request fd If VHOST_USER_PROTOCOL_F_INBAND_NOTIFICATIONS is activated, the user mode linux virtio irq handler only read one msg from the corresponding socket. This creates issues, when the device emulation creates multiple call requests (e.g. for multiple virtqueues), as the socket buffer tend to fill up and the call requests are delayed. This creates a deadlock situation, when the device simulation blocks, because of sending a msg and the kernel side blocks because of synchronously waiting for an acknowledge of kick request. Actually inband notifications are meant to be used in combination with the time travel protocol, but it is not required, therefore this corner case needs to be handled. Anyways, in general it seems to be more natural to consume always all messages from a socket, instead of only a single one. Fixes: 2cd097ba8c05 ("um: virtio: Implement VHOST_USER_PROTOCOL_F_SLAVE_REQ") Signed-off-by: Benjamin Beichler Reviewed-by: Johannes Berg Signed-off-by: Richard Weinberger --- arch/um/drivers/virtio_uml.c | 71 +++++++++++++++++++++++--------------------- 1 file changed, 37 insertions(+), 34 deletions(-) diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index e719af8bdf56..588930a0ced1 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -374,45 +374,48 @@ static irqreturn_t vu_req_read_message(struct virtio_uml_device *vu_dev, u8 extra_payload[512]; } msg; int rc; + irqreturn_t irq_rc = IRQ_NONE; - rc = vhost_user_recv_req(vu_dev, &msg.msg, - sizeof(msg.msg.payload) + - sizeof(msg.extra_payload)); - - vu_dev->recv_rc = rc; - if (rc) - return IRQ_NONE; - - switch (msg.msg.header.request) { - case VHOST_USER_SLAVE_CONFIG_CHANGE_MSG: - vu_dev->config_changed_irq = true; - response = 0; - break; - case VHOST_USER_SLAVE_VRING_CALL: - virtio_device_for_each_vq((&vu_dev->vdev), vq) { - if (vq->index == msg.msg.payload.vring_state.index) { - response = 0; - vu_dev->vq_irq_vq_map |= BIT_ULL(vq->index); - break; + while (1) { + rc = vhost_user_recv_req(vu_dev, &msg.msg, + sizeof(msg.msg.payload) + + sizeof(msg.extra_payload)); + if (rc) + break; + + switch (msg.msg.header.request) { + case VHOST_USER_SLAVE_CONFIG_CHANGE_MSG: + vu_dev->config_changed_irq = true; + response = 0; + break; + case VHOST_USER_SLAVE_VRING_CALL: + virtio_device_for_each_vq((&vu_dev->vdev), vq) { + if (vq->index == msg.msg.payload.vring_state.index) { + response = 0; + vu_dev->vq_irq_vq_map |= BIT_ULL(vq->index); + break; + } } + break; + case VHOST_USER_SLAVE_IOTLB_MSG: + /* not supported - VIRTIO_F_ACCESS_PLATFORM */ + case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG: + /* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */ + default: + vu_err(vu_dev, "unexpected slave request %d\n", + msg.msg.header.request); } - break; - case VHOST_USER_SLAVE_IOTLB_MSG: - /* not supported - VIRTIO_F_ACCESS_PLATFORM */ - case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG: - /* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */ - default: - vu_err(vu_dev, "unexpected slave request %d\n", - msg.msg.header.request); - } - - if (ev && !vu_dev->suspended) - time_travel_add_irq_event(ev); - if (msg.msg.header.flags & VHOST_USER_FLAG_NEED_REPLY) - vhost_user_reply(vu_dev, &msg.msg, response); + if (ev && !vu_dev->suspended) + time_travel_add_irq_event(ev); - return IRQ_HANDLED; + if (msg.msg.header.flags & VHOST_USER_FLAG_NEED_REPLY) + vhost_user_reply(vu_dev, &msg.msg, response); + irq_rc = IRQ_HANDLED; + }; + /* mask EAGAIN as we try non-blocking read until socket is empty */ + vu_dev->recv_rc = (rc == -EAGAIN) ? 0 : rc; + return irq_rc; } static irqreturn_t vu_req_interrupt(int irq, void *data) -- cgit From 16c546e148fa6d14a019431436a6f7b4087dbccd Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 12 Jul 2022 15:52:55 +0800 Subject: UM: cpuinfo: Fix a warning for CONFIG_CPUMASK_OFFSTACK When CONFIG_CPUMASK_OFFSTACK and CONFIG_DEBUG_PER_CPU_MAPS is selected, cpu_max_bits_warn() generates a runtime warning similar as below while we show /proc/cpuinfo. Fix this by using nr_cpu_ids (the runtime limit) instead of NR_CPUS to iterate CPUs. [ 3.052463] ------------[ cut here ]------------ [ 3.059679] WARNING: CPU: 3 PID: 1 at include/linux/cpumask.h:108 show_cpuinfo+0x5e8/0x5f0 [ 3.070072] Modules linked in: efivarfs autofs4 [ 3.076257] CPU: 0 PID: 1 Comm: systemd Not tainted 5.19-rc5+ #1052 [ 3.099465] Stack : 9000000100157b08 9000000000f18530 9000000000cf846c 9000000100154000 [ 3.109127] 9000000100157a50 0000000000000000 9000000100157a58 9000000000ef7430 [ 3.118774] 90000001001578e8 0000000000000040 0000000000000020 ffffffffffffffff [ 3.128412] 0000000000aaaaaa 1ab25f00eec96a37 900000010021de80 900000000101c890 [ 3.138056] 0000000000000000 0000000000000000 0000000000000000 0000000000aaaaaa [ 3.147711] ffff8000339dc220 0000000000000001 0000000006ab4000 0000000000000000 [ 3.157364] 900000000101c998 0000000000000004 9000000000ef7430 0000000000000000 [ 3.167012] 0000000000000009 000000000000006c 0000000000000000 0000000000000000 [ 3.176641] 9000000000d3de08 9000000001639390 90000000002086d8 00007ffff0080286 [ 3.186260] 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1c [ 3.195868] ... [ 3.199917] Call Trace: [ 3.203941] [<90000000002086d8>] show_stack+0x38/0x14c [ 3.210666] [<9000000000cf846c>] dump_stack_lvl+0x60/0x88 [ 3.217625] [<900000000023d268>] __warn+0xd0/0x100 [ 3.223958] [<9000000000cf3c90>] warn_slowpath_fmt+0x7c/0xcc [ 3.231150] [<9000000000210220>] show_cpuinfo+0x5e8/0x5f0 [ 3.238080] [<90000000004f578c>] seq_read_iter+0x354/0x4b4 [ 3.245098] [<90000000004c2e90>] new_sync_read+0x17c/0x1c4 [ 3.252114] [<90000000004c5174>] vfs_read+0x138/0x1d0 [ 3.258694] [<90000000004c55f8>] ksys_read+0x70/0x100 [ 3.265265] [<9000000000cfde9c>] do_syscall+0x7c/0x94 [ 3.271820] [<9000000000202fe4>] handle_syscall+0xc4/0x160 [ 3.281824] ---[ end trace 8b484262b4b8c24c ]--- Cc: stable@vger.kernel.org Signed-off-by: Huacai Chen Signed-off-by: Richard Weinberger --- arch/um/kernel/um_arch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index e0de60e503b9..11df93731857 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -96,7 +96,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - return *pos < NR_CPUS ? cpu_data + *pos : NULL; + return *pos < nr_cpu_ids ? cpu_data + *pos : NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) -- cgit From 0d644e918532f7eba2b02e0eaf60ee1a1b20a856 Mon Sep 17 00:00:00 2001 From: Christian Lamparter Date: Sat, 6 Aug 2022 21:52:23 +0200 Subject: um: increase default virtual physical memory to 64 MiB The current 32 MiB of RAM causes OOMs to appear shortly after booting in a minimal OpenWrt 22.03 configuration with a 5.10.134 kernel. Of course, passing a "mem=64M" (from the --help text) parameter works too, but it produces the following (info) message: | [ 0.000000] Unknown kernel command line parameters "mem=64M", will be passed to user space. That's why, I think it would be nicer, if this is working out of the box again :). Signed-off-by: Christian Lamparter Signed-off-by: Richard Weinberger --- arch/um/kernel/um_arch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 11df93731857..207f195dff56 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -132,7 +132,7 @@ static int have_root __initdata; static int have_console __initdata; /* Set in uml_mem_setup and modified in linux_main */ -long long physmem_size = 32 * 1024 * 1024; +long long physmem_size = 64 * 1024 * 1024; EXPORT_SYMBOL(physmem_size); static const char *usage_string = -- cgit From e6e4d33f380fbfd85b909d16c9b639299e5c37a6 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 18 Aug 2022 22:59:51 +0200 Subject: um: move from strlcpy with unused retval to strscpy Follow the advice of the below link and prefer 'strscpy' in this subsystem. Conversion is 1:1 because the return value is not used. Generated by a coccinelle script. Link: https://lore.kernel.org/r/CAHk-=wgfRnXz0W3D37d01q3JFkr_i_uTL=V6A6G1oUZcprmknw@mail.gmail.com/ Signed-off-by: Wolfram Sang Signed-off-by: Richard Weinberger --- arch/um/drivers/net_kern.c | 2 +- arch/um/drivers/vector_kern.c | 2 +- arch/um/kernel/um_arch.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 59331384c2d3..3d7836c46507 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -265,7 +265,7 @@ static void uml_net_poll_controller(struct net_device *dev) static void uml_net_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver)); + strscpy(info->driver, DRIVER_NAME, sizeof(info->driver)); } static const struct ethtool_ops uml_net_ethtool_ops = { diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 548265312743..ded7c47d2fbe 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1372,7 +1372,7 @@ static void vector_net_poll_controller(struct net_device *dev) static void vector_net_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver)); + strscpy(info->driver, DRIVER_NAME, sizeof(info->driver)); } static int vector_net_load_bpf_flash(struct net_device *dev, diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 207f195dff56..0f2adc9a95a2 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -416,7 +416,7 @@ void __init setup_arch(char **cmdline_p) read_initrd(); paging_init(); - strlcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); + strscpy(boot_command_line, command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; setup_hostinfo(host_info, sizeof host_info); -- cgit From b7f28a37a59fb0ae35dc087b9cdfa77d089b996b Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Thu, 18 Aug 2022 23:01:17 +0200 Subject: hostfs: move from strlcpy with unused retval to strscpy Follow the advice of the below link and prefer 'strscpy' in this subsystem. Conversion is 1:1 because the return value is not used. Generated by a coccinelle script. Link: https://lore.kernel.org/r/CAHk-=wgfRnXz0W3D37d01q3JFkr_i_uTL=V6A6G1oUZcprmknw@mail.gmail.com/ Signed-off-by: Wolfram Sang Signed-off-by: Richard Weinberger --- fs/hostfs/hostfs_kern.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 07881b76d42f..277468783fee 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -103,7 +103,7 @@ static char *__dentry_name(struct dentry *dentry, char *name) */ BUG_ON(p + strlen(p) + 1 != name + PATH_MAX); - strlcpy(name, root, PATH_MAX); + strscpy(name, root, PATH_MAX); if (len > p - name) { __putname(name); return NULL; -- cgit From 98639412fee2fda3c9da184825b469e5ac874829 Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Sun, 11 Sep 2022 10:51:40 +0800 Subject: um: virt-pci: add __init/__exit annotations to module init/exit funcs Add missing __init/__exit annotations to module init/exit funcs. Signed-off-by: Xiu Jianfeng Signed-off-by: Richard Weinberger --- arch/um/drivers/virt-pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 027847023184..acb55b302b14 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -857,7 +857,7 @@ void *pci_root_bus_fwnode(struct pci_bus *bus) return um_pci_fwnode; } -static int um_pci_init(void) +static int __init um_pci_init(void) { int err, i; @@ -940,7 +940,7 @@ free: } module_init(um_pci_init); -static void um_pci_exit(void) +static void __exit um_pci_exit(void) { unregister_virtio_driver(&um_pci_virtio_driver); irq_domain_remove(um_pci_msi_domain); -- cgit From 7c5c8faeab4db1eecc181e01ccc7c16b1ec24b99 Mon Sep 17 00:00:00 2001 From: Xiu Jianfeng Date: Sun, 11 Sep 2022 10:52:38 +0800 Subject: um: mmaper: add __exit annotations to module exit funcs Add missing __exit annotations to module exit funcs. Signed-off-by: Xiu Jianfeng Signed-off-by: Richard Weinberger --- arch/um/drivers/mmapper_kern.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/drivers/mmapper_kern.c b/arch/um/drivers/mmapper_kern.c index 0bf78ff89011..807cd3358740 100644 --- a/arch/um/drivers/mmapper_kern.c +++ b/arch/um/drivers/mmapper_kern.c @@ -122,7 +122,7 @@ static int __init mmapper_init(void) return 0; } -static void mmapper_exit(void) +static void __exit mmapper_exit(void) { misc_deregister(&mmapper_dev); } -- cgit From c8b2c268b0b77cb6aad676bf215f49212d903b2a Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Wed, 14 Sep 2022 15:30:27 +0800 Subject: um: remove unused reactivate_chan() declaration All uses of reactivate_chan() were removed by commit 940b241d9050 ("um: Remove obsolete reenable_XX calls"), so remove the declaration, too. Signed-off-by: Gaosheng Cui Acked-By: Anton Ivanov Signed-off-by: Richard Weinberger --- arch/um/drivers/chan.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/um/drivers/chan.h b/arch/um/drivers/chan.h index c37cc4f26f91..3fec3b8406e9 100644 --- a/arch/um/drivers/chan.h +++ b/arch/um/drivers/chan.h @@ -36,7 +36,6 @@ extern int console_write_chan(struct chan *chan, const char *buf, int len); extern int console_open_chan(struct line *line, struct console *co); extern void deactivate_chan(struct chan *chan, int irq); -extern void reactivate_chan(struct chan *chan, int irq); extern void chan_enable_winch(struct chan *chan, struct tty_port *port); extern int enable_chan(struct line *line); extern void close_chan(struct line *line); -- cgit From 758dfdb9185cf94160f20e85bbe05583e3cd4ff4 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Fri, 19 Aug 2022 19:17:24 -0300 Subject: um: Improve panic notifiers consistency and ordering Currently the panic notifiers from user mode linux don't follow the convention for most of the other notifiers present in the kernel (indentation, priority setting, numeric return). More important, the priorities could be improved, since it's a special case (userspace), hence we could run the notifiers earlier; user mode linux shouldn't care much with other panic notifiers but the ordering among the mconsole and arch notifier is important, given that the arch one effectively triggers a core dump. Fix that by running the mconsole notifier as the first panic notifier, followed by the architecture one (that coredumps). Cc: Anton Ivanov Cc: Johannes Berg Cc: Richard Weinberger Signed-off-by: Guilherme G. Piccoli V3: - No changes. V2: - Kept the notifier header to avoid implicit usage - thanks Johannes for the suggestion! Signed-off-by: Richard Weinberger --- arch/um/drivers/mconsole_kern.c | 7 +++---- arch/um/kernel/um_arch.c | 8 ++++---- 2 files changed, 7 insertions(+), 8 deletions(-) diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 8ca67a692683..69af3ce8407a 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -846,13 +846,12 @@ static int notify_panic(struct notifier_block *self, unsigned long unused1, mconsole_notify(notify_socket, MCONSOLE_PANIC, message, strlen(message) + 1); - return 0; + return NOTIFY_DONE; } static struct notifier_block panic_exit_notifier = { - .notifier_call = notify_panic, - .next = NULL, - .priority = 1 + .notifier_call = notify_panic, + .priority = INT_MAX, /* run as soon as possible */ }; static int add_notifier(void) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 0f2adc9a95a2..754d29a387a8 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -247,13 +247,13 @@ static int panic_exit(struct notifier_block *self, unsigned long unused1, bust_spinlocks(0); uml_exitcode = 1; os_dump_core(); - return 0; + + return NOTIFY_DONE; } static struct notifier_block panic_exit_notifier = { - .notifier_call = panic_exit, - .next = NULL, - .priority = 0 + .notifier_call = panic_exit, + .priority = INT_MAX - 1, /* run as 2nd notifier, won't return */ }; void uml_finishsetup(void) -- cgit From 3848d470cb881b7954a4a563bf73ffeb9cf4f30e Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 15 Jul 2022 12:29:38 +0800 Subject: um: Fix comment typo The double `in' is duplicated in line 172, remove one. Signed-off-by: Jason Wang Signed-off-by: Richard Weinberger --- arch/um/kernel/physmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index e7c7b53a1435..91485119ae67 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -169,7 +169,7 @@ __uml_setup("iomem=", parse_iomem, ); /* - * This list is constructed in parse_iomem and addresses filled in in + * This list is constructed in parse_iomem and addresses filled in * setup_iomem, both of which run during early boot. Afterwards, it's * unchanged. */ -- cgit From 4dc5a328315a6acbb60e772fb4826d87626a793d Mon Sep 17 00:00:00 2001 From: Xin Gao Date: Thu, 21 Jul 2022 03:24:51 +0800 Subject: um: Do not initialise statics to 0. do not initialise statics to 0. Signed-off-by: Xin Gao Signed-off-by: Richard Weinberger --- arch/um/drivers/mconsole_kern.c | 2 +- arch/um/drivers/ssl.c | 2 +- arch/um/drivers/stdio_console.c | 2 +- arch/um/drivers/ubd_kern.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 69af3ce8407a..5026e7b9adfe 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -283,7 +283,7 @@ struct unplugged_pages { }; static DEFINE_MUTEX(plug_mem_mutex); -static unsigned long long unplugged_pages_count = 0; +static unsigned long long unplugged_pages_count; static LIST_HEAD(unplugged_pages); static int unplug_index = UNPLUGGED_PER_PAGE; diff --git a/arch/um/drivers/ssl.c b/arch/um/drivers/ssl.c index 8514966778d5..277cea3d30eb 100644 --- a/arch/um/drivers/ssl.c +++ b/arch/um/drivers/ssl.c @@ -106,7 +106,7 @@ static const struct tty_operations ssl_ops = { /* Changed by ssl_init and referenced by ssl_exit, which are both serialized * by being an initcall and exitcall, respectively. */ -static int ssl_init_done = 0; +static int ssl_init_done; static void ssl_console_write(struct console *c, const char *string, unsigned len) diff --git a/arch/um/drivers/stdio_console.c b/arch/um/drivers/stdio_console.c index 489d5a746ed3..1c239737d88e 100644 --- a/arch/um/drivers/stdio_console.c +++ b/arch/um/drivers/stdio_console.c @@ -88,7 +88,7 @@ static int con_remove(int n, char **error_out) } /* Set in an initcall, checked in an exitcall */ -static int con_init_done = 0; +static int con_init_done; static int con_install(struct tty_driver *driver, struct tty_struct *tty) { diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index eb2d2f0f0bcc..f4c1e6e97ad5 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1555,7 +1555,7 @@ static void do_io(struct io_thread_req *req, struct io_desc *desc) int kernel_fd = -1; /* Only changed by the io thread. XXX: currently unused. */ -static int io_count = 0; +static int io_count; int io_thread(void *arg) { -- cgit From 193cb8372424184dde28088a4230a5fed0afb0ad Mon Sep 17 00:00:00 2001 From: Shaomin Deng Date: Sat, 27 Aug 2022 12:26:31 -0400 Subject: uml: Remove the initialization of statics to 0 It is always unnecessary to initialise statics to 0. Signed-off-by: Shaomin Deng Signed-off-by: Richard Weinberger --- arch/um/kernel/umid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/kernel/umid.c b/arch/um/kernel/umid.c index 8031a038eb58..72bc60ade347 100644 --- a/arch/um/kernel/umid.c +++ b/arch/um/kernel/umid.c @@ -9,7 +9,7 @@ #include /* Changed by set_umid_arg */ -static int umid_inited = 0; +static int umid_inited; static int __init set_umid_arg(char *name, int *add) { -- cgit From a84b280f195df83124eea755132df072c1e15c46 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Mon, 19 Sep 2022 14:14:28 +0800 Subject: nvdimm/region: Fix kernel-doc drivers/nvdimm/region_devs.c:1103: warning: expecting prototype for nvdimm_flush(). Prototype was for generic_nvdimm_flush() instead. Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=2209 Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Link: https://lore.kernel.org/r/20220919061428.102883-1-jiapeng.chong@linux.alibaba.com Signed-off-by: Dan Williams --- drivers/nvdimm/region_devs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 473a71bbd9c9..70f1a23cbe31 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -1096,7 +1096,7 @@ int nvdimm_flush(struct nd_region *nd_region, struct bio *bio) return rc; } /** - * nvdimm_flush - flush any posted write queues between the cpu and pmem media + * generic_nvdimm_flush() - flush any posted write queues between the cpu and pmem media * @nd_region: interleaved pmem region */ int generic_nvdimm_flush(struct nd_region *nd_region) -- cgit From 7912d30fbb1a9df7e99eb7a5991582512e65927c Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Wed, 14 Sep 2022 14:12:51 +0800 Subject: nvdimm: make __nvdimm_security_overwrite_query static This symbol is not used outside of security.c, so marks it static. drivers/nvdimm/security.c:411:6: warning: no previous prototype for function '__nvdimm_security_overwrite_query'. Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=2148 Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Link: https://lore.kernel.org/r/20220914061251.42052-1-jiapeng.chong@linux.alibaba.com Signed-off-by: Dan Williams --- drivers/nvdimm/security.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvdimm/security.c b/drivers/nvdimm/security.c index b5aa55c61461..8aefb60c42ff 100644 --- a/drivers/nvdimm/security.c +++ b/drivers/nvdimm/security.c @@ -408,7 +408,7 @@ static int security_overwrite(struct nvdimm *nvdimm, unsigned int keyid) return rc; } -void __nvdimm_security_overwrite_query(struct nvdimm *nvdimm) +static void __nvdimm_security_overwrite_query(struct nvdimm *nvdimm) { struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nvdimm->dev); int rc; -- cgit From 23a2d0c5944896ce9123f36ab62d7ca64c8b25ff Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 3 Aug 2022 04:19:18 +0800 Subject: nvdimm/namespace: Fix comment typo The double `existing' is duplicated in the comment, remove one. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20220802201918.8408-1-wangborong@cdjrlc.com Signed-off-by: Dan Williams --- drivers/nvdimm/namespace_devs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index bf4f5c09d9b1..847816992b9e 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -388,7 +388,7 @@ static resource_size_t init_dpa_allocation(struct nd_label_id *label_id, * * BLK-space is valid as long as it does not precede a PMEM * allocation in a given region. PMEM-space must be contiguous - * and adjacent to an existing existing allocation (if one + * and adjacent to an existing allocation (if one * exists). If reserving PMEM any space is valid. */ static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd, -- cgit From 27ef523a6653b35270296114dc50a9f630d896a9 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Thu, 13 Jan 2022 09:36:22 +0800 Subject: ubifs: Fix ubifs_check_dir_empty() kernel-doc comment Fix function name in fs/ubifs/dir.c kernel-doc comment to remove warning found by running scripts/kernel-doc, which is caused by using 'make W=1'. fs/ubifs/dir.c:883: warning: expecting prototype for check_dir_empty(). Prototype was for ubifs_check_dir_empty() instead Reported-by: Abaci Robot Signed-off-by: Yang Li Signed-off-by: Richard Weinberger --- fs/ubifs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 86151889548e..7306f88b2c7e 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -872,7 +872,7 @@ out_fname: } /** - * check_dir_empty - check if a directory is empty or not. + * ubifs_check_dir_empty - check if a directory is empty or not. * @dir: VFS inode object of the directory to check * * This function checks if directory @dir is empty. Returns zero if the -- cgit From 6c97bb345f163e45a8e4a14acc9391be0beaa6bb Mon Sep 17 00:00:00 2001 From: Li zeming Date: Wed, 17 Aug 2022 09:14:06 +0800 Subject: ubi: block: Remove in vain semicolon Remove the repeated ';' from code, it is not needed. Signed-off-by: Li zeming Reviewed-by: Zhihao Cheng [rw: Massaged commit message a bit] Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/block.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 4cf67a2a0d04..4fc7e756d885 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -409,7 +409,7 @@ int ubiblock_create(struct ubi_volume_info *vi) ret = blk_mq_alloc_tag_set(&dev->tag_set); if (ret) { dev_err(disk_to_dev(dev->gd), "blk_mq_alloc_tag_set failed"); - goto out_free_dev;; + goto out_free_dev; } -- cgit From 818f9e8353c8e60dd0876bdac445e8fad346e50a Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Thu, 11 Aug 2022 21:57:30 +0800 Subject: ubi: ubi-media.h: Fix comment typo The double `the' is duplicated in the comment, remove one. Signed-off-by: Jason Wang Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/ubi-media.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/ubi-media.h b/drivers/mtd/ubi/ubi-media.h index 386db0598e95..2c9cd3b6434f 100644 --- a/drivers/mtd/ubi/ubi-media.h +++ b/drivers/mtd/ubi/ubi-media.h @@ -131,7 +131,7 @@ enum { * is changed radically. This field is duplicated in the volume identifier * header. * - * The @vid_hdr_offset and @data_offset fields contain the offset of the the + * The @vid_hdr_offset and @data_offset fields contain the offset of the * volume identifier header and user data, relative to the beginning of the * physical eraseblock. These values have to be the same for all physical * eraseblocks. -- cgit From ec1f97f501a746403990515bbefcaecd7562b042 Mon Sep 17 00:00:00 2001 From: Jilin Yuan Date: Wed, 10 Aug 2022 21:38:56 +0800 Subject: ubi: Fix repeated words in comments Delete the redundant word 'a'. Delete the redundant word 'the'. Signed-off-by: Jilin Yuan Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/cdev.c | 2 +- drivers/mtd/ubi/eba.c | 2 +- drivers/mtd/ubi/io.c | 2 +- drivers/mtd/ubi/ubi.h | 6 +++--- drivers/mtd/ubi/wl.c | 6 +++--- 5 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index cc9a28cf9d82..1d3bbcfb4bb5 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -672,7 +672,7 @@ static int verify_rsvol_req(const struct ubi_device *ubi, * @req: volumes re-name request * * This is a helper function for the volume re-name IOCTL which validates the - * the request, opens the volume and calls corresponding volumes management + * request, opens the volume and calls corresponding volumes management * function. Returns zero in case of success and a negative error code in case * of failure. */ diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index ccc5979642b7..09c408c45a62 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -377,7 +377,7 @@ static int leb_write_lock(struct ubi_device *ubi, int vol_id, int lnum) * * This function locks a logical eraseblock for writing if there is no * contention and does nothing if there is contention. Returns %0 in case of - * success, %1 in case of contention, and and a negative error code in case of + * success, %1 in case of contention, and a negative error code in case of * failure. */ static int leb_write_trylock(struct ubi_device *ubi, int vol_id, int lnum) diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c index 8a7306cc1947..01b644861253 100644 --- a/drivers/mtd/ubi/io.c +++ b/drivers/mtd/ubi/io.c @@ -1147,7 +1147,7 @@ fail: * @ubi: UBI device description object * @pnum: the physical eraseblock number to check * - * This function returns zero if the erase counter header is all right and and + * This function returns zero if the erase counter header is all right and * a negative error code if not or if an error occurred. */ static int self_check_peb_ec_hdr(const struct ubi_device *ubi, int pnum) diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index 078112e23dfd..0110eb3d4db6 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -86,7 +86,7 @@ void ubi_err(const struct ubi_device *ubi, const char *fmt, ...); * Error codes returned by the I/O sub-system. * * UBI_IO_FF: the read region of flash contains only 0xFFs - * UBI_IO_FF_BITFLIPS: the same as %UBI_IO_FF, but also also there was a data + * UBI_IO_FF_BITFLIPS: the same as %UBI_IO_FF, but also there was a data * integrity error reported by the MTD driver * (uncorrectable ECC error in case of NAND) * UBI_IO_BAD_HDR: the EC or VID header is corrupted (bad magic or CRC) @@ -281,7 +281,7 @@ struct ubi_eba_leb_desc { /** * struct ubi_volume - UBI volume description data structure. - * @dev: device object to make use of the the Linux device model + * @dev: device object to make use of the Linux device model * @cdev: character device object to create character device * @ubi: reference to the UBI device description object * @vol_id: volume ID @@ -439,7 +439,7 @@ struct ubi_debug_info { /** * struct ubi_device - UBI device description structure - * @dev: UBI device object to use the the Linux device model + * @dev: UBI device object to use the Linux device model * @cdev: character device object to create character device * @ubi_num: UBI device number * @ubi_name: UBI device name diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 55bae06cf408..0fadd55beee0 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -376,7 +376,7 @@ static struct ubi_wl_entry *find_mean_wl_entry(struct ubi_device *ubi, * refill_wl_user_pool(). * @ubi: UBI device description object * - * This function returns a a wear leveling entry in case of success and + * This function returns a wear leveling entry in case of success and * NULL in case of failure. */ static struct ubi_wl_entry *wl_get_wle(struct ubi_device *ubi) @@ -429,7 +429,7 @@ static int prot_queue_del(struct ubi_device *ubi, int pnum) /** * sync_erase - synchronously erase a physical eraseblock. * @ubi: UBI device description object - * @e: the the physical eraseblock to erase + * @e: the physical eraseblock to erase * @torture: if the physical eraseblock has to be tortured * * This function returns zero in case of success and a negative error code in @@ -1016,7 +1016,7 @@ static int ensure_wear_leveling(struct ubi_device *ubi, int nested) /* * If the ubi->scrub tree is not empty, scrubbing is needed, and the - * the WL worker has to be scheduled anyway. + * WL worker has to be scheduled anyway. */ if (!ubi->scrub.rb_node) { #ifdef CONFIG_MTD_UBI_FASTMAP -- cgit From b58b25280003f078f9b861656ca097074267f75a Mon Sep 17 00:00:00 2001 From: Zhang Jiaming Date: Mon, 4 Jul 2022 10:13:56 +0800 Subject: ubi: fastmap: Fix typo in comments There are a typo(dont't) in comments. Fix it. Signed-off-by: Zhang Jiaming Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/wl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 0fadd55beee0..68eb0f21b3fe 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -1464,7 +1464,7 @@ static bool scrub_possible(struct ubi_device *ubi, struct ubi_wl_entry *e) * ubi_bitflip_check - Check an eraseblock for bitflips and scrub it if needed. * @ubi: UBI device description object * @pnum: the physical eraseblock to schedule - * @force: dont't read the block, assume bitflips happened and take action. + * @force: don't read the block, assume bitflips happened and take action. * * This function reads the given eraseblock and checks if bitflips occured. * In case of bitflips, the eraseblock is scheduled for scrubbing. -- cgit From e079be2c354aede45ce130027264611b276dcef1 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Mon, 14 Mar 2022 12:53:37 +0100 Subject: ubi: block: Fix typos in comments Various spelling mistakes in comments. Detected with the help of Coccinelle. Signed-off-by: Julia Lawall Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/block.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 4fc7e756d885..75eaecc8639f 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -441,7 +441,7 @@ int ubiblock_create(struct ubi_volume_info *vi) /* * Create one workqueue per volume (per registered block device). - * Rembember workqueues are cheap, they're not threads. + * Remember workqueues are cheap, they're not threads. */ dev->wq = alloc_workqueue("%s", 0, 0, gd->disk_name); if (!dev->wq) { -- cgit From 019ac05e4c97f51913318d9b0e2ffd34db917d3c Mon Sep 17 00:00:00 2001 From: Jiang Jian Date: Thu, 23 Jun 2022 15:19:53 +0800 Subject: mtd: ubi: drop unexpected word 'a' in comments there is an unexpected word 'a' in the comments that need to be dropped file - drivers/mtd/ubi/vmt.c line - 626,779 * Returns zero if volume is all right and a a negative error code if not. changed to: * Returns zero if volume is all right and a negative error code if not. Signed-off-by: Jiang Jian Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/vmt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 6ea95ade4ca6..8fcc0bdf0635 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -623,7 +623,7 @@ void ubi_free_volume(struct ubi_device *ubi, struct ubi_volume *vol) * @ubi: UBI device description object * @vol_id: volume ID * - * Returns zero if volume is all right and a a negative error code if not. + * Returns zero if volume is all right and a negative error code if not. */ static int self_check_volume(struct ubi_device *ubi, int vol_id) { @@ -776,7 +776,7 @@ fail: * self_check_volumes - check information about all volumes. * @ubi: UBI device description object * - * Returns zero if volumes are all right and a a negative error code if not. + * Returns zero if volumes are all right and a negative error code if not. */ static int self_check_volumes(struct ubi_device *ubi) { -- cgit From 713346ca1db2bebd4c7c4d5ea364ed03d504f5ed Mon Sep 17 00:00:00 2001 From: ZhaoLong Wang Date: Sat, 9 Jul 2022 16:40:32 +0800 Subject: ubifs: Fix UBIFS ro fail due to truncate in the encrypted directory The ubifs_compress() function does not compress the data When the data length is short than 128 bytes or the compressed data length is not ideal.It cause that the compressed length of the truncated data in the truncate_data_node() function may be greater than the length of the raw data read from the flash. The above two lengths are transferred to the ubifs_encrypt() function as parameters. This may lead to assertion fails and then the file system becomes read-only. This patch use the actual length of the data in the memory as the input parameter for assert comparison, which avoids the problem. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216213 Signed-off-by: ZhaoLong Wang Signed-off-by: Richard Weinberger --- fs/ubifs/crypto.c | 11 +++++++++++ fs/ubifs/journal.c | 28 +++++++++++++++++----------- 2 files changed, 28 insertions(+), 11 deletions(-) diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c index c57b46a352d8..3125e76376ee 100644 --- a/fs/ubifs/crypto.c +++ b/fs/ubifs/crypto.c @@ -24,6 +24,17 @@ static bool ubifs_crypt_empty_dir(struct inode *inode) return ubifs_check_dir_empty(inode) == 0; } +/** + * ubifs_encrypt - Encrypt data. + * @inode: inode which refers to the data node + * @dn: data node to encrypt + * @in_len: length of data to be compressed + * @out_len: allocated memory size for the data area of @dn + * @block: logical block number of the block + * + * This function encrypt a possibly-compressed data in the data node. + * The encrypted data length will store in @out_len. + */ int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn, unsigned int in_len, unsigned int *out_len, int block) { diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 75dab0ae3939..2b1d7c4297bf 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -1472,23 +1472,25 @@ out_free: * @block: data block number * @dn: data node to re-compress * @new_len: new length + * @dn_size: size of the data node @dn in memory * * This function is used when an inode is truncated and the last data node of * the inode has to be re-compressed/encrypted and re-written. */ static int truncate_data_node(const struct ubifs_info *c, const struct inode *inode, unsigned int block, struct ubifs_data_node *dn, - int *new_len) + int *new_len, int dn_size) { void *buf; - int err, dlen, compr_type, out_len, old_dlen; + int err, dlen, compr_type, out_len, data_size; out_len = le32_to_cpu(dn->size); buf = kmalloc_array(out_len, WORST_COMPR_FACTOR, GFP_NOFS); if (!buf) return -ENOMEM; - dlen = old_dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ; + dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ; + data_size = dn_size - UBIFS_DATA_NODE_SZ; compr_type = le16_to_cpu(dn->compr_type); if (IS_ENCRYPTED(inode)) { @@ -1508,11 +1510,11 @@ static int truncate_data_node(const struct ubifs_info *c, const struct inode *in } if (IS_ENCRYPTED(inode)) { - err = ubifs_encrypt(inode, dn, out_len, &old_dlen, block); + err = ubifs_encrypt(inode, dn, out_len, &data_size, block); if (err) goto out; - out_len = old_dlen; + out_len = data_size; } else { dn->compr_size = 0; } @@ -1550,6 +1552,7 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, struct ubifs_trun_node *trun; struct ubifs_data_node *dn; int err, dlen, len, lnum, offs, bit, sz, sync = IS_SYNC(inode); + int dn_size; struct ubifs_inode *ui = ubifs_inode(inode); ino_t inum = inode->i_ino; unsigned int blk; @@ -1562,10 +1565,13 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, ubifs_assert(c, S_ISREG(inode->i_mode)); ubifs_assert(c, mutex_is_locked(&ui->ui_mutex)); - sz = UBIFS_TRUN_NODE_SZ + UBIFS_INO_NODE_SZ + - UBIFS_MAX_DATA_NODE_SZ * WORST_COMPR_FACTOR; + dn_size = COMPRESSED_DATA_NODE_BUF_SZ; - sz += ubifs_auth_node_sz(c); + if (IS_ENCRYPTED(inode)) + dn_size += UBIFS_CIPHER_BLOCK_SIZE; + + sz = UBIFS_TRUN_NODE_SZ + UBIFS_INO_NODE_SZ + + dn_size + ubifs_auth_node_sz(c); ino = kmalloc(sz, GFP_NOFS); if (!ino) @@ -1596,15 +1602,15 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, if (dn_len <= 0 || dn_len > UBIFS_BLOCK_SIZE) { ubifs_err(c, "bad data node (block %u, inode %lu)", blk, inode->i_ino); - ubifs_dump_node(c, dn, sz - UBIFS_INO_NODE_SZ - - UBIFS_TRUN_NODE_SZ); + ubifs_dump_node(c, dn, dn_size); goto out_free; } if (dn_len <= dlen) dlen = 0; /* Nothing to do */ else { - err = truncate_data_node(c, inode, blk, dn, &dlen); + err = truncate_data_node(c, inode, blk, dn, + &dlen, dn_size); if (err) goto out_free; } -- cgit From a0c51565730729f0df2ee886e34b4da6d359a10b Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 19 Jul 2022 16:00:17 +0800 Subject: ubifs: Fix AA deadlock when setting xattr for encrypted file Following process: vfs_setxattr(host) ubifs_xattr_set down_write(host_ui->xattr_sem) <- lock first time create_xattr ubifs_new_inode(host) fscrypt_prepare_new_inode(host) fscrypt_policy_to_inherit(host) if (IS_ENCRYPTED(inode)) fscrypt_require_key(host) fscrypt_get_encryption_info(host) ubifs_xattr_get(host) down_read(host_ui->xattr_sem) <- AA deadlock , which may trigger an AA deadlock problem: [ 102.620871] INFO: task setfattr:1599 blocked for more than 10 seconds. [ 102.625298] Not tainted 5.19.0-rc7-00001-gb666b6823ce0-dirty #711 [ 102.628732] task:setfattr state:D stack: 0 pid: 1599 [ 102.628749] Call Trace: [ 102.628753] [ 102.628776] __schedule+0x482/0x1060 [ 102.629964] schedule+0x92/0x1a0 [ 102.629976] rwsem_down_read_slowpath+0x287/0x8c0 [ 102.629996] down_read+0x84/0x170 [ 102.630585] ubifs_xattr_get+0xd1/0x370 [ubifs] [ 102.630730] ubifs_crypt_get_context+0x1f/0x30 [ubifs] [ 102.630791] fscrypt_get_encryption_info+0x7d/0x1c0 [ 102.630810] fscrypt_policy_to_inherit+0x56/0xc0 [ 102.630817] fscrypt_prepare_new_inode+0x35/0x160 [ 102.630830] ubifs_new_inode+0xcc/0x4b0 [ubifs] [ 102.630873] ubifs_xattr_set+0x591/0x9f0 [ubifs] [ 102.630961] xattr_set+0x8c/0x3e0 [ubifs] [ 102.631003] __vfs_setxattr+0x71/0xc0 [ 102.631026] vfs_setxattr+0x105/0x270 [ 102.631034] do_setxattr+0x6d/0x110 [ 102.631041] setxattr+0xa0/0xd0 [ 102.631087] __x64_sys_setxattr+0x2f/0x40 Fetch a reproducer in [Link]. Just like ext4 does, which skips encrypting for inode with EXT4_EA_INODE_FL flag. Stop encypting xattr inode for ubifs. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216260 Fixes: f4e3634a3b64222 ("ubifs: Fix races between xattr_{set|get} ...") Fixes: d475a507457b5ca ("ubifs: Add skeleton for fscrypto") Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- fs/ubifs/dir.c | 25 ++++++++++++++----------- fs/ubifs/ubifs.h | 2 +- fs/ubifs/xattr.c | 2 +- 3 files changed, 16 insertions(+), 13 deletions(-) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 7306f88b2c7e..8d0f68f8907c 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -68,13 +68,14 @@ static int inherit_flags(const struct inode *dir, umode_t mode) * @c: UBIFS file-system description object * @dir: parent directory inode * @mode: inode mode flags + * @is_xattr: whether the inode is xattr inode * * This function finds an unused inode number, allocates new inode and * initializes it. Returns new inode in case of success and an error code in * case of failure. */ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, - umode_t mode) + umode_t mode, bool is_xattr) { int err; struct inode *inode; @@ -99,10 +100,12 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, current_time(inode); inode->i_mapping->nrpages = 0; - err = fscrypt_prepare_new_inode(dir, inode, &encrypted); - if (err) { - ubifs_err(c, "fscrypt_prepare_new_inode failed: %i", err); - goto out_iput; + if (!is_xattr) { + err = fscrypt_prepare_new_inode(dir, inode, &encrypted); + if (err) { + ubifs_err(c, "fscrypt_prepare_new_inode failed: %i", err); + goto out_iput; + } } switch (mode & S_IFMT) { @@ -309,7 +312,7 @@ static int ubifs_create(struct user_namespace *mnt_userns, struct inode *dir, sz_change = CALC_DENT_SIZE(fname_len(&nm)); - inode = ubifs_new_inode(c, dir, mode); + inode = ubifs_new_inode(c, dir, mode, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_fname; @@ -370,7 +373,7 @@ static struct inode *create_whiteout(struct inode *dir, struct dentry *dentry) if (err) return ERR_PTR(err); - inode = ubifs_new_inode(c, dir, mode); + inode = ubifs_new_inode(c, dir, mode, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_free; @@ -462,7 +465,7 @@ static int ubifs_tmpfile(struct user_namespace *mnt_userns, struct inode *dir, return err; } - inode = ubifs_new_inode(c, dir, mode); + inode = ubifs_new_inode(c, dir, mode, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_budg; @@ -1004,7 +1007,7 @@ static int ubifs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, sz_change = CALC_DENT_SIZE(fname_len(&nm)); - inode = ubifs_new_inode(c, dir, S_IFDIR | mode); + inode = ubifs_new_inode(c, dir, S_IFDIR | mode, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_fname; @@ -1091,7 +1094,7 @@ static int ubifs_mknod(struct user_namespace *mnt_userns, struct inode *dir, sz_change = CALC_DENT_SIZE(fname_len(&nm)); - inode = ubifs_new_inode(c, dir, mode); + inode = ubifs_new_inode(c, dir, mode, false); if (IS_ERR(inode)) { kfree(dev); err = PTR_ERR(inode); @@ -1173,7 +1176,7 @@ static int ubifs_symlink(struct user_namespace *mnt_userns, struct inode *dir, sz_change = CALC_DENT_SIZE(fname_len(&nm)); - inode = ubifs_new_inode(c, dir, S_IFLNK | S_IRWXUGO); + inode = ubifs_new_inode(c, dir, S_IFLNK | S_IRWXUGO, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_fname; diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 7d6d2f152e03..478bbbb5382f 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -2026,7 +2026,7 @@ int ubifs_update_time(struct inode *inode, struct timespec64 *time, int flags); /* dir.c */ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, - umode_t mode); + umode_t mode, bool is_xattr); int ubifs_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); int ubifs_check_dir_empty(struct inode *dir); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index e4c4761aff7f..3db8486e3725 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -110,7 +110,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host, if (err) return err; - inode = ubifs_new_inode(c, host, S_IFREG | S_IRWXUGO); + inode = ubifs_new_inode(c, host, S_IFREG | S_IRWXUGO, true); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out_budg; -- cgit From e7f35da21f6f8c6a8c7d262dd4e4bd32e3083f79 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 4 Jul 2022 20:46:00 +0200 Subject: ubi: fastmap: Use the bitmap API to allocate bitmaps Use bitmap_zalloc()/bitmap_free() instead of hand-writing them. It is less verbose and it improves the semantic. Signed-off-by: Christophe JAILLET Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/fastmap.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index 6e95c4b1473e..ca2d9efe62c3 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -20,8 +20,7 @@ static inline unsigned long *init_seen(struct ubi_device *ubi) if (!ubi_dbg_chk_fastmap(ubi)) return NULL; - ret = kcalloc(BITS_TO_LONGS(ubi->peb_count), sizeof(unsigned long), - GFP_KERNEL); + ret = bitmap_zalloc(ubi->peb_count, GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); @@ -34,7 +33,7 @@ static inline unsigned long *init_seen(struct ubi_device *ubi) */ static inline void free_seen(unsigned long *seen) { - kfree(seen); + bitmap_free(seen); } /** @@ -1108,8 +1107,7 @@ int ubi_fastmap_init_checkmap(struct ubi_volume *vol, int leb_count) if (!ubi->fast_attach) return 0; - vol->checkmap = kcalloc(BITS_TO_LONGS(leb_count), sizeof(unsigned long), - GFP_KERNEL); + vol->checkmap = bitmap_zalloc(leb_count, GFP_KERNEL); if (!vol->checkmap) return -ENOMEM; @@ -1118,7 +1116,7 @@ int ubi_fastmap_init_checkmap(struct ubi_volume *vol, int leb_count) void ubi_fastmap_destroy_checkmap(struct ubi_volume *vol) { - kfree(vol->checkmap); + bitmap_free(vol->checkmap); } /** -- cgit From fd6dd9584ed3ee6debf2e7f9c9e69ef09b368277 Mon Sep 17 00:00:00 2001 From: Bernardo Rodrigues Date: Sun, 5 Dec 2021 18:00:49 -0300 Subject: leds: pca963x: fix blink with hw acceleration LEDs would behave differently depending on the blink hardware acceleration configuration. This commit will make LEDs respond exactly the same independently of the hardware acceleration status. In other words, if you had two pca963x, side by side, one with blink hardware acceleration "ON" and the other "OFF; and performed some arbitrary sequence of API calls (e.g. turn on/off, change brightness, change blink mode, etc.) you probably would end with not matching LED states. 'pca963x software blink' and 'leds-gpio' behavior were used as reference. Actual chip used to validate this change: pca9634 Some of the unmatched behaviors being fixed are (when hw blink was "ON") - Leds would stop blinking when the brightness was changed. - Leds would persist their blinking mode even after being turned off (brightness = 0). - Leds would only blink if another led was solid (pca963x will be forced out of low power) Signed-off-by: Bernardo Rodrigues Signed-off-by: Pavel Machek --- drivers/leds/leds-pca963x.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c index 00aecd67e348..d8d866bcda19 100644 --- a/drivers/leds/leds-pca963x.c +++ b/drivers/leds/leds-pca963x.c @@ -101,6 +101,7 @@ struct pca963x_led { struct pca963x *chip; struct led_classdev led_cdev; int led_num; /* 0 .. 15 potentially */ + bool blinking; u8 gdc; u8 gfrq; }; @@ -129,12 +130,21 @@ static int pca963x_brightness(struct pca963x_led *led, switch (brightness) { case LED_FULL: - val = (ledout & ~mask) | (PCA963X_LED_ON << shift); + if (led->blinking) { + val = (ledout & ~mask) | (PCA963X_LED_GRP_PWM << shift); + ret = i2c_smbus_write_byte_data(client, + PCA963X_PWM_BASE + + led->led_num, + LED_FULL); + } else { + val = (ledout & ~mask) | (PCA963X_LED_ON << shift); + } ret = i2c_smbus_write_byte_data(client, ledout_addr, val); break; case LED_OFF: val = ledout & ~mask; ret = i2c_smbus_write_byte_data(client, ledout_addr, val); + led->blinking = false; break; default: ret = i2c_smbus_write_byte_data(client, @@ -144,7 +154,11 @@ static int pca963x_brightness(struct pca963x_led *led, if (ret < 0) return ret; - val = (ledout & ~mask) | (PCA963X_LED_PWM << shift); + if (led->blinking) + val = (ledout & ~mask) | (PCA963X_LED_GRP_PWM << shift); + else + val = (ledout & ~mask) | (PCA963X_LED_PWM << shift); + ret = i2c_smbus_write_byte_data(client, ledout_addr, val); break; } @@ -181,6 +195,7 @@ static void pca963x_blink(struct pca963x_led *led) } mutex_unlock(&led->chip->mutex); + led->blinking = true; } static int pca963x_power_state(struct pca963x_led *led) @@ -275,6 +290,8 @@ static int pca963x_blink_set(struct led_classdev *led_cdev, led->gfrq = gfrq; pca963x_blink(led); + led->led_cdev.brightness = LED_FULL; + pca963x_led_set(led_cdev, LED_FULL); *delay_on = time_on; *delay_off = time_off; @@ -337,6 +354,7 @@ static int pca963x_register_leds(struct i2c_client *client, led->led_cdev.brightness_set_blocking = pca963x_led_set; if (hw_blink) led->led_cdev.blink_set = pca963x_blink_set; + led->blinking = false; init_data.fwnode = child; /* for backwards compatibility */ -- cgit From 31fd7108302388d732973c58470d4be559d352ec Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 17 Feb 2022 18:43:57 +0100 Subject: dt-bindings: leds: Document mmc trigger The mmc subsystem supports triggering leds on card activity, document the trigger value here. The value is a pattern in this case. Signed-off-by: Marek Vasut Cc: Jacek Anaszewski Cc: Pavel Machek Cc: Rob Herring Cc: devicetree@vger.kernel.org To: linux-leds@vger.kernel.org Signed-off-by: Pavel Machek Reviewed-by: Rob Herring --- Documentation/devicetree/bindings/leds/common.yaml | 39 ++++++++++++---------- 1 file changed, 21 insertions(+), 18 deletions(-) diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml index 328952d7acbb..3c14a98430e1 100644 --- a/Documentation/devicetree/bindings/leds/common.yaml +++ b/Documentation/devicetree/bindings/leds/common.yaml @@ -79,24 +79,27 @@ properties: the LED. $ref: /schemas/types.yaml#/definitions/string - enum: - # LED will act as a back-light, controlled by the framebuffer system - - backlight - # LED will turn on (but for leds-gpio see "default-state" property in - # Documentation/devicetree/bindings/leds/leds-gpio.yaml) - - default-on - # LED "double" flashes at a load average based rate - - heartbeat - # LED indicates disk activity - - disk-activity - # LED indicates IDE disk activity (deprecated), in new implementations - # use "disk-activity" - - ide-disk - # LED flashes at a fixed, configurable rate - - timer - # LED alters the brightness for the specified duration with one software - # timer (requires "led-pattern" property) - - pattern + oneOf: + - enum: + # LED will act as a back-light, controlled by the framebuffer system + - backlight + # LED will turn on (but for leds-gpio see "default-state" property in + # Documentation/devicetree/bindings/leds/leds-gpio.yaml) + - default-on + # LED "double" flashes at a load average based rate + - heartbeat + # LED indicates disk activity + - disk-activity + # LED indicates IDE disk activity (deprecated), in new implementations + # use "disk-activity" + - ide-disk + # LED flashes at a fixed, configurable rate + - timer + # LED alters the brightness for the specified duration with one software + # timer (requires "led-pattern" property) + - pattern + # LED is triggered by SD/MMC activity + - pattern: "^mmc[0-9]+$" led-pattern: description: | -- cgit From 669d204469c46e91d99da24914130f78277a71d3 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 17 Aug 2022 11:27:35 +0800 Subject: ubi: fastmap: Add fastmap control support for 'UBI_IOCATT' ioctl [1] suggests that fastmap is suitable for large flash devices. Module parameter 'fm_autoconvert' is a coarse grained switch to enable all ubi devices to generate fastmap, which may turn on fastmap even for small flash devices. This patch imports a new field 'disable_fm' in struct 'ubi_attach_req' to support following situations by ioctl 'UBI_IOCATT'. [old functions] A. Disable 'fm_autoconvert': Disbable fastmap for all ubi devices B. Enable 'fm_autoconvert': Enable fastmap for all ubi devices [new function] C. Enable 'fm_autoconvert', set 'disable_fm' for given device: Don't create new fastmap and do full scan (existed fastmap will be destroyed) for the given ubi device. A simple test case in [2]. [1] http://www.linux-mtd.infradead.org/doc/ubi.html#L_fastmap [2] https://bugzilla.kernel.org/show_bug.cgi?id=216278 Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/build.c | 14 ++++++++++---- drivers/mtd/ubi/cdev.c | 2 +- drivers/mtd/ubi/ubi.h | 3 ++- include/uapi/mtd/ubi-user.h | 8 +++++++- 4 files changed, 20 insertions(+), 7 deletions(-) diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index a32050fecabf..a901f8edfa41 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -807,6 +807,7 @@ static int autoresize(struct ubi_device *ubi, int vol_id) * @ubi_num: number to assign to the new UBI device * @vid_hdr_offset: VID header offset * @max_beb_per1024: maximum expected number of bad PEB per 1024 PEBs + * @disable_fm: whether disable fastmap * * This function attaches MTD device @mtd_dev to UBI and assign @ubi_num number * to the newly created UBI device, unless @ubi_num is %UBI_DEV_NUM_AUTO, in @@ -814,11 +815,15 @@ static int autoresize(struct ubi_device *ubi, int vol_id) * automatically. Returns the new UBI device number in case of success and a * negative error code in case of failure. * + * If @disable_fm is true, ubi doesn't create new fastmap even the module param + * 'fm_autoconvert' is set, and existed old fastmap will be destroyed after + * doing full scanning. + * * Note, the invocations of this function has to be serialized by the * @ubi_devices_mutex. */ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, - int vid_hdr_offset, int max_beb_per1024) + int vid_hdr_offset, int max_beb_per1024, bool disable_fm) { struct ubi_device *ubi; int i, err; @@ -921,7 +926,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, UBI_FM_MIN_POOL_SIZE); ubi->fm_wl_pool.max_size = ubi->fm_pool.max_size / 2; - ubi->fm_disabled = !fm_autoconvert; + ubi->fm_disabled = (!fm_autoconvert || disable_fm) ? 1 : 0; if (fm_debug) ubi_enable_dbg_chk_fastmap(ubi); @@ -962,7 +967,7 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, if (!ubi->fm_buf) goto out_free; #endif - err = ubi_attach(ubi, 0); + err = ubi_attach(ubi, disable_fm ? 1 : 0); if (err) { ubi_err(ubi, "failed to attach mtd%d, error %d", mtd->index, err); @@ -1242,7 +1247,8 @@ static int __init ubi_init(void) mutex_lock(&ubi_devices_mutex); err = ubi_attach_mtd_dev(mtd, p->ubi_num, - p->vid_hdr_offs, p->max_beb_per1024); + p->vid_hdr_offs, p->max_beb_per1024, + false); mutex_unlock(&ubi_devices_mutex); if (err < 0) { pr_err("UBI error: cannot attach mtd%d\n", diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index 1d3bbcfb4bb5..f43430b9c1e6 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -1041,7 +1041,7 @@ static long ctrl_cdev_ioctl(struct file *file, unsigned int cmd, */ mutex_lock(&ubi_devices_mutex); err = ubi_attach_mtd_dev(mtd, req.ubi_num, req.vid_hdr_offset, - req.max_beb_per1024); + req.max_beb_per1024, !!req.disable_fm); mutex_unlock(&ubi_devices_mutex); if (err < 0) put_mtd_device(mtd); diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index 0110eb3d4db6..c8f1bd4fa100 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -937,7 +937,8 @@ int ubi_io_write_vid_hdr(struct ubi_device *ubi, int pnum, /* build.c */ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, - int vid_hdr_offset, int max_beb_per1024); + int vid_hdr_offset, int max_beb_per1024, + bool disable_fm); int ubi_detach_mtd_dev(int ubi_num, int anyway); struct ubi_device *ubi_get_device(int ubi_num); void ubi_put_device(struct ubi_device *ubi); diff --git a/include/uapi/mtd/ubi-user.h b/include/uapi/mtd/ubi-user.h index b69e9ba6742b..dcb179de4358 100644 --- a/include/uapi/mtd/ubi-user.h +++ b/include/uapi/mtd/ubi-user.h @@ -247,6 +247,7 @@ enum { * @vid_hdr_offset: VID header offset (use defaults if %0) * @max_beb_per1024: maximum expected number of bad PEB per 1024 PEBs * @padding: reserved for future, not used, has to be zeroed + * @disable_fm: whether disable fastmap * * This data structure is used to specify MTD device UBI has to attach and the * parameters it has to use. The number which should be assigned to the new UBI @@ -281,13 +282,18 @@ enum { * eraseblocks for new bad eraseblocks, but attempts to use available * eraseblocks (if any). The accepted range is 0-768. If 0 is given, the * default kernel value of %CONFIG_MTD_UBI_BEB_LIMIT will be used. + * + * If @disable_fm is not zero, ubi doesn't create new fastmap even the module + * param 'fm_autoconvert' is set, and existed old fastmap will be destroyed + * after doing full scanning. */ struct ubi_attach_req { __s32 ubi_num; __s32 mtd_num; __s32 vid_hdr_offset; __s16 max_beb_per1024; - __s8 padding[10]; + __s8 disable_fm; + __s8 padding[9]; }; /* -- cgit From 7ab72c597356be1e7f0f3d856e54ce78527f43c8 Mon Sep 17 00:00:00 2001 From: Andrew Bresticker Date: Thu, 15 Sep 2022 15:37:01 -0400 Subject: riscv: Make VM_WRITE imply VM_READ RISC-V does not presently have write-only mappings as that PTE bit pattern is considered reserved in the privileged spec, so allow handling of read faults in VMAs that have VM_WRITE without VM_READ in order to be consistent with other architectures that have similar limitations. Fixes: 2139619bcad7 ("riscv: mmap with PROT_WRITE but no PROT_READ is invalid") Reviewed-by: Atish Patra Signed-off-by: Andrew Bresticker Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220915193702.2201018-2-abrestic@rivosinc.com/ Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/fault.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index f2fbd1400b7c..d86f7cebd4a7 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -184,7 +184,8 @@ static inline bool access_error(unsigned long cause, struct vm_area_struct *vma) } break; case EXC_LOAD_PAGE_FAULT: - if (!(vma->vm_flags & VM_READ)) { + /* Write implies read */ + if (!(vma->vm_flags & (VM_READ | VM_WRITE))) { return true; } break; -- cgit From 9e2e6042a7ec6504fe8e366717afa2f40cf16488 Mon Sep 17 00:00:00 2001 From: Andrew Bresticker Date: Thu, 15 Sep 2022 15:37:02 -0400 Subject: riscv: Allow PROT_WRITE-only mmap() Commit 2139619bcad7 ("riscv: mmap with PROT_WRITE but no PROT_READ is invalid") made mmap() return EINVAL if PROT_WRITE was set wihtout PROT_READ with the justification that a write-only PTE is considered a reserved PTE permission bit pattern in the privileged spec. This check is unnecessary since we let VM_WRITE imply VM_READ on RISC-V, and it is inconsistent with other architectures that don't support write-only PTEs, creating a potential software portability issue. Just remove the check altogether and let PROT_WRITE imply PROT_READ as is the case on other architectures. Note that this also allows PROT_WRITE|PROT_EXEC mappings which were disallowed prior to the aforementioned commit; PROT_READ is implied in such mappings as well. Fixes: 2139619bcad7 ("riscv: mmap with PROT_WRITE but no PROT_READ is invalid") Reviewed-by: Atish Patra Signed-off-by: Andrew Bresticker Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220915193702.2201018-3-abrestic@rivosinc.com/ Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/sys_riscv.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 571556bb9261..5d3f2fbeb33c 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -18,9 +18,6 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; - if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ))) - return -EINVAL; - return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } -- cgit From 4d1632151bde847230a0bd2318806380d309655f Mon Sep 17 00:00:00 2001 From: Pavel Machek Date: Mon, 26 Sep 2022 23:16:37 +0200 Subject: leds: pca963: fix misleading indentation I'm getting warnings: /tmp/next/build/drivers/leds/leds-pca963x.c: In function 'pca963x_register_leds': /tmp/next/build/drivers/leds/leds-pca963x.c:355:3: error: this 'if' clause does not guard... +[-Werror=misleading-indentation] 355 | if (hw_blink) | ^~ /tmp/next/build/drivers/leds/leds-pca963x.c:357:4: note: ...this statement, but the latter is +misleadingly indented as if it were guarded by the 'if' 357 | led->blinking = false; | ^~~ cc1: all warnings being treated as errors Fix the indentation to make them go away. Signed-off-by: Pavel Machek --- drivers/leds/leds-pca963x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c index d8d866bcda19..a7e052c1db53 100644 --- a/drivers/leds/leds-pca963x.c +++ b/drivers/leds/leds-pca963x.c @@ -354,7 +354,7 @@ static int pca963x_register_leds(struct i2c_client *client, led->led_cdev.brightness_set_blocking = pca963x_led_set; if (hw_blink) led->led_cdev.blink_set = pca963x_blink_set; - led->blinking = false; + led->blinking = false; init_data.fwnode = child; /* for backwards compatibility */ -- cgit From a0d49a8f77f26609036a05e7832393b6279554db Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 27 Sep 2022 12:19:13 +0100 Subject: dt-bindings: riscv: microchip: document icicle reference design The icicle kit reference design's v2022.09 release made some changes to the memory map - including adding the ability to read the fabric clock controllers via the system controller bus & making the PCI controller work with upstream Linux. While the PCI was not working in the v2022.03 design, so nothing is broken there in terms of backwards compatibility, the fabric clocks used in the v2022.03 design were chosen by the individual run of the synthesis tool. In the v2022.09 reference design, the clocks are fixed to use the "north west" fabric Clock Conditioning Circuitry. In the v2022.10 release, the memory map on the DDR side is also changing, so to avoid making a breaking change here twice, jump over the v2022.09 release and straight to the v2022.10 one. Make use of a new compatible to denote that v2022.{09,10} reference design releases are not backwards compatible. Acked-by: Krzysztof Kozlowski Signed-off-by: Conor Dooley --- Documentation/devicetree/bindings/riscv/microchip.yaml | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/riscv/microchip.yaml b/Documentation/devicetree/bindings/riscv/microchip.yaml index 1aa7336a9672..5c1ad2108049 100644 --- a/Documentation/devicetree/bindings/riscv/microchip.yaml +++ b/Documentation/devicetree/bindings/riscv/microchip.yaml @@ -17,12 +17,18 @@ properties: $nodename: const: '/' compatible: - items: - - enum: - - microchip,mpfs-icicle-kit - - microchip,mpfs-icicle-reference-rtlv2203 - - sundance,polarberry - - const: microchip,mpfs + oneOf: + - items: + - enum: + - microchip,mpfs-icicle-reference-rtlv2203 + - microchip,mpfs-icicle-reference-rtlv2210 + - const: microchip,mpfs-icicle-kit + - const: microchip,mpfs + + - items: + - enum: + - sundance,polarberry + - const: microchip,mpfs additionalProperties: true -- cgit From 0ebdc51787dbb8ef8d259daa98b8fd35babf8970 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 27 Sep 2022 12:19:14 +0100 Subject: dt-bindings: riscv: microchip: document the aries m100pfsevp Add a compatible for the Aries Embedded M100PFSEVP SOM + EVK platform. Link: https://www.aries-embedded.com/polarfire-soc-fpga-microsemi-m100pfs-som-mpfs025t-pcie-serdes Signed-off-by: Conor Dooley Acked-by: Rob Herring --- Documentation/devicetree/bindings/riscv/microchip.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/riscv/microchip.yaml b/Documentation/devicetree/bindings/riscv/microchip.yaml index 5c1ad2108049..681cedc5578f 100644 --- a/Documentation/devicetree/bindings/riscv/microchip.yaml +++ b/Documentation/devicetree/bindings/riscv/microchip.yaml @@ -27,6 +27,7 @@ properties: - items: - enum: + - aries,m100pfsevp - sundance,polarberry - const: microchip,mpfs -- cgit From db3d481698efe8a7a943ecbba9491648c5a49ef3 Mon Sep 17 00:00:00 2001 From: Shravan Chippa Date: Tue, 27 Sep 2022 12:19:15 +0100 Subject: dt-bindings: riscv: microchip: document the sev kit Update devicetree bindings document with PolarFire SoC Video Kit, known by its "sev-kit" product code. Link: https://onlinedocs.microchip.com/pr/GUID-404D3738-DC76-46BA-8683-6A77E837C2DD-en-US-1/index.html?GUID-065AEBEE-7B2C-4895-8579-B1D73D797F06 Signed-off-by: Shravan Chippa Reviewed-by: Krzysztof Kozlowski Signed-off-by: Conor Dooley --- Documentation/devicetree/bindings/riscv/microchip.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/riscv/microchip.yaml b/Documentation/devicetree/bindings/riscv/microchip.yaml index 681cedc5578f..2b8c6a695e99 100644 --- a/Documentation/devicetree/bindings/riscv/microchip.yaml +++ b/Documentation/devicetree/bindings/riscv/microchip.yaml @@ -28,6 +28,7 @@ properties: - items: - enum: - aries,m100pfsevp + - microchip,mpfs-sev-kit - sundance,polarberry - const: microchip,mpfs -- cgit From f890e67f292db46c9bd5b5c004ba0f98761d1a33 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 27 Sep 2022 12:19:16 +0100 Subject: riscv: dts: microchip: add pci dma ranges for the icicle kit The recently removed, accidentally included, "matr0" property was used in place of a dma-ranges property. The PCI controller is non-functional with mainline Linux in the v2022.02 or later reference designs and has not worked without configuration of address-translation since v2021.08. Add the address translation that will be used by the v2022.09 reference design & update the compatible used by the dts. Since this change is not backwards compatible, update the compatible to denote this, jumping over v2022.09 directly to v2022.10. Signed-off-by: Conor Dooley --- arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi | 7 ++++++- arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts | 3 ++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index 0d28858b83f2..eec5aba43436 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -2,7 +2,8 @@ /* Copyright (c) 2020-2021 Microchip Technology Inc */ / { - compatible = "microchip,mpfs-icicle-reference-rtlv2203", "microchip,mpfs"; + compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit", + "microchip,mpfs"; core_pwm0: pwm@41000000 { compatible = "microchip,corepwm-rtl-v4"; @@ -37,3 +38,7 @@ clock-frequency = <125000000>; }; }; + +&pcie { + dma-ranges = <0x02000000 0x0 0x00000000 0x0 0x00000000 0x1 0x00000000>; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts index 044982a11df5..42d350fe6c6b 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts @@ -11,7 +11,8 @@ / { model = "Microchip PolarFire-SoC Icicle Kit"; - compatible = "microchip,mpfs-icicle-kit", "microchip,mpfs"; + compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit", + "microchip,mpfs"; aliases { ethernet0 = &mac1; -- cgit From 99d451a7db1624308bc9eb94b7befb3722f67b10 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 27 Sep 2022 12:19:17 +0100 Subject: riscv: dts: microchip: move the mpfs' pci node to -fabric.dtsi In today's edition of moving things around: The PCIe root port on PolarFire SoC is more part of the FPGA than of the Core Complex. It is located on the other side of the chip and, apart from its interrupts, most of its configuration is determined by the FPGA bitstream rather. This includes: - address translation in both directions - the addresses at which the config and data regions appear to the core complex - the clocks used by the AXI bus - the plic interrupt used Moving the PCIe node to the -fabric.dtsi makes it clearer than a singular configuration for root port is not correct & allows the base SoC dtsi to be more easily included. Signed-off-by: Conor Dooley --- .../boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi | 32 ++++++++++++++++++++-- .../boot/dts/microchip/mpfs-polarberry-fabric.dtsi | 29 ++++++++++++++++++++ arch/riscv/boot/dts/microchip/mpfs.dtsi | 30 -------------------- 3 files changed, 58 insertions(+), 33 deletions(-) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index eec5aba43436..688ef0fc5a64 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -37,8 +37,34 @@ #clock-cells = <0>; clock-frequency = <125000000>; }; -}; -&pcie { - dma-ranges = <0x02000000 0x0 0x00000000 0x0 0x00000000 0x1 0x00000000>; + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + dma-ranges = <0x02000000 0x0 0x00000000 0x0 0x00000000 0x1 0x00000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; }; diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi index 49380c428ec9..67303bc0e451 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi @@ -13,4 +13,33 @@ #clock-cells = <0>; clock-frequency = <125000000>; }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; }; diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi index 45e3cc659882..79fd8dfce96f 100644 --- a/arch/riscv/boot/dts/microchip/mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -464,36 +464,6 @@ status = "disabled"; }; - pcie: pcie@2000000000 { - compatible = "microchip,pcie-host-1.0"; - #address-cells = <0x3>; - #interrupt-cells = <0x1>; - #size-cells = <0x2>; - device_type = "pci"; - reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; - reg-names = "cfg", "apb"; - bus-range = <0x0 0x7f>; - interrupt-parent = <&plic>; - interrupts = <119>; - interrupt-map = <0 0 0 1 &pcie_intc 0>, - <0 0 0 2 &pcie_intc 1>, - <0 0 0 3 &pcie_intc 2>, - <0 0 0 4 &pcie_intc 3>; - interrupt-map-mask = <0 0 0 7>; - clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; - clock-names = "fic0", "fic1", "fic3"; - ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; - msi-parent = <&pcie>; - msi-controller; - microchip,axi-m-atr0 = <0x10 0x0>; - status = "disabled"; - pcie_intc: legacy-interrupt-controller { - #address-cells = <0>; - #interrupt-cells = <1>; - interrupt-controller; - }; - }; - mbox: mailbox@37020000 { compatible = "microchip,mpfs-mailbox"; reg = <0x0 0x37020000 0x0 0x1000>, <0x0 0x2000318C 0x0 0x40>; -- cgit From 6fc655ed4986f88b91e3f7b339222fc1c4ffba08 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 27 Sep 2022 12:19:18 +0100 Subject: riscv: dts: microchip: icicle: update pci address properties For the v2022.09 reference design the PCI root port's data region has been moved to FIC1 from FIC0. This is a shorter path, allowing for higher clock rates and improved through-put. As a result, the address at which the PCIe's data region appears to the core complex has changed. The config region's address is unchanged. As FIC0 is no longer used, its clock can be removed too. Signed-off-by: Conor Dooley --- arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index 688ef0fc5a64..9ca2ac4ad8e2 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -38,13 +38,13 @@ clock-frequency = <125000000>; }; - pcie: pcie@2000000000 { + pcie: pcie@3000000000 { compatible = "microchip,pcie-host-1.0"; #address-cells = <0x3>; #interrupt-cells = <0x1>; #size-cells = <0x2>; device_type = "pci"; - reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg = <0x30 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; reg-names = "cfg", "apb"; bus-range = <0x0 0x7f>; interrupt-parent = <&plic>; @@ -54,9 +54,9 @@ <0 0 0 3 &pcie_intc 2>, <0 0 0 4 &pcie_intc 3>; interrupt-map-mask = <0 0 0 7>; - clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; - clock-names = "fic0", "fic1", "fic3"; - ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + clocks = <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x30 0x8000000 0x0 0x80000000>; dma-ranges = <0x02000000 0x0 0x00000000 0x0 0x00000000 0x1 0x00000000>; msi-parent = <&pcie>; msi-controller; -- cgit From ab291621a8b85269496ae9a964b6d49cd1e030c8 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 27 Sep 2022 12:19:19 +0100 Subject: riscv: dts: microchip: icicle: re-jig fabric peripheral addresses When users try to add onto the reference design, they find that the current addresses that peripherals connected to Fabric InterConnect (FIC) 3 use are restrictive. For the v2022.09 reference design, the peripherals have been shifted down, leaving more contiguous address space for their custom IP/peripherals. Signed-off-by: Conor Dooley --- arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index 9ca2ac4ad8e2..35030ea330ee 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -5,18 +5,18 @@ compatible = "microchip,mpfs-icicle-reference-rtlv2210", "microchip,mpfs-icicle-kit", "microchip,mpfs"; - core_pwm0: pwm@41000000 { + core_pwm0: pwm@40000000 { compatible = "microchip,corepwm-rtl-v4"; - reg = <0x0 0x41000000 0x0 0xF0>; + reg = <0x0 0x40000000 0x0 0xF0>; microchip,sync-update-mask = /bits/ 32 <0>; #pwm-cells = <2>; clocks = <&fabric_clk3>; status = "disabled"; }; - i2c2: i2c@44000000 { + i2c2: i2c@40000200 { compatible = "microchip,corei2c-rtl-v7"; - reg = <0x0 0x44000000 0x0 0x1000>; + reg = <0x0 0x40000200 0x0 0x1000>; #address-cells = <1>; #size-cells = <0>; clocks = <&fabric_clk3>; -- cgit From fa52935abef422d119dda3c10c02787a86e6289d Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 27 Sep 2022 12:19:20 +0100 Subject: riscv: dts: microchip: reduce the fic3 clock rate For the v2022.09 release of the reference design, the fic3 clock rate been reduced from 62.5 MHz to 50 MHz as it allows timing to be closed significantly more quickly by customers who chose to build the reference design themselves. Signed-off-by: Conor Dooley --- arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index 35030ea330ee..b6bfe177ccb2 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -29,7 +29,7 @@ fabric_clk3: fabric-clk3 { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <62500000>; + clock-frequency = <50000000>; }; fabric_clk1: fabric-clk1 { -- cgit From 978a17d1a688db025275d282665ab3f39407191d Mon Sep 17 00:00:00 2001 From: Vattipalli Praveen Date: Tue, 27 Sep 2022 12:19:21 +0100 Subject: riscv: dts: microchip: add sevkit device tree Add a basic dts for the Microchip Smart Embedded Vision dev kit. The SEV kit is an upcoming first party board, featuring an MPFS250T and: - Dual Sony Camera Sensors (IMX334) - IEEE 802.11 b/g/n 20MHz (1x1) Wi-Fi - Bluetooth 5 Low Energy - 4 GB DDR4 x64 - 2 GB LPDDR4 x32 - 1 GB SPI Flash - 8 GB eMMC flash & SD card slot (multiplexed) - HDMI2.0 Video Input/Output - MIPI DSI Output - MIPI CSI-2 Input Link: https://onlinedocs.microchip.com/pr/GUID-404D3738-DC76-46BA-8683-6A77E837C2DD-en-US-1/index.html?GUID-065AEBEE-7B2C-4895-8579-B1D73D797F06 Signed-off-by: Vattipalli Praveen Signed-off-by: Conor Dooley --- arch/riscv/boot/dts/microchip/Makefile | 1 + .../boot/dts/microchip/mpfs-sev-kit-fabric.dtsi | 45 +++++++ arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts | 145 +++++++++++++++++++++ 3 files changed, 191 insertions(+) create mode 100644 arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts diff --git a/arch/riscv/boot/dts/microchip/Makefile b/arch/riscv/boot/dts/microchip/Makefile index 39aae7b04f1c..f18477b2e86d 100644 --- a/arch/riscv/boot/dts/microchip/Makefile +++ b/arch/riscv/boot/dts/microchip/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-icicle-kit.dtb dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-polarberry.dtb +dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-sev-kit.dtb obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi new file mode 100644 index 000000000000..8545baf4d129 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts new file mode 100644 index 000000000000..013cb666c72d --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-sev-kit-fabric.dtsi" + +/* Clock frequency (in Hz) of the rtcclk */ +#define MTIMER_FREQ 1000000 + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "Microchip PolarFire-SoC SEV Kit"; + compatible = "microchip,mpfs-sev-kit", "microchip,mpfs"; + + aliases { + ethernet0 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + cpus { + timebase-frequency = ; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + fabricbuf0ddrc: buffer@80000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0x80000000 0x0 0x2000000>; + }; + + fabricbuf1ddrnc: buffer@c4000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0xc4000000 0x0 0x4000000>; + }; + + fabricbuf2ddrncwcb: buffer@d4000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0xd4000000 0x0 0x4000000>; + }; + }; + + ddrc_cache: memory@1000000000 { + device_type = "memory"; + reg = <0x10 0x0 0x0 0x76000000>; + }; +}; + +&i2c0 { + status = "okay"; +}; + +&gpio2 { + interrupts = <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>; + status = "okay"; +}; + +&mac0 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy0>; + phy1: ethernet-phy@9 { + reg = <9>; + }; + phy0: ethernet-phy@8 { + reg = <8>; + }; +}; + +&mac1 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy1>; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + status = "okay"; + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + cap-mmc-highspeed; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; + +&syscontroller { + status = "okay"; +}; + +&usb { + status = "okay"; + dr_mode = "otg"; +}; -- cgit From d49166646e44064b694a2e631fcdba4f814746d9 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 27 Sep 2022 12:19:22 +0100 Subject: riscv: dts: microchip: add a devicetree for aries' m100pfsevp Add device trees for both configs used by the Aries Embedded M100PFSEVP. The M100OFSEVP consists of a MPFS250T on a SOM, featuring: - 2GB DDR4 SDRAM dedicated to the HMS - 512MB DDR4 SDRAM dedicated to the FPGA - 32 MB SPI NOR Flash - 4 GByte eMMC and a carrier board with: - 2x Gigabit Ethernet - USB - 2x UART - 2x CAN - TFT connector - HSMC extension connector - 3x PMOD extension connectors - microSD-card slot Link: https://www.aries-embedded.com/polarfire-soc-fpga-microsemi-m100pfs-som-mpfs025t-pcie-serdes Link: https://www.aries-embedded.com/evaluation-kit/fpga/polarfire-microchip-soc-fpga-m100pfsevp-riscv-hsmc-pmod Link: https://downloads.aries-embedded.de/products/M100PFS/Hardware/M100PFSEVP-Schematics.pdf Co-developed-by: Wolfgang Grandegger Signed-off-by: Wolfgang Grandegger Signed-off-by: Conor Dooley --- arch/riscv/boot/dts/microchip/Makefile | 1 + .../boot/dts/microchip/mpfs-m100pfs-fabric.dtsi | 45 ++++++ arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts | 179 +++++++++++++++++++++ 3 files changed, 225 insertions(+) create mode 100644 arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts diff --git a/arch/riscv/boot/dts/microchip/Makefile b/arch/riscv/boot/dts/microchip/Makefile index f18477b2e86d..7427a20934f3 100644 --- a/arch/riscv/boot/dts/microchip/Makefile +++ b/arch/riscv/boot/dts/microchip/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-icicle-kit.dtb +dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-m100pfsevp.dtb dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-polarberry.dtb dtb-$(CONFIG_SOC_MICROCHIP_POLARFIRE) += mpfs-sev-kit.dtb obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .o, $(dtb-y)) diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi new file mode 100644 index 000000000000..7b9ee13b6a3a --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43000000 0x0 0x10000>; + reg-names = "cfg", "apb"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts new file mode 100644 index 000000000000..184cb36a175e --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Original all-in-one devicetree: + * Copyright (C) 2021-2022 - Wolfgang Grandegger + * Rewritten to use includes: + * Copyright (C) 2022 - Conor Dooley + */ +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-m100pfs-fabric.dtsi" + +/* Clock frequency (in Hz) of the rtcclk */ +#define MTIMER_FREQ 1000000 + +/ { + model = "Aries Embedded M100PFEVPS"; + compatible = "aries,m100pfsevp", "microchip,mpfs"; + + aliases { + ethernet0 = &mac0; + ethernet1 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + gpio0 = &gpio0; + gpio1 = &gpio2; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + cpus { + timebase-frequency = ; + }; + + ddrc_cache_lo: memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x40000000>; + }; + ddrc_cache_hi: memory@1040000000 { + device_type = "memory"; + reg = <0x10 0x40000000 0x0 0x40000000>; + }; +}; + +&can0 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c1 { + status = "okay"; +}; + +&gpio0 { + interrupts = <13>, <14>, <15>, <16>, + <17>, <18>, <19>, <20>, + <21>, <22>, <23>, <24>, + <25>, <26>; + ngpios = <14>; + status = "okay"; + + pmic-irq-hog { + gpio-hog; + gpios = <13 0>; + input; + }; + + /* Set to low for eMMC, high for SD-card */ + mmc-sel-hog { + gpio-hog; + gpios = <12 0>; + output-high; + }; +}; + +&gpio2 { + interrupts = <13>, <14>, <15>, <16>, + <17>, <18>, <19>, <20>, + <21>, <22>, <23>, <24>, + <25>, <26>, <27>, <28>, + <29>, <30>, <31>, <32>, + <33>, <34>, <35>, <36>, + <37>, <38>, <39>, <40>, + <41>, <42>, <43>, <44>; + status = "okay"; +}; + +&mac0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mac1 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy1>; + phy1: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + max-frequency = <50000000>; + bus-width = <4>; + cap-mmc-highspeed; + cap-sd-highspeed; + no-1-8-v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + disable-wp; + status = "okay"; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&pcie { + status = "okay"; +}; + +&qspi { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&spi1 { + status = "okay"; +}; + +&syscontroller { + status = "okay"; +}; + +&usb { + status = "okay"; + dr_mode = "host"; +}; -- cgit From 6c1193301791d3fcc0ad9ff3b861a8216e00773b Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 27 Sep 2022 12:19:23 +0100 Subject: riscv: dts: microchip: update memory configuration for v2022.10 In the v2022.10 reference design, the seg registers are going to be changed, resulting in a required change to the memory map in Linux. A small 4M reservation is made at the end of 32-bit DDR to provide some memory for the HSS to use, so that it can cache its payload.bin between reboots of a specific context. Signed-off-by: Conor Dooley --- arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts index 42d350fe6c6b..31f88cb4d5e5 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts @@ -33,15 +33,26 @@ ddrc_cache_lo: memory@80000000 { device_type = "memory"; - reg = <0x0 0x80000000 0x0 0x2e000000>; + reg = <0x0 0x80000000 0x0 0x40000000>; status = "okay"; }; ddrc_cache_hi: memory@1000000000 { device_type = "memory"; - reg = <0x10 0x0 0x0 0x40000000>; + reg = <0x10 0x40000000 0x0 0x40000000>; status = "okay"; }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + hss_payload: region@BFC00000 { + reg = <0x0 0xBFC00000 0x0 0x400000>; + no-map; + }; + }; }; &core_pwm0 { -- cgit From 2e5021cc42ba26c98fe83b973d774a999fa4f219 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Tue, 30 Aug 2022 00:45:05 -0500 Subject: libnvdimm/region: Allow setting align attribute on regions without mappings The alignment constraint for namespace creation in a region was increased, from 2M to 16M, for non-PowerPC architectures in v5.7 with commit 2522afb86a8c ("libnvdimm/region: Introduce an 'align' attribute"). The thought behind the change was that region alignment should be uniform across all architectures and, since PowerPC had the largest alignment constraint of 16M, all architectures should conform to that alignment. The change regressed namespace creation in pre-defined regions that relied on 2M alignment but a workaround was provided in the form of a sysfs attribute, named 'align', that could be adjusted to a non-default alignment value. However, the sysfs attribute's store function returned an error (-ENXIO) when userspace attempted to change the alignment of a region that had no mappings. This affected 2M aligned regions of volatile memory that were defined in a device tree using "pmem-region" and created by the of_pmem_region_driver, since those regions do not contain mappings (ndr_mappings is 0). Allow userspace to set the align attribute on pre-existing regions that do not have mappings so that namespaces can still be within those regions, despite not being aligned to 16M. Link: https://lore.kernel.org/lkml/CA+CK2bDJ3hrWoE91L2wpAk+Yu0_=GtYw=4gLDDD7mxs321b_aA@mail.gmail.com Fixes: 2522afb86a8c ("libnvdimm/region: Introduce an 'align' attribute") Signed-off-by: Tyler Hicks Link: https://lore.kernel.org/r/20220830054505.1159488-1-tyhicks@linux.microsoft.com Signed-off-by: Dan Williams --- drivers/nvdimm/region_devs.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index 70f1a23cbe31..e0875d369762 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -509,16 +509,13 @@ static ssize_t align_store(struct device *dev, { struct nd_region *nd_region = to_nd_region(dev); unsigned long val, dpa; - u32 remainder; + u32 mappings, remainder; int rc; rc = kstrtoul(buf, 0, &val); if (rc) return rc; - if (!nd_region->ndr_mappings) - return -ENXIO; - /* * Ensure space-align is evenly divisible by the region * interleave-width because the kernel typically has no facility @@ -526,7 +523,8 @@ static ssize_t align_store(struct device *dev, * contribute to the tail capacity in system-physical-address * space for the namespace. */ - dpa = div_u64_rem(val, nd_region->ndr_mappings, &remainder); + mappings = max_t(u32, 1, nd_region->ndr_mappings); + dpa = div_u64_rem(val, mappings, &remainder); if (!is_power_of_2(dpa) || dpa < PAGE_SIZE || val > region_size(nd_region) || remainder) return -EINVAL; -- cgit From 0f702033a64bd3adcd57c9d5cf91ea64c08fad42 Mon Sep 17 00:00:00 2001 From: Bo Liu Date: Sun, 25 Sep 2022 21:26:35 -0400 Subject: dax: Remove usage of the deprecated ida_simple_xxx API ida_alloc_max() makes it clear that the second argument is inclusive, and the alloc/free terminology is more idiomatic and symmetric then get/remove. Signed-off-by: Bo Liu Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/20220926012635.3205-1-liubo03@inspur.com [djbw: reword changelog] Signed-off-by: Dan Williams --- drivers/dax/super.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 9b5e2a5eb0ae..da4438f3188c 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -363,7 +363,7 @@ static void dax_free_inode(struct inode *inode) { struct dax_device *dax_dev = to_dax_dev(inode); if (inode->i_rdev) - ida_simple_remove(&dax_minor_ida, iminor(inode)); + ida_free(&dax_minor_ida, iminor(inode)); kmem_cache_free(dax_cache, dax_dev); } @@ -445,7 +445,7 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) if (WARN_ON_ONCE(ops && !ops->zero_page_range)) return ERR_PTR(-EINVAL); - minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL); + minor = ida_alloc_max(&dax_minor_ida, MINORMASK, GFP_KERNEL); if (minor < 0) return ERR_PTR(-ENOMEM); @@ -459,7 +459,7 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) return dax_dev; err_dev: - ida_simple_remove(&dax_minor_ida, minor); + ida_free(&dax_minor_ida, minor); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(alloc_dax); -- cgit From 6a02124c87f0b61dcaaeb65e7fd406d8afb40fd4 Mon Sep 17 00:00:00 2001 From: Lin Yujun Date: Wed, 14 Sep 2022 11:37:55 +0800 Subject: ACPI: HMAT: Release platform device in case of platform_device_add_data() fails The platform device is not released when platform_device_add_data() fails. And platform_device_put() perfom one more pointer check than put_device() to check for errors in the 'pdev' pointer. Use platform_device_put() to release platform device in platform_device_add()/platform_device_add_data()/ platform_device_add_resources() error case. Fixes: c01044cc8191 ("ACPI: HMAT: refactor hmat_register_target_device to hmem_register_device") Signed-off-by: Lin Yujun Link: https://lore.kernel.org/r/20220914033755.99924-1-linyujun809@huawei.com Signed-off-by: Dan Williams --- drivers/dax/hmem/device.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c index cb6401c9e9a4..f87ae005431a 100644 --- a/drivers/dax/hmem/device.c +++ b/drivers/dax/hmem/device.c @@ -47,7 +47,7 @@ void hmem_register_device(int target_nid, struct resource *r) rc = platform_device_add_data(pdev, &info, sizeof(info)); if (rc < 0) { pr_err("hmem memregion_info allocation failure for %pr\n", &res); - goto out_pdev; + goto out_resource; } rc = platform_device_add_resources(pdev, &res, 1); @@ -65,7 +65,7 @@ void hmem_register_device(int target_nid, struct resource *r) return; out_resource: - put_device(&pdev->dev); + platform_device_put(pdev); out_pdev: memregion_free(id); } -- cgit From 54b978e03a3ce7aa3b40deeb1b4c0c9dd6660aa1 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Mon, 26 Sep 2022 22:30:21 +0300 Subject: drm/i915: Round to closest in g4x+ HDMI clock readout MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On pre-ddi platforms we have slightly different code being used for HDMI TMDS clock to dotclock conversion between the state computation and state readout. Both of these need to round the same way in order to not get a mismatch between the computed and read out states. Fix up the rounding direction in the readout path to match what is used during state computation. Another option would to just use intel_crtc_dotclock() in the readout path as well, but I don't really want to do that as the current code more accurately represents how the hardware really works; The HDMI port register defines whether we're actually outputting 8bpc or 12bpc over HDMI, and the PIPECONF bpc setting just defines what goes over FDI between the CPU and PCH. The fact that we try to cram all that into a single pipe_bpp during state computation is perhaps not entirely great... Fixes: f2c9df101095 ("drm/i915: Round TMDS clock to nearest") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20220926193021.23287-1-ville.syrjala@linux.intel.com Reviewed-by: Jani Nikula (cherry picked from commit 86b972ef1091882d66672399c6f8ebdd12a3b707) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/g4x_hdmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c index 5fbd2ae95869..2b73f5ff0d02 100644 --- a/drivers/gpu/drm/i915/display/g4x_hdmi.c +++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c @@ -120,7 +120,7 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder, pipe_config->hw.adjusted_mode.flags |= flags; if ((tmp & SDVO_COLOR_FORMAT_MASK) == HDMI_COLOR_FORMAT_12bpc) - dotclock = pipe_config->port_clock * 2 / 3; + dotclock = DIV_ROUND_CLOSEST(pipe_config->port_clock * 2, 3); else dotclock = pipe_config->port_clock; -- cgit From af4e20d335d4414814030ba26f1689884c831269 Mon Sep 17 00:00:00 2001 From: Tejas Upadhyay Date: Fri, 30 Sep 2022 19:02:23 +0530 Subject: drm/i915/ehl: Update MOCS table for EHL Add these extra EHL entries back since we have drm-tip commit 13d29c823738 ("drm/i915/ehl: unconditionally flush the pages on acquire") introduces proper flushing to make it work as expected. Cc: Chris Wilson Cc: Matthew Auld Fixes: 046091758b50 ("Revert "drm/i915/ehl: Update MOCS table for EHL"") Signed-off-by: Matt Roper Signed-off-by: Tejas Upadhyay Acked-by: Matthew Auld Signed-off-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20220930133223.2757282-1-tejas.upadhyay@intel.com (cherry picked from commit 6fa964c045a6bc3321a9186e87bfbcfd1059b0f1) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/gt/intel_mocs.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index c6ebe2781076..152244d7f62a 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -207,6 +207,14 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = { MOCS_ENTRY(15, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(2) | LE_AOM(1), \ L3_3_WB), \ + /* Bypass LLC - Uncached (EHL+) */ \ + MOCS_ENTRY(16, \ + LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ + L3_1_UC), \ + /* Bypass LLC - L3 (Read-Only) (EHL+) */ \ + MOCS_ENTRY(17, \ + LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ + L3_3_WB), \ /* Self-Snoop - L3 + LLC */ \ MOCS_ENTRY(18, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(3) | LE_SSE(3), \ -- cgit From 1de2e7e08e8cd0f281ba9f079a25e72543fe82f6 Mon Sep 17 00:00:00 2001 From: Jouni Högander Date: Mon, 3 Oct 2022 10:20:11 +0300 Subject: drm/i915/psr: Fix PSR_IMR/IIR field handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Current PSR code is supposed to use TRANSCODER_EDP to force 0 shift for bits in PSR_IMR/IIR registers: /* * gen12+ has registers relative to transcoder and one per transcoder * using the same bit definition: handle it as TRANSCODER_EDP to force * 0 shift in bit definition */ At the time of writing the code assumption "TRANSCODER_EDP == 0" was made. This is not the case and all fields in PSR_IMR and PSR_IIR are shifted incorrectly if DISPLAY_VER >= 12. Fix this by adding separate register field defines for >=12 and add bit getter functions to keep code readability. v4: - Remove EDP from TGL definitions (José) - Use REG_BIT and REG_GENMASK (José) v3: - Add separate register field defines (José) - Add bit getter functions (José) v2: - Improve commit message (José) Cc: José Roberto de Souza Cc: Mika Kahola Fixes: 8241cfbe67f4 ("drm/i915/tgl: Access the right register when handling PSR interruptions") Signed-off-by: Jouni Högander Reviewed-by: José Roberto de Souza Signed-off-by: José Roberto de Souza Link: https://patchwork.freedesktop.org/patch/msgid/20221003072011.72408-1-jouni.hogander@intel.com (cherry picked from commit 8da8e32e0b095613af2c2ce4b322240269164a8e) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_psr.c | 78 +++++++++++++++++++------------- drivers/gpu/drm/i915/i915_reg.h | 16 +++++-- 2 files changed, 59 insertions(+), 35 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 9def8d9fade6..d4cce627d7a8 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -116,34 +116,56 @@ static bool psr2_global_enabled(struct intel_dp *intel_dp) } } +static u32 psr_irq_psr_error_bit_get(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return DISPLAY_VER(dev_priv) >= 12 ? TGL_PSR_ERROR : + EDP_PSR_ERROR(intel_dp->psr.transcoder); +} + +static u32 psr_irq_post_exit_bit_get(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return DISPLAY_VER(dev_priv) >= 12 ? TGL_PSR_POST_EXIT : + EDP_PSR_POST_EXIT(intel_dp->psr.transcoder); +} + +static u32 psr_irq_pre_entry_bit_get(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return DISPLAY_VER(dev_priv) >= 12 ? TGL_PSR_PRE_ENTRY : + EDP_PSR_PRE_ENTRY(intel_dp->psr.transcoder); +} + +static u32 psr_irq_mask_get(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return DISPLAY_VER(dev_priv) >= 12 ? TGL_PSR_MASK : + EDP_PSR_MASK(intel_dp->psr.transcoder); +} + static void psr_irq_control(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - enum transcoder trans_shift; i915_reg_t imr_reg; u32 mask, val; - /* - * gen12+ has registers relative to transcoder and one per transcoder - * using the same bit definition: handle it as TRANSCODER_EDP to force - * 0 shift in bit definition - */ - if (DISPLAY_VER(dev_priv) >= 12) { - trans_shift = 0; + if (DISPLAY_VER(dev_priv) >= 12) imr_reg = TRANS_PSR_IMR(intel_dp->psr.transcoder); - } else { - trans_shift = intel_dp->psr.transcoder; + else imr_reg = EDP_PSR_IMR; - } - mask = EDP_PSR_ERROR(trans_shift); + mask = psr_irq_psr_error_bit_get(intel_dp); if (intel_dp->psr.debug & I915_PSR_DEBUG_IRQ) - mask |= EDP_PSR_POST_EXIT(trans_shift) | - EDP_PSR_PRE_ENTRY(trans_shift); + mask |= psr_irq_post_exit_bit_get(intel_dp) | + psr_irq_pre_entry_bit_get(intel_dp); - /* Warning: it is masking/setting reserved bits too */ val = intel_de_read(dev_priv, imr_reg); - val &= ~EDP_PSR_TRANS_MASK(trans_shift); + val &= ~psr_irq_mask_get(intel_dp); val |= ~mask; intel_de_write(dev_priv, imr_reg, val); } @@ -191,25 +213,21 @@ void intel_psr_irq_handler(struct intel_dp *intel_dp, u32 psr_iir) enum transcoder cpu_transcoder = intel_dp->psr.transcoder; struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); ktime_t time_ns = ktime_get(); - enum transcoder trans_shift; i915_reg_t imr_reg; - if (DISPLAY_VER(dev_priv) >= 12) { - trans_shift = 0; + if (DISPLAY_VER(dev_priv) >= 12) imr_reg = TRANS_PSR_IMR(intel_dp->psr.transcoder); - } else { - trans_shift = intel_dp->psr.transcoder; + else imr_reg = EDP_PSR_IMR; - } - if (psr_iir & EDP_PSR_PRE_ENTRY(trans_shift)) { + if (psr_iir & psr_irq_pre_entry_bit_get(intel_dp)) { intel_dp->psr.last_entry_attempt = time_ns; drm_dbg_kms(&dev_priv->drm, "[transcoder %s] PSR entry attempt in 2 vblanks\n", transcoder_name(cpu_transcoder)); } - if (psr_iir & EDP_PSR_POST_EXIT(trans_shift)) { + if (psr_iir & psr_irq_post_exit_bit_get(intel_dp)) { intel_dp->psr.last_exit = time_ns; drm_dbg_kms(&dev_priv->drm, "[transcoder %s] PSR exit completed\n", @@ -226,7 +244,7 @@ void intel_psr_irq_handler(struct intel_dp *intel_dp, u32 psr_iir) } } - if (psr_iir & EDP_PSR_ERROR(trans_shift)) { + if (psr_iir & psr_irq_psr_error_bit_get(intel_dp)) { u32 val; drm_warn(&dev_priv->drm, "[transcoder %s] PSR aux error\n", @@ -243,7 +261,7 @@ void intel_psr_irq_handler(struct intel_dp *intel_dp, u32 psr_iir) * or unset irq_aux_error. */ val = intel_de_read(dev_priv, imr_reg); - val |= EDP_PSR_ERROR(trans_shift); + val |= psr_irq_psr_error_bit_get(intel_dp); intel_de_write(dev_priv, imr_reg, val); schedule_work(&intel_dp->psr.work); @@ -1194,14 +1212,12 @@ static bool psr_interrupt_error_check(struct intel_dp *intel_dp) * first time that PSR HW tries to activate so lets keep PSR disabled * to avoid any rendering problems. */ - if (DISPLAY_VER(dev_priv) >= 12) { + if (DISPLAY_VER(dev_priv) >= 12) val = intel_de_read(dev_priv, TRANS_PSR_IIR(intel_dp->psr.transcoder)); - val &= EDP_PSR_ERROR(0); - } else { + else val = intel_de_read(dev_priv, EDP_PSR_IIR); - val &= EDP_PSR_ERROR(intel_dp->psr.transcoder); - } + val &= psr_irq_psr_error_bit_get(intel_dp); if (val) { intel_dp->psr.sink_not_reliable = true; drm_dbg_kms(&dev_priv->drm, diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 1a9bd829fc7e..0b287a59dc2f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2157,10 +2157,18 @@ #define TRANS_PSR_IIR(tran) _MMIO_TRANS2(tran, _PSR_IIR_A) #define _EDP_PSR_TRANS_SHIFT(trans) ((trans) == TRANSCODER_EDP ? \ 0 : ((trans) - TRANSCODER_A + 1) * 8) -#define EDP_PSR_TRANS_MASK(trans) (0x7 << _EDP_PSR_TRANS_SHIFT(trans)) -#define EDP_PSR_ERROR(trans) (0x4 << _EDP_PSR_TRANS_SHIFT(trans)) -#define EDP_PSR_POST_EXIT(trans) (0x2 << _EDP_PSR_TRANS_SHIFT(trans)) -#define EDP_PSR_PRE_ENTRY(trans) (0x1 << _EDP_PSR_TRANS_SHIFT(trans)) +#define TGL_PSR_MASK REG_GENMASK(2, 0) +#define TGL_PSR_ERROR REG_BIT(2) +#define TGL_PSR_POST_EXIT REG_BIT(1) +#define TGL_PSR_PRE_ENTRY REG_BIT(0) +#define EDP_PSR_MASK(trans) (TGL_PSR_MASK << \ + _EDP_PSR_TRANS_SHIFT(trans)) +#define EDP_PSR_ERROR(trans) (TGL_PSR_ERROR << \ + _EDP_PSR_TRANS_SHIFT(trans)) +#define EDP_PSR_POST_EXIT(trans) (TGL_PSR_POST_EXIT << \ + _EDP_PSR_TRANS_SHIFT(trans)) +#define EDP_PSR_PRE_ENTRY(trans) (TGL_PSR_PRE_ENTRY << \ + _EDP_PSR_TRANS_SHIFT(trans)) #define _SRD_AUX_DATA_A 0x60814 #define _SRD_AUX_DATA_EDP 0x6f814 -- cgit From c56453a00f19ccddee302f5f9fe96b80e0b47fd3 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Mon, 3 Oct 2022 14:15:39 +0300 Subject: drm/i915: Fix watermark calculations for gen12+ RC CCS modifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Take the gen12+ RC CCS modifier into account when calculating the watermarks. Othwerwise we'll calculate the watermarks thinking this Y-tiled modifier is linear. The rc_surface part is actually a nop since that is not used for any glk+ platform. v2: Split RC CCS vs. MC CCS to separate patches Cc: stable@vger.kernel.org Fixes: b3e57bccd68a ("drm/i915/tgl: Gen-12 render decompression") Reviewed-by: Juha-Pekka Heikkila Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20221003111544.8007-2-ville.syrjala@linux.intel.com (cherry picked from commit a89a96a586114f67598c6391c75678b4dba5c2da) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/skl_watermark.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index 01b0932757ed..132baada3e11 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -1710,10 +1710,12 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state, modifier == I915_FORMAT_MOD_4_TILED || modifier == I915_FORMAT_MOD_Yf_TILED || modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS; + modifier == I915_FORMAT_MOD_Yf_TILED_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS; wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS; + modifier == I915_FORMAT_MOD_Yf_TILED_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS; wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier); wp->width = width; -- cgit From 484b2b9281000274ef7c5cb0a9ebc5da6f5c281c Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Mon, 3 Oct 2022 14:15:40 +0300 Subject: drm/i915: Fix watermark calculations for gen12+ MC CCS modifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Take the gen12+ MC CCS modifier into account when calculating the watermarks. Othwerwise we'll calculate the watermarks thinking this Y-tiled modifier is linear. The rc_surface part is actually a nop since that is not used for any glk+ platform. v2: Split RC CCS vs. MC CCS to separate patches Cc: stable@vger.kernel.org Fixes: 2dfbf9d2873a ("drm/i915/tgl: Gen-12 display can decompress surfaces compressed by the media engine") Reviewed-by: Juha-Pekka Heikkila Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20221003111544.8007-3-ville.syrjala@linux.intel.com (cherry picked from commit 91c9651425fe955b1387f3637607dda005f3f710) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/skl_watermark.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index 132baada3e11..49fc5e2b56fd 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -1711,11 +1711,13 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state, modifier == I915_FORMAT_MOD_Yf_TILED || modifier == I915_FORMAT_MOD_Y_TILED_CCS || modifier == I915_FORMAT_MOD_Yf_TILED_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS; + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS; wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || modifier == I915_FORMAT_MOD_Yf_TILED_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS; + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS; wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier); wp->width = width; -- cgit From 070a2855900de17b1e11a0dc35af9794e80f1a28 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Mon, 3 Oct 2022 14:15:41 +0300 Subject: drm/i915: Fix watermark calculations for gen12+ CCS+CC modifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Take the gen12+ CCS+CC modifier into account when calculating the watermarks. Othwerwise we'll calculate the watermarks thinking this Y-tiled modifier is linear. The rc_surface part is actually a nop since that is not used for any glk+ platform. Cc: stable@vger.kernel.org Fixes: d1e2775e9b96 ("drm/i915/tgl: Add Clear Color support for TGL Render Decompression") Reviewed-by: Juha-Pekka Heikkila Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20221003111544.8007-4-ville.syrjala@linux.intel.com (cherry picked from commit a627455bbe50a111475d7a42beb58fa64bd96c83) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/skl_watermark.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index 49fc5e2b56fd..3676662897e7 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -1712,12 +1712,14 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state, modifier == I915_FORMAT_MOD_Y_TILED_CCS || modifier == I915_FORMAT_MOD_Yf_TILED_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS; + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC; wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || modifier == I915_FORMAT_MOD_Yf_TILED_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS; + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC; wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier); wp->width = width; -- cgit From ccfa6d35f9233702c924316cdf40c05b6ce88113 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Mon, 3 Oct 2022 14:15:42 +0300 Subject: drm/i915: Fix watermark calculations for DG2 CCS modifiers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Take the DG2 CCS modifiers into account when calculating the watermarks. Othwerwise we'll calculate the watermarks thinking these tile-4 modifiers are linear. The rc_surface part is actually a nop since that is not used for any glk+ platform. Cc: stable@vger.kernel.org Fixes: 4c3afa72138c ("drm/i915/dg2: Add support for DG2 render and media compression") Reviewed-by: Juha-Pekka Heikkila Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20221003111544.8007-5-ville.syrjala@linux.intel.com (cherry picked from commit f25d9f81a8e09ace4f04106995550bae1f522143) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/skl_watermark.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index 3676662897e7..a120d49b95ca 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -1713,13 +1713,17 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state, modifier == I915_FORMAT_MOD_Yf_TILED_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC; + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || + modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS || + modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS; wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || modifier == I915_FORMAT_MOD_Yf_TILED_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC; + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || + modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS || + modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS; wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier); wp->width = width; -- cgit From b2e3a1af8cce4117de06ff1a4eab0749753ede27 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Mon, 3 Oct 2022 14:15:43 +0300 Subject: drm/i915: Fix watermark calculations for DG2 CCS+CC modifier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Take the DG2 CCS+CC modifier into account when calculating the watermarks. Othwerwise we'll calculate the watermarks thinking this tile-4 modifier is linear. The rc_surface part is actually a nop since that is not used for any glk+ platform. Cc: stable@vger.kernel.org Fixes: 680025dcc400 ("drm/i915/dg2: Add support for DG2 clear color compression") Reviewed-by: Juha-Pekka Heikkila Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20221003111544.8007-6-ville.syrjala@linux.intel.com (cherry picked from commit 334810f82024815283a6e7febd3d2de1fed6c232) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/skl_watermark.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c index a120d49b95ca..18178b01375e 100644 --- a/drivers/gpu/drm/i915/display/skl_watermark.c +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -1715,7 +1715,8 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state, modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS || - modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS; + modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS || + modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC; wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || modifier == I915_FORMAT_MOD_Yf_TILED_CCS || @@ -1723,7 +1724,8 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state, modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS || - modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS; + modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS || + modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC; wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier); wp->width = width; -- cgit From cdf6428dd518435a05739abf7659589de30970f4 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Tue, 27 Sep 2022 21:24:55 +0300 Subject: drm/i915: Reject excessive dotclocks early MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make sure modes with crazy big dotclocks are rejected early, so as to not cause problems for subsequent code via integer overflows and whatnot. These would eventually be rejected in intel_crtc_compute_pipe_mode() but that is now too late as we do the clock computations a bit earlier than that. And we don't want to just reorder the two since we still want to check the final computed dotclock against the hardware limit to make sure we didn't end up above the limit due to rounding/etc. Fixes: 0ff0e219d9b8 ("drm/i915: Compute clocks earlier") Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20220927182455.3422-1-ville.syrjala@linux.intel.com Reviewed-by: Jani Nikula (cherry picked from commit df2f59c5857b56a5cc40b6562b032c5d8d50cdfc) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_display.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index accf5311b664..f0063e0d4ed3 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -8130,6 +8130,17 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) drm_helper_move_panel_connectors_to_head(&dev_priv->drm); } +static int max_dotclock(struct drm_i915_private *i915) +{ + int max_dotclock = i915->max_dotclk_freq; + + /* icl+ might use bigjoiner */ + if (DISPLAY_VER(i915) >= 11) + max_dotclock *= 2; + + return max_dotclock; +} + static enum drm_mode_status intel_mode_valid(struct drm_device *dev, const struct drm_display_mode *mode) @@ -8167,6 +8178,13 @@ intel_mode_valid(struct drm_device *dev, DRM_MODE_FLAG_CLKDIV2)) return MODE_BAD; + /* + * Reject clearly excessive dotclocks early to + * avoid having to worry about huge integers later. + */ + if (mode->clock > max_dotclock(dev_priv)) + return MODE_CLOCK_HIGH; + /* Transcoder timing limits */ if (DISPLAY_VER(dev_priv) >= 11) { hdisplay_max = 16384; -- cgit From 3baca1a4d490484fcd555413f1fec85b2e071912 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Wed, 27 Jul 2022 10:08:29 +0530 Subject: RISC-V: Add mvendorid, marchid, and mimpid to /proc/cpuinfo output Identifying the underlying RISC-V implementation can be important for some of the user space applications. For example, the perf tool uses arch specific CPU implementation id (i.e. CPUID) to select a JSON file describing custom perf events on a CPU. Currently, there is no way to identify RISC-V implementation so we add mvendorid, marchid, and mimpid to /proc/cpuinfo output. Signed-off-by: Anup Patel Reviewed-by: Heinrich Schuchardt Tested-by: Nikita Shubin Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220727043829.151794-1-apatel@ventanamicro.com/ Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/cpu.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 0be8a2403212..250220e2cceb 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -3,10 +3,13 @@ * Copyright (C) 2012 Regents of the University of California */ +#include #include #include #include +#include #include +#include #include #include @@ -68,6 +71,50 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) } #ifdef CONFIG_PROC_FS + +struct riscv_cpuinfo { + unsigned long mvendorid; + unsigned long marchid; + unsigned long mimpid; +}; +static DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); + +static int riscv_cpuinfo_starting(unsigned int cpu) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); + ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->mvendorid = csr_read(CSR_MVENDORID); + ci->marchid = csr_read(CSR_MARCHID); + ci->mimpid = csr_read(CSR_MIMPID); +#else + ci->mvendorid = 0; + ci->marchid = 0; + ci->mimpid = 0; +#endif + + return 0; +} + +static int __init riscv_cpuinfo_init(void) +{ + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "riscv/cpuinfo:starting", + riscv_cpuinfo_starting, NULL); + if (ret < 0) { + pr_err("cpuinfo: failed to register hotplug callbacks.\n"); + return ret; + } + + return 0; +} +device_initcall(riscv_cpuinfo_init); + #define __RISCV_ISA_EXT_DATA(UPROP, EXTID) \ { \ .uprop = #UPROP, \ @@ -185,6 +232,7 @@ static int c_show(struct seq_file *m, void *v) { unsigned long cpu_id = (unsigned long)v - 1; struct device_node *node = of_get_cpu_node(cpu_id, NULL); + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); const char *compat, *isa; seq_printf(m, "processor\t: %lu\n", cpu_id); @@ -195,6 +243,9 @@ static int c_show(struct seq_file *m, void *v) if (!of_property_read_string(node, "compatible", &compat) && strcmp(compat, "riscv")) seq_printf(m, "uarch\t\t: %s\n", compat); + seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid); + seq_printf(m, "marchid\t\t: 0x%lx\n", ci->marchid); + seq_printf(m, "mimpid\t\t: 0x%lx\n", ci->mimpid); seq_puts(m, "\n"); of_node_put(node); -- cgit From 1d800f32b2574c1d055984ad17223198caddbb54 Mon Sep 17 00:00:00 2001 From: Jonathan Derrick Date: Mon, 3 Oct 2022 14:25:11 -0600 Subject: MAINTAINERS: Update SED-Opal Maintainers Add my new email address and remove Revanth Signed-off-by: Jonathan Derrick Link: https://lore.kernel.org/r/20221003202511.5124-1-jonathan.derrick@linux.dev Signed-off-by: Jens Axboe --- MAINTAINERS | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 47f27eea29ba..f9f5184e7e74 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18298,8 +18298,7 @@ S: Maintained F: drivers/mmc/host/sdhci-esdhc-imx.c SECURE ENCRYPTING DEVICE (SED) OPAL DRIVER -M: Jonathan Derrick -M: Revanth Rajashekar +M: Jonathan Derrick L: linux-block@vger.kernel.org S: Supported F: block/opal_proto.h -- cgit From 417b9c51f59734d852e47252476fadc293ad994a Mon Sep 17 00:00:00 2001 From: Callum Osmotherly Date: Wed, 5 Oct 2022 17:44:16 +1030 Subject: ALSA: hda/realtek: remove ALC289_FIXUP_DUAL_SPK for Dell 5530 After some feedback from users with Dell Precision 5530 machines, this patch reverts the previous change to add ALC289_FIXUP_DUAL_SPK. While it improved the speaker output quality, it caused the headphone jack to have an audible "pop" sound when power saving was toggled. Fixes: 1885ff13d4c4 ("ALSA: hda/realtek: Enable 4-speaker output Dell Precision 5530 laptop") Signed-off-by: Callum Osmotherly Cc: Link: https://lore.kernel.org/r/Yz0uyN1zwZhnyRD6@piranha Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 - 1 file changed, 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index bce82b834cec..d89f95ae0efc 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9198,7 +9198,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB), - SND_PCI_QUIRK(0x1028, 0x087d, "Dell Precision 5530", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), -- cgit From 07d2872bf4c864eb83d034263c155746a2fb7a3b Mon Sep 17 00:00:00 2001 From: Avri Altman Date: Wed, 28 Sep 2022 12:57:44 +0300 Subject: mmc: core: Add SD card quirk for broken discard Some SD-cards from Sandisk that are SDA-6.0 compliant reports they supports discard, while they actually don't. This might cause mk2fs to fail while trying to format the card and revert it to a read-only mode. To fix this problem, let's add a card quirk (MMC_QUIRK_BROKEN_SD_DISCARD) to indicate that we shall fall-back to use the legacy erase command instead. Signed-off-by: Avri Altman Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220928095744.16455-1-avri.altman@wdc.com [Ulf: Updated the commit message] Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 6 +++++- drivers/mmc/core/card.h | 6 ++++++ drivers/mmc/core/quirks.h | 6 ++++++ include/linux/mmc/card.h | 1 + 4 files changed, 18 insertions(+), 1 deletion(-) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index ce89611a136e..54cd009aee50 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1140,8 +1140,12 @@ static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) { struct mmc_blk_data *md = mq->blkdata; struct mmc_card *card = md->queue.card; + unsigned int arg = card->erase_arg; - mmc_blk_issue_erase_rq(mq, req, MMC_BLK_DISCARD, card->erase_arg); + if (mmc_card_broken_sd_discard(card)) + arg = SD_ERASE_ARG; + + mmc_blk_issue_erase_rq(mq, req, MMC_BLK_DISCARD, arg); } static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq, diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h index 99045e138ba4..cfdd1ff40b86 100644 --- a/drivers/mmc/core/card.h +++ b/drivers/mmc/core/card.h @@ -73,6 +73,7 @@ struct mmc_fixup { #define EXT_CSD_REV_ANY (-1u) #define CID_MANFID_SANDISK 0x2 +#define CID_MANFID_SANDISK_SD 0x3 #define CID_MANFID_ATP 0x9 #define CID_MANFID_TOSHIBA 0x11 #define CID_MANFID_MICRON 0x13 @@ -258,4 +259,9 @@ static inline int mmc_card_broken_hpi(const struct mmc_card *c) return c->quirks & MMC_QUIRK_BROKEN_HPI; } +static inline int mmc_card_broken_sd_discard(const struct mmc_card *c) +{ + return c->quirks & MMC_QUIRK_BROKEN_SD_DISCARD; +} + #endif diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h index be4393988086..29b9497936df 100644 --- a/drivers/mmc/core/quirks.h +++ b/drivers/mmc/core/quirks.h @@ -100,6 +100,12 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = { MMC_FIXUP("V10016", CID_MANFID_KINGSTON, CID_OEMID_ANY, add_quirk_mmc, MMC_QUIRK_TRIM_BROKEN), + /* + * Some SD cards reports discard support while they don't + */ + MMC_FIXUP(CID_NAME_ANY, CID_MANFID_SANDISK_SD, 0x5344, add_quirk_sd, + MMC_QUIRK_BROKEN_SD_DISCARD), + END_FIXUP }; diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 8a30de08e913..c726ea781255 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -293,6 +293,7 @@ struct mmc_card { #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ #define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ #define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ +#define MMC_QUIRK_BROKEN_SD_DISCARD (1<<14) /* Disable broken SD discard support */ bool reenable_cmdq; /* Re-enable Command Queue */ -- cgit From 340e134727c9adaefadc7e79b765c038e18e55c3 Mon Sep 17 00:00:00 2001 From: Deming Wang Date: Thu, 6 Oct 2022 04:44:50 -0400 Subject: block: Remove the repeat word 'can' Remove the repeat word 'can' from the comments of bio_kmalloc. Signed-off-by: Deming Wang Link: https://lore.kernel.org/r/20221006084450.1513-1-wangdeming@inspur.com Signed-off-by: Jens Axboe --- block/bio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/bio.c b/block/bio.c index 7cb7d2ff139b..6c470a50a36d 100644 --- a/block/bio.c +++ b/block/bio.c @@ -567,7 +567,7 @@ EXPORT_SYMBOL(bio_alloc_bioset); * be reused by calling bio_uninit() before calling bio_init() again. * * Note that unlike bio_alloc() or bio_alloc_bioset() allocations from this - * function are not backed by a mempool can can fail. Do not use this function + * function are not backed by a mempool can fail. Do not use this function * for allocations in the file system I/O path. * * Returns: Pointer to new bio on success, NULL on failure. -- cgit From 91954c6c904b515baafaee6a1f35c94409a3bb68 Mon Sep 17 00:00:00 2001 From: Daniel Gomez Date: Sun, 25 Sep 2022 23:53:13 +0200 Subject: drm/amd/display: Fix mutex lock in dcn10 Removal of DC_FP_* wrappers from dml (9696679bf7ac) provokes a mutex lock [2] on the amdgpu driver. Re-arrange the dcn10 code to avoid locking the mutex by placing the DC_FP_* wrappers around the proper functions. This fixes the following WARN/stacktrace: BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 227, name: systemd-udevd preempt_count: 1, expected: 0 CPU: 4 PID: 227 Comm: systemd-udevd Not tainted 6.0.0-rc6-qtec-standard #2 Hardware name: Qtechnology A/S QT5222/QT5221, BIOS v1.0.1 06/07/2021 Call Trace: dump_stack_lvl+0x33/0x42 __might_resched.cold.172+0xa5/0xb3 mutex_lock+0x1a/0x40 amdgpu_dpm_get_clock_by_type_with_voltage+0x38/0x70 [amdgpu] dm_pp_get_clock_levels_by_type_with_voltage+0x64/0xa0 [amdgpu] dcn_bw_update_from_pplib+0x70/0x340 [amdgpu] dcn10_create_resource_pool+0x8c8/0xd20 [amdgpu] ? __kmalloc+0x1c7/0x4a0 dc_create_resource_pool+0xe7/0x190 [amdgpu] dc_create+0x212/0x5d0 [amdgpu] amdgpu_dm_init+0x246/0x370 [amdgpu] ? schedule_hrtimeout_range_clock+0x93/0x120 ? phm_wait_for_register_unequal.part.1+0x4a/0x80 [amdgpu] dm_hw_init+0xe/0x20 [amdgpu] amdgpu_device_init.cold.56+0x1324/0x1653 [amdgpu] ? pci_bus_read_config_word+0x43/0x80 amdgpu_driver_load_kms+0x15/0x120 [amdgpu] amdgpu_pci_probe+0x116/0x320 [amdgpu] pci_device_probe+0x97/0x110 really_probe+0xdd/0x340 __driver_probe_device+0x80/0x170 driver_probe_device+0x1f/0x90 __driver_attach+0xdc/0x180 ? __device_attach_driver+0x100/0x100 ? __device_attach_driver+0x100/0x100 bus_for_each_dev+0x74/0xc0 bus_add_driver+0x19e/0x210 ? kset_find_obj+0x30/0xa0 ? 0xffffffffa0a5b000 driver_register+0x6b/0xc0 ? 0xffffffffa0a5b000 do_one_initcall+0x4a/0x1f0 ? __vunmap+0x28e/0x2f0 ? __cond_resched+0x15/0x30 ? kmem_cache_alloc_trace+0x3d/0x440 do_init_module+0x4a/0x1e0 load_module+0x1cba/0x1e10 ? __do_sys_finit_module+0xb7/0x120 __do_sys_finit_module+0xb7/0x120 do_syscall_64+0x3c/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7ff2b5f5422d Code: 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d c3 ab 0e 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc44ab28e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 0000555c566a9240 RCX: 00007ff2b5f5422d RDX: 0000000000000000 RSI: 00007ff2b60bb353 RDI: 0000000000000019 RBP: 00007ff2b60bb353 R08: 0000000000000000 R09: 0000555c566a9240 R10: 0000000000000019 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000020000 R14: 0000000000000000 R15: 0000000000000000 Fixes: 9696679bf7ac ("drm/amd/display: remove DC_FP_* wrapper from dml folder") Reviewed-by: Hamza Mahfooz Tested-by: Daniel Wheeler Signed-off-by: Daniel Gomez Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 12 ++- .../gpu/drm/amd/display/dc/dcn10/dcn10_resource.c | 66 +++++++++++- .../gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c | 118 +++++++++------------ drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h | 19 +++- 4 files changed, 138 insertions(+), 77 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 72521749c01d..4390f6d7050f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3005,6 +3005,7 @@ void dcn10_prepare_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3027,8 +3028,11 @@ void dcn10_prepare_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); } if (dc->debug.sanity_checks) @@ -3041,6 +3045,7 @@ void dcn10_optimize_bandwidth( { struct dce_hwseq *hws = dc->hwseq; struct hubbub *hubbub = dc->res_pool->hubbub; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; if (dc->debug.sanity_checks) hws->funcs.verify_allow_pstate_change_high(dc); @@ -3064,8 +3069,11 @@ void dcn10_optimize_bandwidth( if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) { DC_FP_START(); - dcn_bw_notify_pplib_of_wm_ranges(dc); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); } if (dc->debug.sanity_checks) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c index 831080b9eb87..56d30baf12df 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c @@ -1336,6 +1336,21 @@ static noinline void dcn10_resource_construct_fp( } } +static bool verify_clock_values(struct dm_pp_clock_levels_with_voltage *clks) +{ + int i; + + if (clks->num_levels == 0) + return false; + + for (i = 0; i < clks->num_levels; i++) + /* Ensure that the result is sane */ + if (clks->data[i].clocks_in_khz == 0) + return false; + + return true; +} + static bool dcn10_resource_construct( uint8_t num_virtual_links, struct dc *dc, @@ -1345,6 +1360,9 @@ static bool dcn10_resource_construct( int j; struct dc_context *ctx = dc->ctx; uint32_t pipe_fuses = read_pipe_fuses(ctx); + struct dm_pp_clock_levels_with_voltage fclks = {0}, dcfclks = {0}; + int min_fclk_khz, min_dcfclk_khz, socclk_khz; + bool res; ctx->dc_bios->regs = &bios_regs; @@ -1523,15 +1541,53 @@ static bool dcn10_resource_construct( && pool->base.pp_smu->rv_funcs.set_pme_wa_enable != NULL) dc->debug.az_endpoint_mute_only = false; - DC_FP_START(); - if (!dc->debug.disable_pplib_clock_request) - dcn_bw_update_from_pplib(dc); + + if (!dc->debug.disable_pplib_clock_request) { + /* + * TODO: This is not the proper way to obtain + * fabric_and_dram_bandwidth, should be min(fclk, memclk). + */ + res = dm_pp_get_clock_levels_by_type_with_voltage( + ctx, DM_PP_CLOCK_TYPE_FCLK, &fclks); + + DC_FP_START(); + + if (res) + res = verify_clock_values(&fclks); + + if (res) + dcn_bw_update_from_pplib_fclks(dc, &fclks); + else + BREAK_TO_DEBUGGER(); + + DC_FP_END(); + + res = dm_pp_get_clock_levels_by_type_with_voltage( + ctx, DM_PP_CLOCK_TYPE_DCFCLK, &dcfclks); + + DC_FP_START(); + + if (res) + res = verify_clock_values(&dcfclks); + + if (res) + dcn_bw_update_from_pplib_dcfclks(dc, &dcfclks); + else + BREAK_TO_DEBUGGER(); + + DC_FP_END(); + } + dcn_bw_sync_calcs_and_dml(dc); if (!dc->debug.disable_pplib_wm_range) { dc->res_pool = &pool->base; - dcn_bw_notify_pplib_of_wm_ranges(dc); + DC_FP_START(); + dcn_get_soc_clks( + dc, &min_fclk_khz, &min_dcfclk_khz, &socclk_khz); + DC_FP_END(); + dcn_bw_notify_pplib_of_wm_ranges( + dc, min_fclk_khz, min_dcfclk_khz, socclk_khz); } - DC_FP_END(); { struct irq_service_init_data init_data; diff --git a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c index d46adc849d2a..e73f089c84bb 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c @@ -1444,81 +1444,67 @@ unsigned int dcn_find_dcfclk_suits_all( return dcf_clk; } -static bool verify_clock_values(struct dm_pp_clock_levels_with_voltage *clks) +void dcn_bw_update_from_pplib_fclks( + struct dc *dc, + struct dm_pp_clock_levels_with_voltage *fclks) { - int i; - - if (clks->num_levels == 0) - return false; - - for (i = 0; i < clks->num_levels; i++) - /* Ensure that the result is sane */ - if (clks->data[i].clocks_in_khz == 0) - return false; + unsigned vmin0p65_idx, vmid0p72_idx, vnom0p8_idx, vmax0p9_idx; - return true; + ASSERT(fclks->num_levels); + + vmin0p65_idx = 0; + vmid0p72_idx = fclks->num_levels - + (fclks->num_levels > 2 ? 3 : (fclks->num_levels > 1 ? 2 : 1)); + vnom0p8_idx = fclks->num_levels - (fclks->num_levels > 1 ? 2 : 1); + vmax0p9_idx = fclks->num_levels - 1; + + dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = + 32 * (fclks->data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0; + dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = + dc->dcn_soc->number_of_channels * + (fclks->data[vmid0p72_idx].clocks_in_khz / 1000.0) + * ddr4_dram_factor_single_Channel / 1000.0; + dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = + dc->dcn_soc->number_of_channels * + (fclks->data[vnom0p8_idx].clocks_in_khz / 1000.0) + * ddr4_dram_factor_single_Channel / 1000.0; + dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = + dc->dcn_soc->number_of_channels * + (fclks->data[vmax0p9_idx].clocks_in_khz / 1000.0) + * ddr4_dram_factor_single_Channel / 1000.0; } -void dcn_bw_update_from_pplib(struct dc *dc) +void dcn_bw_update_from_pplib_dcfclks( + struct dc *dc, + struct dm_pp_clock_levels_with_voltage *dcfclks) { - struct dc_context *ctx = dc->ctx; - struct dm_pp_clock_levels_with_voltage fclks = {0}, dcfclks = {0}; - bool res; - unsigned vmin0p65_idx, vmid0p72_idx, vnom0p8_idx, vmax0p9_idx; - - /* TODO: This is not the proper way to obtain fabric_and_dram_bandwidth, should be min(fclk, memclk) */ - res = dm_pp_get_clock_levels_by_type_with_voltage( - ctx, DM_PP_CLOCK_TYPE_FCLK, &fclks); - - if (res) - res = verify_clock_values(&fclks); - - if (res) { - ASSERT(fclks.num_levels); - - vmin0p65_idx = 0; - vmid0p72_idx = fclks.num_levels - - (fclks.num_levels > 2 ? 3 : (fclks.num_levels > 1 ? 2 : 1)); - vnom0p8_idx = fclks.num_levels - (fclks.num_levels > 1 ? 2 : 1); - vmax0p9_idx = fclks.num_levels - 1; - - dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = - 32 * (fclks.data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0; - dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = - dc->dcn_soc->number_of_channels * - (fclks.data[vmid0p72_idx].clocks_in_khz / 1000.0) - * ddr4_dram_factor_single_Channel / 1000.0; - dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = - dc->dcn_soc->number_of_channels * - (fclks.data[vnom0p8_idx].clocks_in_khz / 1000.0) - * ddr4_dram_factor_single_Channel / 1000.0; - dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = - dc->dcn_soc->number_of_channels * - (fclks.data[vmax0p9_idx].clocks_in_khz / 1000.0) - * ddr4_dram_factor_single_Channel / 1000.0; - } else - BREAK_TO_DEBUGGER(); - - res = dm_pp_get_clock_levels_by_type_with_voltage( - ctx, DM_PP_CLOCK_TYPE_DCFCLK, &dcfclks); - - if (res) - res = verify_clock_values(&dcfclks); + if (dcfclks->num_levels >= 3) { + dc->dcn_soc->dcfclkv_min0p65 = dcfclks->data[0].clocks_in_khz / 1000.0; + dc->dcn_soc->dcfclkv_mid0p72 = dcfclks->data[dcfclks->num_levels - 3].clocks_in_khz / 1000.0; + dc->dcn_soc->dcfclkv_nom0p8 = dcfclks->data[dcfclks->num_levels - 2].clocks_in_khz / 1000.0; + dc->dcn_soc->dcfclkv_max0p9 = dcfclks->data[dcfclks->num_levels - 1].clocks_in_khz / 1000.0; + } +} - if (res && dcfclks.num_levels >= 3) { - dc->dcn_soc->dcfclkv_min0p65 = dcfclks.data[0].clocks_in_khz / 1000.0; - dc->dcn_soc->dcfclkv_mid0p72 = dcfclks.data[dcfclks.num_levels - 3].clocks_in_khz / 1000.0; - dc->dcn_soc->dcfclkv_nom0p8 = dcfclks.data[dcfclks.num_levels - 2].clocks_in_khz / 1000.0; - dc->dcn_soc->dcfclkv_max0p9 = dcfclks.data[dcfclks.num_levels - 1].clocks_in_khz / 1000.0; - } else - BREAK_TO_DEBUGGER(); +void dcn_get_soc_clks( + struct dc *dc, + int *min_fclk_khz, + int *min_dcfclk_khz, + int *socclk_khz) +{ + *min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32; + *min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000; + *socclk_khz = dc->dcn_soc->socclk * 1000; } -void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc) +void dcn_bw_notify_pplib_of_wm_ranges( + struct dc *dc, + int min_fclk_khz, + int min_dcfclk_khz, + int socclk_khz) { struct pp_smu_funcs_rv *pp = NULL; struct pp_smu_wm_range_sets ranges = {0}; - int min_fclk_khz, min_dcfclk_khz, socclk_khz; const int overdrive = 5000000; /* 5 GHz to cover Overdrive */ if (dc->res_pool->pp_smu) @@ -1526,10 +1512,6 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc) if (!pp || !pp->set_wm_ranges) return; - min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32; - min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000; - socclk_khz = dc->dcn_soc->socclk * 1000; - /* Now notify PPLib/SMU about which Watermarks sets they should select * depending on DPM state they are in. And update BW MGR GFX Engine and * Memory clock member variables for Watermarks calculations for each diff --git a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h index 806f3041db14..9e4ddc985240 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h @@ -628,8 +628,23 @@ unsigned int dcn_find_dcfclk_suits_all( const struct dc *dc, struct dc_clocks *clocks); -void dcn_bw_update_from_pplib(struct dc *dc); -void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc); +void dcn_get_soc_clks( + struct dc *dc, + int *min_fclk_khz, + int *min_dcfclk_khz, + int *socclk_khz); + +void dcn_bw_update_from_pplib_fclks( + struct dc *dc, + struct dm_pp_clock_levels_with_voltage *fclks); +void dcn_bw_update_from_pplib_dcfclks( + struct dc *dc, + struct dm_pp_clock_levels_with_voltage *dcfclks); +void dcn_bw_notify_pplib_of_wm_ranges( + struct dc *dc, + int min_fclk_khz, + int min_dcfclk_khz, + int socclk_khz); void dcn_bw_sync_calcs_and_dml(struct dc *dc); enum source_macro_tile_size swizzle_mode_to_macro_tile_size(enum swizzle_mode_values sw_mode); -- cgit From 8ab1d7a27eff87001ebd0977db600e4187f63f78 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Wed, 17 Aug 2022 10:47:59 -0400 Subject: drm/amd/display: Only commit SubVP state after pipe programming [Description] We only want to commit the SubVP config to DMCUB after the main and phantom pipe programming has completed. Commiting the state early can cause issues such as P-State being allowed by the HW early which causes the SubVP state machine to go into a bad state Reviewed-by: Jun Lei Acked-by: Brian Chang Signed-off-by: Alvin Lee Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 258ba5a872b1..ccaa43d071cf 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3495,6 +3495,9 @@ static void commit_planes_for_stream(struct dc *dc, if (update_type != UPDATE_TYPE_FAST) dc->hwss.post_unlock_program_front_end(dc, context); + if (update_type != UPDATE_TYPE_FAST) + if (dc->hwss.commit_subvp_config) + dc->hwss.commit_subvp_config(dc, context); if (update_type != UPDATE_TYPE_FAST) if (dc->hwss.commit_subvp_config) -- cgit From d37f379ad04dcc21ebd1d2380c3bc979d54f7c46 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 29 Sep 2022 17:02:00 +0800 Subject: drm/amd/display: change to enc314_stream_encoder_dp_blank static enc314_stream_encoder_dp_blank is only used in dcn314_dio_stream_encoder.c now, change it to static. Fixes: c55bf690fe79 ("drm/amd/display: Add explicit FIFO disable for DP blank") Signed-off-by: Yang Yingliang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c index 0d2ffb692957..7e773bf7b895 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c @@ -262,7 +262,7 @@ static bool is_two_pixels_per_containter(const struct dc_crtc_timing *timing) return two_pix; } -void enc314_stream_encoder_dp_blank( +static void enc314_stream_encoder_dp_blank( struct dc_link *link, struct stream_encoder *enc) { -- cgit From 8abbc4f768ddc5c2190ab8966e529cec42b4b2d4 Mon Sep 17 00:00:00 2001 From: Li Zhong Date: Sat, 24 Sep 2022 15:19:39 -0700 Subject: drivers/amd/pm: check the return value of amdgpu_bo_kmap amdgpu_bo_kmap() returns error when fails to map buffer object. Add the error check and propagate the error. Signed-off-by: Li Zhong Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index 8fd0782a2b20..f5e08b60f66e 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -1384,13 +1384,16 @@ static int kv_dpm_enable(struct amdgpu_device *adev) static void kv_dpm_disable(struct amdgpu_device *adev) { struct kv_power_info *pi = kv_get_pi(adev); + int err; amdgpu_irq_put(adev, &adev->pm.dpm.thermal.irq, AMDGPU_THERMAL_IRQ_LOW_TO_HIGH); amdgpu_irq_put(adev, &adev->pm.dpm.thermal.irq, AMDGPU_THERMAL_IRQ_HIGH_TO_LOW); - amdgpu_kv_smc_bapm_enable(adev, false); + err = amdgpu_kv_smc_bapm_enable(adev, false); + if (err) + DRM_ERROR("amdgpu_kv_smc_bapm_enable failed\n"); if (adev->asic_type == CHIP_MULLINS) kv_enable_nb_dpm(adev, false); -- cgit From f7367b5fe0e38af02d6915a355f2ee63b172c9ac Mon Sep 17 00:00:00 2001 From: Dillon Varone Date: Mon, 19 Sep 2022 10:29:24 -0400 Subject: drm/amd/display: Program SubVP in dc_commit_state_no_check [Why?] Currently SubVP programming is only done in commit_planes_for_stream, as it was expected only this call would add/remove planes from a display. [How?] Add SubVP programming to dc_commit_state_no_check. Reviewed-by: Alvin Lee Acked-by: Hamza Mahfooz Signed-off-by: Dillon Varone Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index ccaa43d071cf..4ba2c1f95dcb 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1734,10 +1734,20 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c int i, k, l; struct dc_stream_state *dc_streams[MAX_STREAMS] = {0}; struct dc_state *old_state; + bool subvp_prev_use = false; dc_z10_restore(dc); dc_allow_idle_optimizations(dc, false); + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + /* Check old context for SubVP */ + subvp_prev_use |= (old_pipe->stream && old_pipe->stream->mall_stream_config.type == SUBVP_PHANTOM); + if (subvp_prev_use) + break; + } + for (i = 0; i < context->stream_count; i++) dc_streams[i] = context->streams[i]; @@ -1777,6 +1787,9 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc->hwss.wait_for_mpcc_disconnect(dc, dc->res_pool, pipe); } + if (dc->hwss.subvp_pipe_control_lock) + dc->hwss.subvp_pipe_control_lock(dc, context, true, true, NULL, subvp_prev_use); + result = dc->hwss.apply_ctx_to_hw(dc, context); if (result != DC_OK) { @@ -1794,6 +1807,12 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc->hwss.interdependent_update_lock(dc, context, false); dc->hwss.post_unlock_program_front_end(dc, context); } + + if (dc->hwss.commit_subvp_config) + dc->hwss.commit_subvp_config(dc, context); + if (dc->hwss.subvp_pipe_control_lock) + dc->hwss.subvp_pipe_control_lock(dc, context, false, true, NULL, subvp_prev_use); + for (i = 0; i < context->stream_count; i++) { const struct dc_link *link = context->streams[i]->link; -- cgit From c1969fbaa57d88ddef626bb8ae313d38478d8631 Mon Sep 17 00:00:00 2001 From: Dillon Varone Date: Mon, 19 Sep 2022 13:14:02 -0400 Subject: drm/amd/display: Reorder FCLK P-state switch sequence for DCN32 [WHY?] In some cases, DCFCLK hardmin requests are not acknowledged by SMU as the requested clock does not have a compatible ratio with current FCLK, and it cannot be changed as FCLK P-state is not allowed. [HOW?] Allow FCLK p-state change prior to changing DCFCLK hardmin. Reviewed-by: Alvin Lee Acked-by: Hamza Mahfooz Signed-off-by: Dillon Varone Signed-off-by: Alex Deucher --- .../amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c | 44 +++++++++++----------- 1 file changed, 23 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index f0f3f66629cc..96d5e0d5b3ce 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -333,6 +333,21 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, if (enter_display_off == safe_to_lower) dcn30_smu_set_num_of_displays(clk_mgr, display_count); + clk_mgr_base->clks.fclk_prev_p_state_change_support = clk_mgr_base->clks.fclk_p_state_change_support; + + total_plane_count = clk_mgr_helper_get_active_plane_cnt(dc, context); + fclk_p_state_change_support = new_clocks->fclk_p_state_change_support || (total_plane_count == 0); + + if (should_update_pstate_support(safe_to_lower, fclk_p_state_change_support, clk_mgr_base->clks.fclk_p_state_change_support)) { + clk_mgr_base->clks.fclk_p_state_change_support = fclk_p_state_change_support; + + /* To enable FCLK P-state switching, send FCLK_PSTATE_NOTSUPPORTED message to PMFW */ + if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && clk_mgr_base->clks.fclk_p_state_change_support && update_fclk) { + /* Handle the code for sending a message to PMFW that FCLK P-state change is supported */ + dcn32_smu_send_fclk_pstate_message(clk_mgr, FCLK_PSTATE_SUPPORTED); + } + } + if (dc->debug.force_min_dcfclk_mhz > 0) new_clocks->dcfclk_khz = (new_clocks->dcfclk_khz > (dc->debug.force_min_dcfclk_mhz * 1000)) ? new_clocks->dcfclk_khz : (dc->debug.force_min_dcfclk_mhz * 1000); @@ -352,7 +367,6 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, clk_mgr_base->clks.socclk_khz = new_clocks->socclk_khz; clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support; - clk_mgr_base->clks.fclk_prev_p_state_change_support = clk_mgr_base->clks.fclk_p_state_change_support; clk_mgr_base->clks.prev_num_ways = clk_mgr_base->clks.num_ways; if (clk_mgr_base->clks.num_ways != new_clocks->num_ways && @@ -361,9 +375,8 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, dcn32_smu_send_cab_for_uclk_message(clk_mgr, clk_mgr_base->clks.num_ways); } - total_plane_count = clk_mgr_helper_get_active_plane_cnt(dc, context); + p_state_change_support = new_clocks->p_state_change_support || (total_plane_count == 0); - fclk_p_state_change_support = new_clocks->fclk_p_state_change_support || (total_plane_count == 0); if (should_update_pstate_support(safe_to_lower, p_state_change_support, clk_mgr_base->clks.p_state_change_support)) { clk_mgr_base->clks.p_state_change_support = p_state_change_support; @@ -373,15 +386,14 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries - 1].memclk_mhz); } - if (should_update_pstate_support(safe_to_lower, fclk_p_state_change_support, clk_mgr_base->clks.fclk_p_state_change_support) && - clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21) { - clk_mgr_base->clks.fclk_p_state_change_support = fclk_p_state_change_support; + /* Always update saved value, even if new value not set due to P-State switching unsupported. Also check safe_to_lower for FCLK */ + if (safe_to_lower && (clk_mgr_base->clks.fclk_p_state_change_support != clk_mgr_base->clks.fclk_prev_p_state_change_support)) { + update_fclk = true; + } - /* To disable FCLK P-state switching, send FCLK_PSTATE_NOTSUPPORTED message to PMFW */ - if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && !clk_mgr_base->clks.fclk_p_state_change_support) { - /* Handle code for sending a message to PMFW that FCLK P-state change is not supported */ - dcn32_smu_send_fclk_pstate_message(clk_mgr, FCLK_PSTATE_NOTSUPPORTED); - } + if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && !clk_mgr_base->clks.fclk_p_state_change_support && update_fclk) { + /* Handle code for sending a message to PMFW that FCLK P-state change is not supported */ + dcn32_smu_send_fclk_pstate_message(clk_mgr, FCLK_PSTATE_NOTSUPPORTED); } /* Always update saved value, even if new value not set due to P-State switching unsupported */ @@ -390,21 +402,11 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, update_uclk = true; } - /* Always update saved value, even if new value not set due to P-State switching unsupported. Also check safe_to_lower for FCLK */ - if (safe_to_lower && (clk_mgr_base->clks.fclk_p_state_change_support != clk_mgr_base->clks.fclk_prev_p_state_change_support)) { - update_fclk = true; - } - /* set UCLK to requested value if P-State switching is supported, or to re-enable P-State switching */ if (clk_mgr_base->clks.p_state_change_support && (update_uclk || !clk_mgr_base->clks.prev_p_state_change_support)) dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)); - if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && clk_mgr_base->clks.fclk_p_state_change_support && update_fclk) { - /* Handle the code for sending a message to PMFW that FCLK P-state change is supported */ - dcn32_smu_send_fclk_pstate_message(clk_mgr, FCLK_PSTATE_SUPPORTED); - } - if (clk_mgr_base->clks.num_ways != new_clocks->num_ways && clk_mgr_base->clks.num_ways > new_clocks->num_ways) { clk_mgr_base->clks.num_ways = new_clocks->num_ways; -- cgit From ab5220bb5a910246c61512a9e29a4e2406cb1ecd Mon Sep 17 00:00:00 2001 From: Dmytro Laktyushkin Date: Thu, 8 Sep 2022 11:37:58 -0400 Subject: drm/amd/display: fix dcn315 dml detile overestimation DML does not take the fact that dcn315 does not have enough detile buffer to max all pipes. This change adds a workaround to apply the same logic DC does when calculating detile buffer size in DML. Reviewed-by: Charlene Liu Acked-by: Hamza Mahfooz Signed-off-by: Dmytro Laktyushkin Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c | 2 +- .../drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c | 15 +++++++++++++++ drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c | 1 + drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h | 1 + 4 files changed, 18 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index b6e99eefe869..94b0842cd89b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c @@ -739,7 +739,7 @@ void dcn315_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param } if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) - dml_init_instance(&dc->dml, &dcn3_15_soc, &dcn3_15_ip, DML_PROJECT_DCN31); + dml_init_instance(&dc->dml, &dcn3_15_soc, &dcn3_15_ip, DML_PROJECT_DCN315); else dml_init_instance(&dc->dml, &dcn3_15_soc, &dcn3_15_ip, DML_PROJECT_DCN31_FPGA); } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c index 8dfe639b6508..b612edb14417 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c @@ -43,6 +43,8 @@ #define BPP_BLENDED_PIPE 0xffffffff #define DCN31_MAX_DSC_IMAGE_WIDTH 5184 #define DCN31_MAX_FMT_420_BUFFER_WIDTH 4096 +#define DCN3_15_MIN_COMPBUF_SIZE_KB 128 +#define DCN3_15_MAX_DET_SIZE 384 // For DML-C changes that hasn't been propagated to VBA yet //#define __DML_VBA_ALLOW_DELTA__ @@ -3775,6 +3777,17 @@ static noinline void CalculatePrefetchSchedulePerPlane( &v->VReadyOffsetPix[k]); } +static void PatchDETBufferSizeInKByte(unsigned int NumberOfActivePlanes, int NoOfDPPThisState[], unsigned int config_return_buffer_size_in_kbytes, unsigned int *DETBufferSizeInKByte) +{ + int i, total_pipes = 0; + for (i = 0; i < NumberOfActivePlanes; i++) + total_pipes += NoOfDPPThisState[i]; + *DETBufferSizeInKByte = ((config_return_buffer_size_in_kbytes - DCN3_15_MIN_COMPBUF_SIZE_KB) / 64 / total_pipes) * 64; + if (*DETBufferSizeInKByte > DCN3_15_MAX_DET_SIZE) + *DETBufferSizeInKByte = DCN3_15_MAX_DET_SIZE; +} + + void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib) { struct vba_vars_st *v = &mode_lib->vba; @@ -4533,6 +4546,8 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->ODMCombineEnableThisState[k] = v->ODMCombineEnablePerState[i][k]; } + if (v->NumberOfActivePlanes > 1 && mode_lib->project == DML_PROJECT_DCN315) + PatchDETBufferSizeInKByte(v->NumberOfActivePlanes, v->NoOfDPPThisState, v->ip.config_return_buffer_size_in_kbytes, &v->DETBufferSizeInKByte[0]); CalculateSwathAndDETConfiguration( false, v->NumberOfActivePlanes, diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c index f5400eda07a5..4125d3d111d1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c @@ -114,6 +114,7 @@ void dml_init_instance(struct display_mode_lib *lib, break; case DML_PROJECT_DCN31: case DML_PROJECT_DCN31_FPGA: + case DML_PROJECT_DCN315: lib->funcs = dml31_funcs; break; case DML_PROJECT_DCN314: diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h index b1878a1440e2..3d643d50c3eb 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h @@ -40,6 +40,7 @@ enum dml_project { DML_PROJECT_DCN21, DML_PROJECT_DCN30, DML_PROJECT_DCN31, + DML_PROJECT_DCN315, DML_PROJECT_DCN31_FPGA, DML_PROJECT_DCN314, DML_PROJECT_DCN32, -- cgit From d35e8b7ae01430b1e722547b2ef40f42dc30520f Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Tue, 20 Sep 2022 10:46:18 -0400 Subject: drm/amd/display: Block SubVP if rotation being used [Description] - SubVP rotation support is not explicitly implemented, so block SubVP in rotation cases to avoid unexpected behaviors Reviewed-by: Nevenko Stupar Reviewed-by: Jun Lei Acked-by: Hamza Mahfooz Signed-off-by: Alvin Lee Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h | 2 ++ .../drm/amd/display/dc/dcn32/dcn32_resource_helpers.c | 17 +++++++++++++++++ drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 3 ++- 3 files changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h index 55945cca2260..a24f538bdc4c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h @@ -108,6 +108,8 @@ bool dcn32_subvp_in_use(struct dc *dc, bool dcn32_mpo_in_use(struct dc_state *context); +bool dcn32_any_surfaces_rotated(struct dc *dc, struct dc_state *context); + struct pipe_ctx *dcn32_acquire_idle_pipe_for_head_pipe_in_layer( struct dc_state *state, const struct resource_pool *pool, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c index a2a70a1572b7..7f318ced5dee 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c @@ -233,6 +233,23 @@ bool dcn32_mpo_in_use(struct dc_state *context) return false; } + +bool dcn32_any_surfaces_rotated(struct dc *dc, struct dc_state *context) +{ + uint32_t i; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (!pipe->stream) + continue; + + if (pipe->plane_state && pipe->plane_state->rotation != ROTATION_ANGLE_0) + return true; + } + return false; +} + /** * ******************************************************************************************* * dcn32_determine_det_override: Determine DET allocation for each pipe diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 0571700f53f9..a56ee04f7df9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1115,7 +1115,8 @@ static void dcn32_full_validate_bw_helper(struct dc *dc, * 5. (Config doesn't support MCLK in VACTIVE/VBLANK || dc->debug.force_subvp_mclk_switch) */ if (!dc->debug.force_disable_subvp && dcn32_all_pipes_have_stream_and_plane(dc, context) && - !dcn32_mpo_in_use(context) && (*vlevel == context->bw_ctx.dml.soc.num_states || + !dcn32_mpo_in_use(context) && !dcn32_any_surfaces_rotated(dc, context) && + (*vlevel == context->bw_ctx.dml.soc.num_states || vba->DRAMClockChangeSupport[*vlevel][vba->maxMpcComb] == dm_dram_clock_change_unsupported || dc->debug.force_subvp_mclk_switch)) { -- cgit From 96ab3cb3b0f862308a03046d01d66c7b4154846b Mon Sep 17 00:00:00 2001 From: Aric Cyr Date: Mon, 19 Sep 2022 17:42:22 -0400 Subject: Revert "drm/amd/display: correct hostvm flag" This reverts commit 796d6a37ff5ffaf9f2dc0f3f4bf9f4a1034c00de. 4K144 resolution isn't available on DCN31. Reviewed-by: Sherry Wang Acked-by: Hamza Mahfooz Signed-off-by: Aric Cyr Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 8c1a6fb36306..8745132d6374 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -890,7 +890,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_z10 = true, .optimize_edp_link_rate = true, .enable_z9_disable_interface = true, /* Allow support for the PMFW interface for disable Z9*/ - .dml_hostvm_override = DML_HOSTVM_NO_OVERRIDE, + .dml_hostvm_override = DML_HOSTVM_OVERRIDE_FALSE, }; static const struct dc_debug_options debug_defaults_diags = { -- cgit From dfb3367bd082ccf52d3c13ff62257f08407dffcf Mon Sep 17 00:00:00 2001 From: Charlene Liu Date: Tue, 20 Sep 2022 09:23:06 -0400 Subject: drm/amd/display: prevent S4 test from failing [why] limit the vm prefetch check for now, until the feature is fully verified. Reviewed-by: Hansen Dsouza Acked-by: Hamza Mahfooz Signed-off-by: Charlene Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c index 5752271f22df..c5e200d09038 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c @@ -67,15 +67,9 @@ static uint32_t convert_and_clamp( void dcn21_dchvm_init(struct hubbub *hubbub) { struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub); - uint32_t riommu_active, prefetch_done; + uint32_t riommu_active; int i; - REG_GET(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, &prefetch_done); - - if (prefetch_done) { - hubbub->riommu_active = true; - return; - } //Init DCHVM block REG_UPDATE(DCHVM_CTRL0, HOSTVM_INIT_REQ, 1); -- cgit From 40169e2f37127b7fe60736045b1f9fc04f76b471 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Tue, 20 Sep 2022 19:26:27 -0400 Subject: drm/amd/display: Disable GSL when enabling phantom pipe [Description] When enabling phantom pipe on a pipe that was previously using immediate flip, we have to disable GSL or this will prevent the update from taking place right away on the phantom pipe when we enable it in FW Reviewed-by: Jun Lei Acked-by: Hamza Mahfooz Signed-off-by: Alvin Lee Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c index 2038cbda33f7..830562f4139d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c @@ -79,6 +79,8 @@ void hubp32_phantom_hubp_post_enable(struct hubp *hubp) uint32_t reg_val; struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + /* For phantom pipe enable, disable GSL */ + REG_UPDATE(DCSURF_FLIP_CONTROL2, SURFACE_GSL_ENABLE, 0); REG_UPDATE(DCHUBP_CNTL, HUBP_BLANK_EN, 1); reg_val = REG_READ(DCHUBP_CNTL); if (reg_val) { -- cgit From 283e0a673cdf59fe103707ac0466492b315c81a2 Mon Sep 17 00:00:00 2001 From: Wenjing Liu Date: Thu, 22 Sep 2022 14:22:04 -0400 Subject: drm/amd/display: fix integer overflow during MSA V_Freq calculation [why] Analyzer shows incorrect V freq in MSA for some large timing. [how] Cast an 32 bit integer to uint64_t before multiplication to avoid integer overflow for a very large timing. Reviewed-by: Ariel Bernstein Acked-by: Hamza Mahfooz Signed-off-by: Wenjing Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c index 52fb2bf3d578..d71d89268a07 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c @@ -197,7 +197,7 @@ static void dcn31_hpo_dp_stream_enc_set_stream_attribute( uint32_t h_back_porch; uint32_t h_width; uint32_t v_height; - unsigned long long v_freq; + uint64_t v_freq; uint8_t misc0 = 0; uint8_t misc1 = 0; uint8_t hsp; @@ -360,7 +360,7 @@ static void dcn31_hpo_dp_stream_enc_set_stream_attribute( v_height = hw_crtc_timing.v_border_top + hw_crtc_timing.v_addressable + hw_crtc_timing.v_border_bottom; hsp = hw_crtc_timing.flags.HSYNC_POSITIVE_POLARITY ? 0 : 0x80; vsp = hw_crtc_timing.flags.VSYNC_POSITIVE_POLARITY ? 0 : 0x80; - v_freq = hw_crtc_timing.pix_clk_100hz * 100; + v_freq = (uint64_t)hw_crtc_timing.pix_clk_100hz * 100; /* MSA Packet Mapping to 32-bit Link Symbols - DP2 spec, section 2.7.4.1 * -- cgit From 749b6c2ac9d9a7a4d8f4c2e4dc6fa830fd6c6ac7 Mon Sep 17 00:00:00 2001 From: "Leo (Hanghong) Ma" Date: Tue, 20 Sep 2022 15:23:42 -0400 Subject: drm/amd/display: AUX tracing cleanup [Why && How] Remove the unnecessary AUX trace and use one trace for AUX failure. Reviewed-by: Martin Leung Acked-by: Hamza Mahfooz Signed-off-by: Leo (Hanghong) Ma Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dce/dce_aux.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index 32782ef9ef77..140297c8ff55 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -942,10 +942,6 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, case AUX_RET_ERROR_ENGINE_ACQUIRE: case AUX_RET_ERROR_UNKNOWN: default: - DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION, - LOG_FLAG_I2cAux_DceAux, - "dce_aux_transfer_with_retries: Failure: operation_result=%d", - (int)operation_result); goto fail; } } @@ -953,14 +949,11 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, fail: DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR, LOG_FLAG_Error_I2cAux, - "dce_aux_transfer_with_retries: FAILURE"); + "%s: Failure: operation_result=%d", + __func__, + (int)operation_result); if (!payload_reply) payload->reply = NULL; - DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_ERROR, - WPP_BIT_FLAG_DC_ERROR, - "AUX transaction failed. Result: %d", - operation_result); - return false; } -- cgit From 7aeb2e47e43d5acd4638c64b4c0c01ad90feea51 Mon Sep 17 00:00:00 2001 From: Iswara Nagulendran Date: Mon, 19 Sep 2022 15:53:56 -0400 Subject: drm/amd/display: Allow PSR exit when panel is disconnected [HOW&WHY] Fixed check to only avoid PSR entry when panel is disconnected. PSR exit can be permitted to restore the HW to it's non-PSR state. Reviewed-by: Jayendran Ramani Acked-by: Hamza Mahfooz Signed-off-by: Iswara Nagulendran Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 3d19fb92333b..895c6e6bfeb8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3143,7 +3143,7 @@ bool dc_link_set_psr_allow_active(struct dc_link *link, const bool *allow_active if (!dc_get_edp_link_panel_inst(dc, link, &panel_inst)) return false; - if (allow_active && link->type == dc_connection_none) { + if ((allow_active != NULL) && (*allow_active == true) && (link->type == dc_connection_none)) { // Don't enter PSR if panel is not connected return false; } -- cgit From 1178ac68dc2869a2f4192600b701de3d853272d2 Mon Sep 17 00:00:00 2001 From: Ian Chen Date: Tue, 23 Aug 2022 17:26:51 +0800 Subject: drm/amd/display: Refactor edp ILR caps codes We split out ILR config from "global" to "per-panel" config settings. Reviewed-by: Anthony Koo Acked-by: Hamza Mahfooz Signed-off-by: Ian Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 5 ++++- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 4 ++-- drivers/gpu/drm/amd/display/dc/dc.h | 1 - drivers/gpu/drm/amd/display/dc/dc_link.h | 4 ++++ drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c | 13 ++++++++++++- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c | 13 ++++++++++++- drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c | 13 ++++++++++++- drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c | 13 ++++++++++++- drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c | 13 ++++++++++++- drivers/gpu/drm/amd/display/dc/inc/core_types.h | 1 + 10 files changed, 71 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 895c6e6bfeb8..c4daef1e708c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1307,7 +1307,10 @@ static bool detect_link_and_local_sink(struct dc_link *link, } if (link->connector_signal == SIGNAL_TYPE_EDP) { - // Init dc_panel_config + /* Init dc_panel_config by HW config */ + if (dc_ctx->dc->res_pool->funcs->get_panel_config_defaults) + dc_ctx->dc->res_pool->funcs->get_panel_config_defaults(&link->panel_config); + /* Pickup base DM settings */ dm_helpers_init_panel_settings(dc_ctx, &link->panel_config, sink); // Override dc_panel_config if system has specific settings dm_helpers_override_panel_settings(dc_ctx, &link->panel_config); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index c57df45e83ff..70456580eecc 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -5795,7 +5795,7 @@ void detect_edp_sink_caps(struct dc_link *link) * Per VESA eDP spec, "The DPCD revision for eDP v1.4 is 13h" */ if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_13 && - (link->dc->debug.optimize_edp_link_rate || + (link->panel_config.ilr.optimize_edp_link_rate || link->reported_link_cap.link_rate == LINK_RATE_UNKNOWN)) { // Read DPCD 00010h - 0001Fh 16 bytes at one shot core_link_read_dpcd(link, DP_SUPPORTED_LINK_RATES, @@ -6744,7 +6744,7 @@ bool is_edp_ilr_optimization_required(struct dc_link *link, struct dc_crtc_timin ASSERT(link || crtc_timing); // invalid input if (link->dpcd_caps.edp_supported_link_rates_count == 0 || - !link->dc->debug.optimize_edp_link_rate) + !link->panel_config.ilr.optimize_edp_link_rate) return false; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 2ecf36e6329b..458a4f431ac6 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -821,7 +821,6 @@ struct dc_debug_options { /* Enable dmub aux for legacy ddc */ bool enable_dmub_aux_for_legacy_ddc; bool disable_fams; - bool optimize_edp_link_rate; /* eDP ILR */ /* FEC/PSR1 sequence enable delay in 100us */ uint8_t fec_enable_delay_in100us; bool enable_driver_sequence_debug; diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index bf5f9e2773bc..caf0c7af2d0b 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -138,6 +138,10 @@ struct dc_panel_config { bool disable_dsc_edp; unsigned int force_dsc_edp_policy; } dsc; + /* eDP ILR */ + struct ilr { + bool optimize_edp_link_rate; /* eDP ILR */ + } ilr; }; /* * A link contains one or more sinks and their connected status. diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 7cb35bb1c0f1..887081472c0d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -657,7 +657,6 @@ static const struct dc_debug_options debug_defaults_drv = { .usbc_combo_phy_reset_wa = true, .dmub_command_table = true, .use_max_lb = true, - .optimize_edp_link_rate = true }; static const struct dc_debug_options debug_defaults_diags = { @@ -677,6 +676,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + enum dcn20_clk_src_array_id { DCN20_CLK_SRC_PLL0, DCN20_CLK_SRC_PLL1, @@ -1367,6 +1372,11 @@ static struct panel_cntl *dcn21_panel_cntl_create(const struct panel_cntl_init_d return &panel_cntl->base; } +static void dcn21_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + #define CTX ctx #define REG(reg_name) \ @@ -1408,6 +1418,7 @@ static const struct resource_funcs dcn21_res_pool_funcs = { .set_mcif_arb_params = dcn20_set_mcif_arb_params, .find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link, .update_bw_bounding_box = dcn21_update_bw_bounding_box, + .get_panel_config_defaults = dcn21_get_panel_config_defaults, }; static bool dcn21_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 8745132d6374..fddc21a5a04c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -888,7 +888,6 @@ static const struct dc_debug_options debug_defaults_drv = { } }, .disable_z10 = true, - .optimize_edp_link_rate = true, .enable_z9_disable_interface = true, /* Allow support for the PMFW interface for disable Z9*/ .dml_hostvm_override = DML_HOSTVM_OVERRIDE_FALSE, }; @@ -911,6 +910,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + static void dcn31_dpp_destroy(struct dpp **dpp) { kfree(TO_DCN20_DPP(*dpp)); @@ -1803,6 +1808,11 @@ validate_out: return out; } +static void dcn31_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap }; @@ -1829,6 +1839,7 @@ static struct resource_funcs dcn31_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn31_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn31_get_panel_config_defaults, }; static struct clock_source *dcn30_clock_source_create( diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 24ec71cbd3e3..70b647b9b4d3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -914,7 +914,6 @@ static const struct dc_debug_options debug_defaults_drv = { .afmt = true, } }, - .optimize_edp_link_rate = true, .seamless_boot_odm_combine = true }; @@ -936,6 +935,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + static void dcn31_dpp_destroy(struct dpp **dpp) { kfree(TO_DCN20_DPP(*dpp)); @@ -1675,6 +1680,11 @@ static void dcn314_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *b DC_FP_END(); } +static void dcn314_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static struct resource_funcs dcn314_res_pool_funcs = { .destroy = dcn314_destroy_resource_pool, .link_enc_create = dcn31_link_encoder_create, @@ -1697,6 +1707,7 @@ static struct resource_funcs dcn314_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn314_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn314_get_panel_config_defaults, }; static struct clock_source *dcn30_clock_source_create( diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c index eebb42c9ddd6..0f71bb86dc9a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c @@ -885,7 +885,6 @@ static const struct dc_debug_options debug_defaults_drv = { .afmt = true, } }, - .optimize_edp_link_rate = true, .psr_power_use_phy_fsm = 0, }; @@ -907,6 +906,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + static void dcn31_dpp_destroy(struct dpp **dpp) { kfree(TO_DCN20_DPP(*dpp)); @@ -1708,6 +1713,11 @@ static int dcn315_populate_dml_pipes_from_context( return pipe_cnt; } +static void dcn315_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap }; @@ -1734,6 +1744,7 @@ static struct resource_funcs dcn315_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn315_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn315_get_panel_config_defaults, }; static bool dcn315_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c index f4b52a35ad84..6b40a11ac83a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c @@ -885,7 +885,6 @@ static const struct dc_debug_options debug_defaults_drv = { .afmt = true, } }, - .optimize_edp_link_rate = true, }; static const struct dc_debug_options debug_defaults_diags = { @@ -906,6 +905,12 @@ static const struct dc_debug_options debug_defaults_diags = { .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .ilr = { + .optimize_edp_link_rate = true, + }, +}; + static void dcn31_dpp_destroy(struct dpp **dpp) { kfree(TO_DCN20_DPP(*dpp)); @@ -1710,6 +1715,11 @@ static int dcn316_populate_dml_pipes_from_context( return pipe_cnt; } +static void dcn316_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap }; @@ -1736,6 +1746,7 @@ static struct resource_funcs dcn316_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn316_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn316_get_panel_config_defaults, }; static bool dcn316_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 8919a2092ac5..4ff1392633a7 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -232,6 +232,7 @@ struct resource_funcs { unsigned int index); bool (*remove_phantom_pipes)(struct dc *dc, struct dc_state *context); + void (*get_panel_config_defaults)(struct dc_panel_config *panel_config); }; struct audio_support{ -- cgit From 380202c84454e89d29a9abc670f09b9145617d58 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Wed, 21 Sep 2022 12:04:25 -0400 Subject: drm/amd/display: For SubVP pipe split case use min transition into MPO [Description] - For SubVP pipe split case we need to use a minimial transition when opening MPO video since we are transitioning from 4 pipes to 3 pipes where an OPP for a previous MPCC will change - Also save and restore mall config when doing fast_validate in case there was a shallow copy of the dc->current_state Reviewed-by: Jun Lei Acked-by: Hamza Mahfooz Signed-off-by: Alvin Lee Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 36 +++++++++++ .../gpu/drm/amd/display/dc/dcn32/dcn32_resource.c | 18 ++++++ .../gpu/drm/amd/display/dc/dcn32/dcn32_resource.h | 20 ++++++ .../amd/display/dc/dcn32/dcn32_resource_helpers.c | 71 ++++++++++++++++++++++ 4 files changed, 145 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 4ba2c1f95dcb..a81a61f006c4 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3564,6 +3564,7 @@ static bool could_mpcc_tree_change_for_active_pipes(struct dc *dc, struct dc_stream_status *cur_stream_status = stream_get_status(dc->current_state, stream); bool force_minimal_pipe_splitting = false; + uint32_t i; *is_plane_addition = false; @@ -3595,6 +3596,36 @@ static bool could_mpcc_tree_change_for_active_pipes(struct dc *dc, } } + /* For SubVP pipe split case when adding MPO video + * we need to add a minimal transition. In this case + * there will be 2 streams (1 main stream, 1 phantom + * stream). + */ + if (cur_stream_status && + dc->current_state->stream_count == 2 && + stream->mall_stream_config.type == SUBVP_MAIN) { + bool is_pipe_split = false; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (dc->current_state->res_ctx.pipe_ctx[i].stream == stream && + (dc->current_state->res_ctx.pipe_ctx[i].bottom_pipe || + dc->current_state->res_ctx.pipe_ctx[i].next_odm_pipe)) { + is_pipe_split = true; + break; + } + } + + /* determine if minimal transition is required due to SubVP*/ + if (surface_count > 0 && is_pipe_split) { + if (cur_stream_status->plane_count > surface_count) { + force_minimal_pipe_splitting = true; + } else if (cur_stream_status->plane_count < surface_count) { + force_minimal_pipe_splitting = true; + *is_plane_addition = true; + } + } + } + return force_minimal_pipe_splitting; } @@ -3604,6 +3635,7 @@ static bool commit_minimal_transition_state(struct dc *dc, struct dc_state *transition_context = dc_create_state(dc); enum pipe_split_policy tmp_mpc_policy; bool temp_dynamic_odm_policy; + bool temp_subvp_policy; enum dc_status ret = DC_ERROR_UNEXPECTED; unsigned int i, j; @@ -3618,6 +3650,9 @@ static bool commit_minimal_transition_state(struct dc *dc, temp_dynamic_odm_policy = dc->debug.enable_single_display_2to1_odm_policy; dc->debug.enable_single_display_2to1_odm_policy = false; + temp_subvp_policy = dc->debug.force_disable_subvp; + dc->debug.force_disable_subvp = true; + dc_resource_state_copy_construct(transition_base_context, transition_context); //commit minimal state @@ -3646,6 +3681,7 @@ static bool commit_minimal_transition_state(struct dc *dc, dc->debug.pipe_split_policy = tmp_mpc_policy; dc->debug.enable_single_display_2to1_odm_policy = temp_dynamic_odm_policy; + dc->debug.force_disable_subvp = temp_subvp_policy; if (ret != DC_OK) { /*this should never happen*/ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 05de97ea855f..752a4accb116 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -1798,14 +1798,32 @@ bool dcn32_validate_bandwidth(struct dc *dc, int vlevel = 0; int pipe_cnt = 0; display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL); + struct mall_temp_config mall_temp_config; DC_LOGGER_INIT(dc->ctx->logger); + /* For fast validation, there are situations where a shallow copy of + * of the dc->current_state is created for the validation. In this case + * we want to save and restore the mall config because we always + * teardown subvp at the beginning of validation (and don't attempt + * to add it back if it's fast validation). If we don't restore the + * subvp config in cases of fast validation + shallow copy of the + * dc->current_state, the dc->current_state will have a partially + * removed subvp state when we did not intend to remove it. + */ + if (fast_validate) { + memset(&mall_temp_config, 0, sizeof(mall_temp_config)); + dcn32_save_mall_state(dc, context, &mall_temp_config); + } + BW_VAL_TRACE_COUNT(); DC_FP_START(); out = dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate); DC_FP_END(); + if (fast_validate) + dcn32_restore_mall_state(dc, context, &mall_temp_config); + if (pipe_cnt == 0) goto validate_out; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h index a24f538bdc4c..f76120e67c16 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h @@ -45,6 +45,17 @@ extern struct _vcs_dpi_ip_params_st dcn3_2_ip; extern struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc; +/* Temp struct used to save and restore MALL config + * during validation. + * + * TODO: Move MALL config into dc_state instead of stream struct + * to avoid needing to save/restore. + */ +struct mall_temp_config { + struct mall_stream_config mall_stream_config[MAX_PIPES]; + bool is_phantom_plane[MAX_PIPES]; +}; + struct dcn32_resource_pool { struct resource_pool base; }; @@ -122,6 +133,15 @@ void dcn32_determine_det_override(struct dc *dc, void dcn32_set_det_allocations(struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes); + +void dcn32_save_mall_state(struct dc *dc, + struct dc_state *context, + struct mall_temp_config *temp_config); + +void dcn32_restore_mall_state(struct dc *dc, + struct dc_state *context, + struct mall_temp_config *temp_config); + /* definitions for run time init of reg offsets */ /* CLK SRC */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c index 7f318ced5dee..d51d0c40ae5b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c @@ -380,3 +380,74 @@ void dcn32_set_det_allocations(struct dc *dc, struct dc_state *context, } else dcn32_determine_det_override(dc, context, pipes); } + +/** + * ******************************************************************************************* + * dcn32_save_mall_state: Save MALL (SubVP) state for fast validation cases + * + * This function saves the MALL (SubVP) case for fast validation cases. For fast validation, + * there are situations where a shallow copy of the dc->current_state is created for the + * validation. In this case we want to save and restore the mall config because we always + * teardown subvp at the beginning of validation (and don't attempt to add it back if it's + * fast validation). If we don't restore the subvp config in cases of fast validation + + * shallow copy of the dc->current_state, the dc->current_state will have a partially + * removed subvp state when we did not intend to remove it. + * + * NOTE: This function ONLY works if the streams are not moved to a different pipe in the + * validation. We don't expect this to happen in fast_validation=1 cases. + * + * @param [in]: dc: Current DC state + * @param [in]: context: New DC state to be programmed + * @param [out]: temp_config: struct used to cache the existing MALL state + * + * @return: void + * + * ******************************************************************************************* + */ +void dcn32_save_mall_state(struct dc *dc, + struct dc_state *context, + struct mall_temp_config *temp_config) +{ + uint32_t i; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->stream) + temp_config->mall_stream_config[i] = pipe->stream->mall_stream_config; + + if (pipe->plane_state) + temp_config->is_phantom_plane[i] = pipe->plane_state->is_phantom; + } +} + +/** + * ******************************************************************************************* + * dcn32_restore_mall_state: Restore MALL (SubVP) state for fast validation cases + * + * Restore the MALL state based on the previously saved state from dcn32_save_mall_state + * + * @param [in]: dc: Current DC state + * @param [in/out]: context: New DC state to be programmed, restore MALL state into here + * @param [in]: temp_config: struct that has the cached MALL state + * + * @return: void + * + * ******************************************************************************************* + */ +void dcn32_restore_mall_state(struct dc *dc, + struct dc_state *context, + struct mall_temp_config *temp_config) +{ + uint32_t i; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; + + if (pipe->stream) + pipe->stream->mall_stream_config = temp_config->mall_stream_config[i]; + + if (pipe->plane_state) + pipe->plane_state->is_phantom = temp_config->is_phantom_plane[i]; + } +} -- cgit From 345d6493476615494bd79a8fe77661918ea7c61a Mon Sep 17 00:00:00 2001 From: Leo Chen Date: Fri, 16 Sep 2022 14:13:11 -0400 Subject: drm/amd/display: Add log for LTTPR [Why & How] Adding log for LTTPR to facilitate debugging. Reviewed-by: Charlene Liu Acked-by: Hamza Mahfooz Signed-off-by: Leo Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 29 +++++++++++++++++++----- 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 70456580eecc..eb32e99fbde1 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -5090,6 +5090,7 @@ bool dp_retrieve_lttpr_cap(struct dc_link *link) (dp_convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == 0)) { ASSERT(0); link->dpcd_caps.lttpr_caps.phy_repeater_cnt = 0x80; + DC_LOG_DC("lttpr_caps forced phy_repeater_cnt = %d\n", link->dpcd_caps.lttpr_caps.phy_repeater_cnt); } /* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */ @@ -5098,6 +5099,7 @@ bool dp_retrieve_lttpr_cap(struct dc_link *link) if (is_lttpr_present) CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: "); + DC_LOG_DC("is_lttpr_present = %d\n", is_lttpr_present); return is_lttpr_present; } @@ -5134,6 +5136,7 @@ void dp_get_lttpr_mode_override(struct dc_link *link, enum lttpr_mode *override) } else if (link->dc->debug.lttpr_mode_override == LTTPR_MODE_NON_LTTPR) { *override = LTTPR_MODE_NON_LTTPR; } + DC_LOG_DC("lttpr_mode_override chose LTTPR_MODE = %d\n", (uint8_t)(*override)); } enum lttpr_mode dp_decide_8b_10b_lttpr_mode(struct dc_link *link) @@ -5146,22 +5149,34 @@ enum lttpr_mode dp_decide_8b_10b_lttpr_mode(struct dc_link *link) return LTTPR_MODE_NON_LTTPR; if (vbios_lttpr_aware) { - if (vbios_lttpr_force_non_transparent) + if (vbios_lttpr_force_non_transparent) { + DC_LOG_DC("chose LTTPR_MODE_NON_TRANSPARENT due to VBIOS DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE set to 1.\n"); return LTTPR_MODE_NON_TRANSPARENT; - else + } else { + DC_LOG_DC("chose LTTPR_MODE_NON_TRANSPARENT by default due to VBIOS not set DCE_INFO_CAPS_LTTPR_SUPPORT_ENABLE set to 1.\n"); return LTTPR_MODE_TRANSPARENT; + } } if (link->dc->config.allow_lttpr_non_transparent_mode.bits.DP1_4A && - link->dc->caps.extended_aux_timeout_support) + link->dc->caps.extended_aux_timeout_support) { + DC_LOG_DC("chose LTTPR_MODE_NON_TRANSPARENT by default and dc->config.allow_lttpr_non_transparent_mode.bits.DP1_4A set to 1.\n"); return LTTPR_MODE_NON_TRANSPARENT; + } + DC_LOG_DC("chose LTTPR_MODE_NON_LTTPR.\n"); return LTTPR_MODE_NON_LTTPR; } enum lttpr_mode dp_decide_128b_132b_lttpr_mode(struct dc_link *link) { - return dp_is_lttpr_present(link) ? LTTPR_MODE_NON_TRANSPARENT : LTTPR_MODE_NON_LTTPR; + enum lttpr_mode mode = LTTPR_MODE_NON_LTTPR; + + if (dp_is_lttpr_present(link)) + mode = LTTPR_MODE_NON_TRANSPARENT; + + DC_LOG_DC("128b_132b chose LTTPR_MODE %d.\n", mode); + return mode; } static bool get_usbc_cable_id(struct dc_link *link, union dp_cable_id *cable_id) @@ -5179,9 +5194,10 @@ static bool get_usbc_cable_id(struct dc_link *link, union dp_cable_id *cable_id) cmd.cable_id.data.input.phy_inst = resource_transmitter_to_phy_idx( link->dc, link->link_enc->transmitter); if (dc_dmub_srv_cmd_with_reply_data(link->ctx->dmub_srv, &cmd) && - cmd.cable_id.header.ret_status == 1) + cmd.cable_id.header.ret_status == 1) { cable_id->raw = cmd.cable_id.data.output_raw; - + DC_LOG_DC("usbc_cable_id = %d.\n", cable_id->raw); + } return cmd.cable_id.header.ret_status == 1; } @@ -5228,6 +5244,7 @@ static enum dc_status wa_try_to_wake_dprx(struct dc_link *link, uint64_t timeout lttpr_present = dp_is_lttpr_present(link) || (!vbios_lttpr_interop || !link->dc->caps.extended_aux_timeout_support); + DC_LOG_DC("lttpr_present = %d.\n", lttpr_present ? 1 : 0); /* Issue an AUX read to test DPRX responsiveness. If LTTPR is supported the first read is expected to * be to determine LTTPR capabilities. Otherwise trying to read power state should be an innocuous AUX read. -- cgit From e4e481e4d838f30985dd46d43ed195110ed265f5 Mon Sep 17 00:00:00 2001 From: Zhikai Zhai Date: Tue, 20 Sep 2022 18:51:02 +0800 Subject: drm/amd/display: skip commit minimal transition state [WHY] Now dynamic ODM will now be disabled when MPO is required safe transitions to avoid underflow, but we are triggering the way of minimal transition too often. Commit state of dc with no check will do pipeline setup which may re-initialize the component with no need such as audio. [HOW] Just do the minimal transition when all of pipes are in use, otherwise return true to skip. Reviewed-by: Dillon Varone Acked-by: Hamza Mahfooz Signed-off-by: Zhikai Zhai Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index a81a61f006c4..6216ceb790b4 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3638,10 +3638,30 @@ static bool commit_minimal_transition_state(struct dc *dc, bool temp_subvp_policy; enum dc_status ret = DC_ERROR_UNEXPECTED; unsigned int i, j; + unsigned int pipe_in_use = 0; if (!transition_context) return false; + /* check current pipes in use*/ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe = &transition_base_context->res_ctx.pipe_ctx[i]; + + if (pipe->plane_state) + pipe_in_use++; + } + + /* When the OS add a new surface if we have been used all of pipes with odm combine + * and mpc split feature, it need use commit_minimal_transition_state to transition safely. + * After OS exit MPO, it will back to use odm and mpc split with all of pipes, we need + * call it again. Otherwise return true to skip. + * + * Reduce the scenarios to use dc_commit_state_no_check in the stage of flip. Especially + * enter/exit MPO when DCN still have enough resources. + */ + if (pipe_in_use != dc->res_pool->pipe_count) + return true; + if (!dc->config.is_vmin_only_asic) { tmp_mpc_policy = dc->debug.pipe_split_policy; dc->debug.pipe_split_policy = MPC_SPLIT_AVOID; -- cgit From 4931ce22eca6ed5f8a3a3820fd13e586011ac219 Mon Sep 17 00:00:00 2001 From: Dmytro Laktyushkin Date: Fri, 16 Sep 2022 15:55:55 -0400 Subject: drm/amd/display: add dummy pstate workaround to dcn315 DCN315 has to always allow pstate change or SMU will hang. This workaround achieves this by applying a low pstate change latency to be used when pstate is calculated to be unsupported. This lower latency only accounts for memory retraining; a previous change handles locking in the highest available pstate allowing us to minimize required latency hiding to only account for memory retraining. Reviewed-by: Charlene Liu Acked-by: Hamza Mahfooz Signed-off-by: Dmytro Laktyushkin Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/dcn30/dcn30_resource.c | 4 + .../drm/amd/display/dc/dcn315/dcn315_resource.c | 2 +- .../gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c | 89 +++++----------------- .../gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h | 1 + 4 files changed, 27 insertions(+), 69 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 3a3b2ac791c7..020f512e9690 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -1655,6 +1655,9 @@ noinline bool dcn30_internal_validate_bw( if (!pipes) return false; + context->bw_ctx.dml.vba.maxMpcComb = 0; + context->bw_ctx.dml.vba.VoltageLevel = 0; + context->bw_ctx.dml.vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive; dc->res_pool->funcs->update_soc_for_wm_a(dc, context); pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); @@ -1873,6 +1876,7 @@ noinline bool dcn30_internal_validate_bw( if (repopulate_pipes) pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); + context->bw_ctx.dml.vba.VoltageLevel = vlevel; *vlevel_out = vlevel; *pipe_cnt_out = pipe_cnt; diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c index 0f71bb86dc9a..58746c437554 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c @@ -1731,7 +1731,7 @@ static struct resource_funcs dcn315_res_pool_funcs = { .panel_cntl_create = dcn31_panel_cntl_create, .validate_bandwidth = dcn31_validate_bandwidth, .calculate_wm_and_dlg = dcn31_calculate_wm_and_dlg, - .update_soc_for_wm_a = dcn31_update_soc_for_wm_a, + .update_soc_for_wm_a = dcn315_update_soc_for_wm_a, .populate_dml_pipes = dcn315_populate_dml_pipes_from_context, .acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer, .add_stream_to_ctx = dcn30_add_stream_to_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index 94b0842cd89b..87bfc42bdaaf 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c @@ -292,6 +292,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = { .urgent_latency_adjustment_fabric_clock_component_us = 0, .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, .num_chans = 4, + .dummy_pstate_latency_us = 10.0 }; struct _vcs_dpi_ip_params_st dcn3_16_ip = { @@ -459,6 +460,23 @@ void dcn31_update_soc_for_wm_a(struct dc *dc, struct dc_state *context) } } +void dcn315_update_soc_for_wm_a(struct dc *dc, struct dc_state *context) +{ + dc_assert_fp_enabled(); + + if (dc->clk_mgr->bw_params->wm_table.entries[WM_A].valid) { + /* For 315 pstate change is only supported if possible in vactive */ + if (context->bw_ctx.dml.vba.DRAMClockChangeSupport[context->bw_ctx.dml.vba.VoltageLevel][context->bw_ctx.dml.vba.maxMpcComb] != dm_dram_clock_change_vactive) + context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us; + else + context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.entries[WM_A].pstate_latency_us; + context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = + dc->clk_mgr->bw_params->wm_table.entries[WM_A].sr_enter_plus_exit_time_us; + context->bw_ctx.dml.soc.sr_exit_time_us = + dc->clk_mgr->bw_params->wm_table.entries[WM_A].sr_exit_time_us; + } +} + void dcn31_calculate_wm_and_dlg_fp( struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, @@ -486,72 +504,6 @@ void dcn31_calculate_wm_and_dlg_fp( pipes[0].clks_cfg.dcfclk_mhz = dcfclk; pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].socclk_mhz; -#if 0 // TODO - /* Set B: - * TODO - */ - if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_B].valid) { - if (vlevel == 0) { - pipes[0].clks_cfg.voltage = 1; - pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dcfclk_mhz; - } - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_B].dml_input.pstate_latency_us; - context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_B].dml_input.sr_enter_plus_exit_time_us; - context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_B].dml_input.sr_exit_time_us; - } - context->bw_ctx.bw.dcn.watermarks.b.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_enter_plus_exit_z8_ns = get_wm_z8_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_exit_z8_ns = get_wm_z8_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.b.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - - pipes[0].clks_cfg.voltage = vlevel; - pipes[0].clks_cfg.dcfclk_mhz = dcfclk; - - /* Set C: - * TODO - */ - if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) { - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.pstate_latency_us; - context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_enter_plus_exit_time_us; - context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].dml_input.sr_exit_time_us; - } - context->bw_ctx.bw.dcn.watermarks.c.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_z8_ns = get_wm_z8_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_z8_ns = get_wm_z8_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.c.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - - /* Set D: - * TODO - */ - if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].valid) { - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.pstate_latency_us; - context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.sr_enter_plus_exit_time_us; - context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_D].dml_input.sr_exit_time_us; - } - context->bw_ctx.bw.dcn.watermarks.d.urgent_ns = get_wm_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_enter_plus_exit_z8_ns = get_wm_z8_stutter_enter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_exit_z8_ns = get_wm_z8_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - context->bw_ctx.bw.dcn.watermarks.d.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; -#endif - /* Set A: * All clocks min required * @@ -568,11 +520,9 @@ void dcn31_calculate_wm_and_dlg_fp( context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; context->bw_ctx.bw.dcn.watermarks.a.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - /* TODO: remove: */ context->bw_ctx.bw.dcn.watermarks.b = context->bw_ctx.bw.dcn.watermarks.a; context->bw_ctx.bw.dcn.watermarks.c = context->bw_ctx.bw.dcn.watermarks.a; context->bw_ctx.bw.dcn.watermarks.d = context->bw_ctx.bw.dcn.watermarks.a; - /* end remove*/ for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { if (!context->res_ctx.pipe_ctx[i].stream) @@ -594,6 +544,9 @@ void dcn31_calculate_wm_and_dlg_fp( } dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); + /* For 31x apu pstate change is only supported if possible in vactive */ + context->bw_ctx.bw.dcn.clk.p_state_change_support = + context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] == dm_dram_clock_change_vactive; } void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h index 4372f17b55d4..fd58b2561ec9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h @@ -35,6 +35,7 @@ void dcn31_zero_pipe_dcc_fraction(display_e2e_pipe_params_st *pipes, int pipe_cnt); void dcn31_update_soc_for_wm_a(struct dc *dc, struct dc_state *context); +void dcn315_update_soc_for_wm_a(struct dc *dc, struct dc_state *context); void dcn31_calculate_wm_and_dlg_fp( struct dc *dc, struct dc_state *context, -- cgit From 8cab4ef0ad9521030e1ae4bd294a1e2e6a04659f Mon Sep 17 00:00:00 2001 From: Lewis Huang Date: Fri, 23 Sep 2022 10:42:40 +0800 Subject: drm/amd/display: Keep OTG on when Z10 is disable [Why] Disable OTG when PSRSU with z10 even if z10 is disable [How] Reverse condition to keep OTG on when Z10 is disable Reviewed-by: Robin Chen Acked-by: Hamza Mahfooz Signed-off-by: Lewis Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index c4daef1e708c..d7b1ace6328a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3378,8 +3378,8 @@ bool dc_link_setup_psr(struct dc_link *link, case FAMILY_YELLOW_CARP: case AMDGPU_FAMILY_GC_10_3_6: case AMDGPU_FAMILY_GC_11_0_1: - if(!dc->debug.disable_z10) - psr_context->psr_level.bits.SKIP_CRTC_DISABLE = false; + if (dc->debug.disable_z10) + psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true; break; default: psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true; -- cgit From b808a7eb30b02e05023b505fe6db590ba799683f Mon Sep 17 00:00:00 2001 From: Dillon Varone Date: Tue, 20 Sep 2022 20:50:49 -0400 Subject: drm/amd/display: Increase compbuf size prior to updating clocks [WHY?] Clocks are updating based on the incoming context's support, however the new compbuf size is not programmed prior to udpating clocks, which can result in P-State hangs. [HOW?] Increase compbuf size prior to updating clocks. Reviewed-by: Alvin Lee Reviewed-by: Martin Leung Acked-by: Hamza Mahfooz Signed-off-by: Dillon Varone Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index e1d271fe9e64..7de511fd004b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2018,6 +2018,10 @@ void dcn20_optimize_bandwidth( context->bw_ctx.bw.dcn.clk.dramclk_khz <= dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000) dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->dc_mode_softmax_memclk); + /* increase compbuf size */ + if (hubbub->funcs->program_compbuf_size) + hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); + dc->clk_mgr->funcs->update_clocks( dc->clk_mgr, context, @@ -2033,9 +2037,6 @@ void dcn20_optimize_bandwidth( pipe_ctx->dlg_regs.optimized_min_dst_y_next_start); } } - /* increase compbuf size */ - if (hubbub->funcs->program_compbuf_size) - hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); } bool dcn20_update_bandwidth( -- cgit From baec651f4160f4c3f029edf84bbc18b4fcba9cf5 Mon Sep 17 00:00:00 2001 From: Wenjing Liu Date: Thu, 22 Sep 2022 14:36:32 -0400 Subject: drm/amd/display: write all 4 bytes of FFE_PRESET dpcd value [why] According to specs, it expects us to write all 4 bytes even if current lane count is less than 4. Reviewed-by: George Shen Acked-by: Hamza Mahfooz Signed-off-by: Wenjing Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 37 ++++++++++++------------ 1 file changed, 18 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index eb32e99fbde1..1254d38f1778 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -944,6 +944,23 @@ enum dc_status dp_get_lane_status_and_lane_adjust( return status; } +static enum dc_status dpcd_128b_132b_set_lane_settings( + struct dc_link *link, + const struct link_training_settings *link_training_setting) +{ + enum dc_status status = core_link_write_dpcd(link, + DP_TRAINING_LANE0_SET, + (uint8_t *)(link_training_setting->dpcd_lane_settings), + sizeof(link_training_setting->dpcd_lane_settings)); + + DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X TX_FFE_PRESET_VALUE = %x\n", + __func__, + DP_TRAINING_LANE0_SET, + link_training_setting->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); + return status; +} + + enum dc_status dpcd_set_lane_settings( struct dc_link *link, const struct link_training_settings *link_training_setting, @@ -964,16 +981,6 @@ enum dc_status dpcd_set_lane_settings( link_training_setting->link_settings.lane_count); if (is_repeater(link_training_setting, offset)) { - if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_128b_132b_ENCODING) - DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n" - " 0x%X TX_FFE_PRESET_VALUE = %x\n", - __func__, - offset, - lane0_set_address, - link_training_setting->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); - else if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_8b_10b_ENCODING) DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Repeater ID: %d\n" " 0x%X VS set = %x PE set = %x max VS Reached = %x max PE Reached = %x\n", __func__, @@ -985,14 +992,6 @@ enum dc_status dpcd_set_lane_settings( link_training_setting->dpcd_lane_settings[0].bits.MAX_PRE_EMPHASIS_REACHED); } else { - if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_128b_132b_ENCODING) - DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X TX_FFE_PRESET_VALUE = %x\n", - __func__, - lane0_set_address, - link_training_setting->dpcd_lane_settings[0].tx_ffe.PRESET_VALUE); - else if (dp_get_link_encoding_format(&link_training_setting->link_settings) == - DP_8b_10b_ENCODING) DC_LOG_HW_LINK_TRAINING("%s\n 0x%X VS set = %x PE set = %x max VS Reached = %x max PE Reached = %x\n", __func__, lane0_set_address, @@ -2023,7 +2022,7 @@ static enum link_training_result dp_perform_128b_132b_channel_eq_done_sequence( result = DP_128b_132b_LT_FAILED; } else { dp_set_hw_lane_settings(link, link_res, lt_settings, DPRX); - dpcd_set_lane_settings(link, lt_settings, DPRX); + dpcd_128b_132b_set_lane_settings(link, lt_settings); } loop_count++; } -- cgit From 51619c671316e96d7adaf2b6ea94ce245b81b6dd Mon Sep 17 00:00:00 2001 From: Aric Cyr Date: Fri, 23 Sep 2022 17:09:54 -0400 Subject: drm/amd/display: Fix vupdate and vline position calculation [how] Large deltas for periodic interrupts could result in the interrupt not being programmed properly and thus not firing. [why] Add proper wrap-around support for calculating VUPDATE and VLINE positions. Reviewed-by: Jun Lei Acked-by: Hamza Mahfooz Signed-off-by: Aric Cyr Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 60 +++++++++------------- 1 file changed, 25 insertions(+), 35 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 4390f6d7050f..f4b3ec32a331 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3818,28 +3818,14 @@ void dcn10_calc_vupdate_position( uint32_t *start_line, uint32_t *end_line) { - const struct dc_crtc_timing *dc_crtc_timing = &pipe_ctx->stream->timing; - int vline_int_offset_from_vupdate = - pipe_ctx->stream->periodic_interrupt.lines_offset; - int vupdate_offset_from_vsync = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx); - int start_position; - - if (vline_int_offset_from_vupdate > 0) - vline_int_offset_from_vupdate--; - else if (vline_int_offset_from_vupdate < 0) - vline_int_offset_from_vupdate++; + const struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; + int vupdate_pos = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx); - start_position = vline_int_offset_from_vupdate + vupdate_offset_from_vsync; - - if (start_position >= 0) - *start_line = start_position; + if (vupdate_pos >= 0) + *start_line = vupdate_pos - ((vupdate_pos / timing->v_total) * timing->v_total); else - *start_line = dc_crtc_timing->v_total + start_position - 1; - - *end_line = *start_line + 2; - - if (*end_line >= dc_crtc_timing->v_total) - *end_line = 2; + *start_line = vupdate_pos + ((-vupdate_pos / timing->v_total) + 1) * timing->v_total - 1; + *end_line = (*start_line + 2) % timing->v_total; } static void dcn10_cal_vline_position( @@ -3848,23 +3834,27 @@ static void dcn10_cal_vline_position( uint32_t *start_line, uint32_t *end_line) { - switch (pipe_ctx->stream->periodic_interrupt.ref_point) { - case START_V_UPDATE: - dcn10_calc_vupdate_position( - dc, - pipe_ctx, - start_line, - end_line); - break; - case START_V_SYNC: + const struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; + int vline_pos = pipe_ctx->stream->periodic_interrupt.lines_offset; + + if (pipe_ctx->stream->periodic_interrupt.ref_point == START_V_UPDATE) { + if (vline_pos > 0) + vline_pos--; + else if (vline_pos < 0) + vline_pos++; + + vline_pos += dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx); + if (vline_pos >= 0) + *start_line = vline_pos - ((vline_pos / timing->v_total) * timing->v_total); + else + *start_line = vline_pos + ((-vline_pos / timing->v_total) + 1) * timing->v_total - 1; + *end_line = (*start_line + 2) % timing->v_total; + } else if (pipe_ctx->stream->periodic_interrupt.ref_point == START_V_SYNC) { // vsync is line 0 so start_line is just the requested line offset - *start_line = pipe_ctx->stream->periodic_interrupt.lines_offset; - *end_line = *start_line + 2; - break; - default: + *start_line = vline_pos; + *end_line = (*start_line + 2) % timing->v_total; + } else ASSERT(0); - break; - } } void dcn10_setup_periodic_interrupt( -- cgit From 2d550a159c55ac836a554fd605545b0feb5f7266 Mon Sep 17 00:00:00 2001 From: Martin Leung Date: Fri, 23 Sep 2022 17:55:14 -0400 Subject: drm/amd/display: block odd h_total timings from halving pixel rate why: when dynamic odm was turned on, there is also logic to halve the pixelclk this still turned on when we avoided odm in the case of odd h_total timings how: block the pixel clk mechanism also in the case of odd h_total timings Reviewed-by: Jun Lei Acked-by: Hamza Mahfooz Signed-off-by: Martin Leung Signed-off-by: Alex Deucher --- .../display/dc/dcn32/dcn32_dio_stream_encoder.c | 35 +++++++++++++++++++++- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | 9 +++--- 2 files changed, 39 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c index 0e9dce414641..3195be9d38f5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c @@ -243,6 +243,39 @@ static bool is_two_pixels_per_containter(const struct dc_crtc_timing *timing) return two_pix; } +static bool is_h_timing_divisible_by_2(const struct dc_crtc_timing *timing) +{ + /* math borrowed from function of same name in inc/resource + * checks if h_timing is divisible by 2 + */ + + bool divisible = false; + uint16_t h_blank_start = 0; + uint16_t h_blank_end = 0; + + if (timing) { + h_blank_start = timing->h_total - timing->h_front_porch; + h_blank_end = h_blank_start - timing->h_addressable; + + /* HTOTAL, Hblank start/end, and Hsync start/end all must be + * divisible by 2 in order for the horizontal timing params + * to be considered divisible by 2. Hsync start is always 0. + */ + divisible = (timing->h_total % 2 == 0) && + (h_blank_start % 2 == 0) && + (h_blank_end % 2 == 0) && + (timing->h_sync_width % 2 == 0); + } + return divisible; +} + +static bool is_dp_dig_pixel_rate_div_policy(struct dc *dc, const struct dc_crtc_timing *timing) +{ + /* should be functionally the same as dcn32_is_dp_dig_pixel_rate_div_policy for DP encoders*/ + return is_h_timing_divisible_by_2(timing) && + dc->debug.enable_dp_dig_pixel_rate_div_policy; +} + static void enc32_stream_encoder_dp_unblank( struct dc_link *link, struct stream_encoder *enc, @@ -259,7 +292,7 @@ static void enc32_stream_encoder_dp_unblank( /* YCbCr 4:2:0 : Computed VID_M will be 2X the input rate */ if (is_two_pixels_per_containter(¶m->timing) || param->opp_cnt > 1 - || dc->debug.enable_dp_dig_pixel_rate_div_policy) { + || is_dp_dig_pixel_rate_div_policy(dc, ¶m->timing)) { /*this logic should be the same in get_pixel_clock_parameters() */ n_multiply = 1; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index a750343ca521..8012a48859b5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -1161,7 +1161,6 @@ unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsign { struct dc_stream_state *stream = pipe_ctx->stream; unsigned int odm_combine_factor = 0; - struct dc *dc = pipe_ctx->stream->ctx->dc; bool two_pix_per_container = false; // For phantom pipes, use the same programming as the main pipes @@ -1189,7 +1188,7 @@ unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsign } else { *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_4; - if ((odm_combine_factor == 2) || dc->debug.enable_dp_dig_pixel_rate_div_policy) + if ((odm_combine_factor == 2) || dcn32_is_dp_dig_pixel_rate_div_policy(pipe_ctx)) *k2_div = PIXEL_RATE_DIV_BY_2; } } @@ -1226,7 +1225,6 @@ void dcn32_unblank_stream(struct pipe_ctx *pipe_ctx, struct dc_link *link = stream->link; struct dce_hwseq *hws = link->dc->hwseq; struct pipe_ctx *odm_pipe; - struct dc *dc = pipe_ctx->stream->ctx->dc; uint32_t pix_per_cycle = 1; params.opp_cnt = 1; @@ -1245,7 +1243,7 @@ void dcn32_unblank_stream(struct pipe_ctx *pipe_ctx, pipe_ctx->stream_res.tg->inst); } else if (dc_is_dp_signal(pipe_ctx->stream->signal)) { if (optc2_is_two_pixels_per_containter(&stream->timing) || params.opp_cnt > 1 - || dc->debug.enable_dp_dig_pixel_rate_div_policy) { + || dcn32_is_dp_dig_pixel_rate_div_policy(pipe_ctx)) { params.timing.pix_clk_100hz /= 2; pix_per_cycle = 2; } @@ -1262,6 +1260,9 @@ bool dcn32_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx) { struct dc *dc = pipe_ctx->stream->ctx->dc; + if (!is_h_timing_divisible_by_2(pipe_ctx->stream)) + return false; + if (dc_is_dp_signal(pipe_ctx->stream->signal) && !is_dp_128b_132b_signal(pipe_ctx) && dc->debug.enable_dp_dig_pixel_rate_div_policy) return true; -- cgit From a2909ff460a8e02168b3658372ebc897f7ab2315 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 20 Sep 2022 13:06:50 -0400 Subject: drm/amd/display: Drop unused code for DCN32/321 Under DCN32/321 we identified some code paths that DC never executes. This commit removes those unused codes to avoid distractions when debugging issues. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- .../amd/display/dc/dcn32/dcn32_dio_link_encoder.c | 7 ------- .../amd/display/dc/dcn32/dcn32_dio_link_encoder.h | 4 ---- .../amd/display/dc/dcn32/dcn32_dio_stream_encoder.c | 20 -------------------- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c | 3 +-- .../amd/display/dc/dcn321/dcn321_dio_link_encoder.c | 1 - .../gpu/drm/amd/display/dc/dcn321/dcn321_resource.c | 2 -- 6 files changed, 1 insertion(+), 36 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c index fdae6aa89908..076969d928af 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.c @@ -150,12 +150,6 @@ static void dcn32_link_encoder_get_max_link_cap(struct link_encoder *enc, } -void enc32_set_dig_output_mode(struct link_encoder *enc, uint8_t pix_per_container) -{ - struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_OUTPUT_PIXEL_MODE, pix_per_container); -} - static const struct link_encoder_funcs dcn32_link_enc_funcs = { .read_state = link_enc2_read_state, .validate_output_with_stream = @@ -186,7 +180,6 @@ static const struct link_encoder_funcs dcn32_link_enc_funcs = { .is_in_alt_mode = dcn32_link_encoder_is_in_alt_mode, .get_max_link_cap = dcn32_link_encoder_get_max_link_cap, .set_dio_phy_mux = dcn31_link_encoder_set_dio_phy_mux, - .set_dig_output_mode = enc32_set_dig_output_mode, }; void dcn32_link_encoder_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h index 749a1e8cb811..bbcfce06bec0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_link_encoder.h @@ -53,8 +53,4 @@ void dcn32_link_encoder_enable_dp_output( const struct dc_link_settings *link_settings, enum clock_source_id clock_source); -void enc32_set_dig_output_mode( - struct link_encoder *enc, - uint8_t pix_per_container); - #endif /* __DC_LINK_ENCODER__DCN32_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c index 3195be9d38f5..40e713c4e172 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c @@ -411,24 +411,6 @@ static void enc32_read_state(struct stream_encoder *enc, struct enc_state *s) } } -static void enc32_stream_encoder_reset_fifo(struct stream_encoder *enc) -{ - struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - uint32_t fifo_enabled; - - REG_GET(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, &fifo_enabled); - - if (fifo_enabled == 0) { - /* reset DIG resync FIFO */ - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1); - /* TODO: fix timeout when wait for DIG_FIFO_RESET_DONE */ - //REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 1, 100); - udelay(1); - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 0); - REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 0, 1, 100); - } -} - static void enc32_set_dig_input_mode(struct stream_encoder *enc, unsigned int pix_per_container) { struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); @@ -458,8 +440,6 @@ static const struct stream_encoder_funcs dcn32_str_enc_funcs = { enc3_stream_encoder_update_dp_info_packets, .stop_dp_info_packets = enc1_stream_encoder_stop_dp_info_packets, - .reset_fifo = - enc32_stream_encoder_reset_fifo, .dp_blank = enc1_stream_encoder_dp_blank, .dp_unblank = diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c index 830562f4139d..f4b901d393eb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c @@ -185,8 +185,7 @@ static struct hubp_funcs dcn32_hubp_funcs = { .hubp_update_force_pstate_disallow = hubp32_update_force_pstate_disallow, .phantom_hubp_post_enable = hubp32_phantom_hubp_post_enable, .hubp_update_mall_sel = hubp32_update_mall_sel, - .hubp_prepare_subvp_buffering = hubp32_prepare_subvp_buffering, - .hubp_set_flip_int = hubp1_set_flip_int + .hubp_prepare_subvp_buffering = hubp32_prepare_subvp_buffering }; bool hubp32_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_dio_link_encoder.c index 49682a31ecbd..fa9b6603cfd3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_dio_link_encoder.c @@ -91,7 +91,6 @@ static const struct link_encoder_funcs dcn321_link_enc_funcs = { .is_in_alt_mode = dcn20_link_encoder_is_in_alt_mode, .get_max_link_cap = dcn20_link_encoder_get_max_link_cap, .set_dio_phy_mux = dcn31_link_encoder_set_dio_phy_mux, - .set_dig_output_mode = enc32_set_dig_output_mode, }; void dcn321_link_encoder_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index aed0f689cbbf..910b63d874d5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -94,8 +94,6 @@ #include "dcn20/dcn20_vmid.h" #define DC_LOGGER_INIT(logger) -#define fixed16_to_double(x) (((double)x) / ((double) (1 << 16))) -#define fixed16_to_double_to_cpu(x) fixed16_to_double(le32_to_cpu(x)) enum dcn321_clk_src_array_id { DCN321_CLK_SRC_PLL0, -- cgit From 47b7dd9f68c12e7d33a0dfd3d9a5bed755097de0 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 20 Sep 2022 13:29:19 -0400 Subject: drm/amd/display: Update DCN321 hook that deals with pipe aquire DCN provides a hook to check if we can have a new pipe allocation based on some DC constraints. If the current configuration supports the new pipe request, DC updates its context; otherwise, it will keep the same configuration. This behavior is similar across multiple ASICs, and for this reason, we reused DCN20 on DCN321. However, this DCN32x has some peculiarities which require its function to avoid weird pipe split issues. This commit update this issue by using dcn32_acquire_idle_pipe_for_head_pipe_in_layer instead of dcn20_acquire_idle_pipe_for_layer. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index 910b63d874d5..6658849d5b4e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -1604,7 +1604,7 @@ static struct resource_funcs dcn321_res_pool_funcs = { .validate_bandwidth = dcn32_validate_bandwidth, .calculate_wm_and_dlg = dcn32_calculate_wm_and_dlg, .populate_dml_pipes = dcn32_populate_dml_pipes_from_context, - .acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer, + .acquire_idle_pipe_for_head_pipe_in_layer = dcn32_acquire_idle_pipe_for_head_pipe_in_layer, .add_stream_to_ctx = dcn30_add_stream_to_ctx, .add_dsc_to_stream_resource = dcn20_add_dsc_to_stream_resource, .remove_stream_from_ctx = dcn20_remove_stream_from_ctx, -- cgit From 9114b55fabae5522b7124af4f16ea6ce6378aa19 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 20 Sep 2022 14:27:04 -0400 Subject: drm/amd/display: Fix SubVP control flow in the MPO context SubVP has some issues related to how we allocate and enable it. This commit fixes this behavior by adding the proper check and configuration to the SubVP code path. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 16 ++++++++++++++-- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 18 ------------------ drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c | 6 ++++++ 3 files changed, 20 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 6216ceb790b4..40a34b600c8e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2946,6 +2946,12 @@ static bool update_planes_and_stream_state(struct dc *dc, dc_resource_state_copy_construct( dc->current_state, context); + /* For each full update, remove all existing phantom pipes first. + * Ensures that we have enough pipes for newly added MPO planes + */ + if (dc->res_pool->funcs->remove_phantom_pipes) + dc->res_pool->funcs->remove_phantom_pipes(dc, context); + /*remove old surfaces from context */ if (!dc_rem_all_planes_for_stream(dc, stream, context)) { @@ -3353,8 +3359,14 @@ static void commit_planes_for_stream(struct dc *dc, /* Since phantom pipe programming is moved to post_unlock_program_front_end, * move the SubVP lock to after the phantom pipes have been setup */ - if (dc->hwss.subvp_pipe_control_lock) - dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use); + if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) { + if (dc->hwss.subvp_pipe_control_lock) + dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use); + } else { + if (dc->hwss.subvp_pipe_control_lock) + dc->hwss.subvp_pipe_control_lock(dc, context, false, should_lock_all_pipes, NULL, subvp_prev_use); + } + return; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 7de511fd004b..d732b6f031a1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1860,24 +1860,6 @@ void dcn20_post_unlock_program_front_end( } } - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; - struct pipe_ctx *mpcc_pipe; - - if (pipe->vtp_locked) { - dc->hwseq->funcs.wait_for_blank_complete(pipe->stream_res.opp); - pipe->plane_res.hubp->funcs->set_blank(pipe->plane_res.hubp, true); - pipe->vtp_locked = false; - - for (mpcc_pipe = pipe->bottom_pipe; mpcc_pipe; mpcc_pipe = mpcc_pipe->bottom_pipe) - mpcc_pipe->plane_res.hubp->funcs->set_blank(mpcc_pipe->plane_res.hubp, true); - - for (i = 0; i < dc->res_pool->pipe_count; i++) - if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable) - dc->hwss.disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]); - } - } - for (i = 0; i < dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 752a4accb116..9585b25f10e5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -1680,6 +1680,8 @@ static void dcn32_enable_phantom_plane(struct dc *dc, phantom_plane->clip_rect.y = 0; phantom_plane->clip_rect.height = phantom_stream->timing.v_addressable; + phantom_plane->is_phantom = true; + dc_add_plane_to_context(dc, phantom_stream, phantom_plane, context); curr_pipe = curr_pipe->bottom_pipe; @@ -1749,6 +1751,10 @@ bool dcn32_remove_phantom_pipes(struct dc *dc, struct dc_state *context) pipe->stream->mall_stream_config.type = SUBVP_NONE; pipe->stream->mall_stream_config.paired_stream = NULL; } + + if (pipe->plane_state) { + pipe->plane_state->is_phantom = false; + } } return removed_pipe; } -- cgit From b33cd65df18f1cf60b066a02c09df92b4763bb31 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Wed, 21 Sep 2022 08:47:44 -0400 Subject: drm/amd/display: Remove OPTC lock check At some point, we decided to blank HUBP during pixel data blank, and to handle that, we added some OPTC lock checks. Later, we realized that this change caused multiple regression, and we removed it. Nevertheless, we still have some leftovers that might affect some ASIC behavior, and this commit drops those changes to keep the code consistent. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c | 11 ----------- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h | 1 - drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c | 1 - drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c | 1 - drivers/gpu/drm/amd/display/dc/inc/core_types.h | 1 - drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h | 1 - 6 files changed, 16 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index ea7739255119..143a900d4d3d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -679,16 +679,6 @@ void optc1_unlock(struct timing_generator *optc) OTG_MASTER_UPDATE_LOCK, 0); } -bool optc1_is_locked(struct timing_generator *optc) -{ - struct optc *optc1 = DCN10TG_FROM_TG(optc); - uint32_t locked; - - REG_GET(OTG_MASTER_UPDATE_LOCK, UPDATE_LOCK_STATUS, &locked); - - return (locked == 1); -} - void optc1_get_position(struct timing_generator *optc, struct crtc_position *position) { @@ -1583,7 +1573,6 @@ static const struct timing_generator_funcs dcn10_tg_funcs = { .enable_crtc_reset = optc1_enable_crtc_reset, .disable_reset_trigger = optc1_disable_reset_trigger, .lock = optc1_lock, - .is_locked = optc1_is_locked, .unlock = optc1_unlock, .enable_optc_clock = optc1_enable_optc_clock, .set_drr = optc1_set_drr, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h index 6323ca6dc3b3..88ac5f6f4c96 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h @@ -654,7 +654,6 @@ void optc1_set_blank(struct timing_generator *optc, bool enable_blanking); bool optc1_is_blanked(struct timing_generator *optc); -bool optc1_is_locked(struct timing_generator *optc); void optc1_program_blank_color( struct timing_generator *optc, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c index 1782b9c26cf4..02459a64ee21 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c @@ -319,7 +319,6 @@ static struct timing_generator_funcs dcn30_tg_funcs = { .enable_crtc_reset = optc1_enable_crtc_reset, .disable_reset_trigger = optc1_disable_reset_trigger, .lock = optc3_lock, - .is_locked = optc1_is_locked, .unlock = optc1_unlock, .lock_doublebuffer_enable = optc3_lock_doublebuffer_enable, .lock_doublebuffer_disable = optc3_lock_doublebuffer_disable, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index 2f7404a97479..d873def1a8f9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -260,7 +260,6 @@ static struct timing_generator_funcs dcn31_tg_funcs = { .enable_crtc_reset = optc1_enable_crtc_reset, .disable_reset_trigger = optc1_disable_reset_trigger, .lock = optc3_lock, - .is_locked = optc1_is_locked, .unlock = optc1_unlock, .lock_doublebuffer_enable = optc3_lock_doublebuffer_enable, .lock_doublebuffer_disable = optc3_lock_doublebuffer_disable, diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 4ff1392633a7..1fd7ad853210 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -439,7 +439,6 @@ struct pipe_ctx { union pipe_update_flags update_flags; struct dwbc *dwbc; struct mcif_wb *mcif_wb; - bool vtp_locked; }; /* Data used for dynamic link encoder assignment. diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h index 72eef7a5ed83..25a1df45b264 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h @@ -209,7 +209,6 @@ struct timing_generator_funcs { void (*set_blank)(struct timing_generator *tg, bool enable_blanking); bool (*is_blanked)(struct timing_generator *tg); - bool (*is_locked)(struct timing_generator *tg); void (*set_overscan_blank_color) (struct timing_generator *tg, const struct tg_color *color); void (*set_blank_color)(struct timing_generator *tg, const struct tg_color *color); void (*set_colors)(struct timing_generator *tg, -- cgit From f1b47f0004cfff051441aa93b7115d756d5eebb7 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 20 Sep 2022 15:34:55 -0400 Subject: drm/amd/display: Adding missing HDMI ACP SEND register Add HDMI ACP bit field definition for DCN32. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h index 250d9a341cf6..e80dd2b92503 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h @@ -106,6 +106,7 @@ SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_GC_CONT, mask_sh),\ SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_GC_SEND, mask_sh),\ SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_NULL_SEND, mask_sh),\ + SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_ACP_SEND, mask_sh),\ SE_SF(DIG0_HDMI_INFOFRAME_CONTROL0, HDMI_AUDIO_INFO_SEND, mask_sh),\ SE_SF(DIG0_HDMI_INFOFRAME_CONTROL1, HDMI_AUDIO_INFO_LINE, mask_sh),\ SE_SF(DIG0_HDMI_GC, HDMI_GC_AVMUTE, mask_sh),\ -- cgit From 3f4dee59253a6882acde98a2a027e55f1330ae86 Mon Sep 17 00:00:00 2001 From: Dillon Varone Date: Fri, 23 Sep 2022 14:00:09 -0400 Subject: drm/amd/display: Fix merging dynamic ODM+MPO configs on DCN32 [WHY&HOW?] When merging ODM pipes that are using MPO, we must copy the stream_res from the new top pipe to the bottom pipe so that the overlayed plane is not pointing to the wrong stream assets. Reviewed-by: Martin Leung Reviewed-by: Jun Lei Acked-by: Hamza Mahfooz Signed-off-by: Dillon Varone Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index a56ee04f7df9..f3f98e9a0ce6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1598,6 +1598,9 @@ bool dcn32_internal_validate_bw(struct dc *dc, /*MPC split rules will handle this case*/ pipe->bottom_pipe->top_pipe = NULL; } else { + /* when merging an ODM pipes, the bottom MPC pipe must now point to + * the previous ODM pipe and its associated stream assets + */ if (pipe->prev_odm_pipe->bottom_pipe) { /* 3 plane MPO*/ pipe->bottom_pipe->top_pipe = pipe->prev_odm_pipe->bottom_pipe; @@ -1607,6 +1610,8 @@ bool dcn32_internal_validate_bw(struct dc *dc, pipe->bottom_pipe->top_pipe = pipe->prev_odm_pipe; pipe->prev_odm_pipe->bottom_pipe = pipe->bottom_pipe; } + + memcpy(&pipe->bottom_pipe->stream_res, &pipe->bottom_pipe->top_pipe->stream_res, sizeof(struct stream_resource)); } } -- cgit From fe674c0b6f5382b7c377ca2c418c26dd78b428b4 Mon Sep 17 00:00:00 2001 From: Eric Bernstein Date: Tue, 25 Jan 2022 14:42:12 -0500 Subject: drm/amd/display: Fix disable DSC logic in the DIO code [Why] In DIO stream encoder, definition of DP_DSC_MODE is changed (only enable/disable) In OPTC, OTG_SET_V_TOTAL_MIN_MASK_EN is removed (same as DCN3.1) [How] In DIO stream encoder, update enc32_dp_set_dsc_config(). In OPTC, use DCN3.1 version for function interfaces .set_vrr_m_const and .set_drr Reviewed-by: Rodrigo Siqueira Signed-off-by: Eric Bernstein Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c index 40e713c4e172..d19fc93dbc75 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.c @@ -388,7 +388,7 @@ static void enc32_dp_set_dsc_config(struct stream_encoder *enc, { struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - REG_UPDATE(DP_DSC_CNTL, DP_DSC_MODE, dsc_mode); + REG_UPDATE(DP_DSC_CNTL, DP_DSC_MODE, dsc_mode == OPTC_DSC_DISABLED ? 0 : 1); } /* this function read dsc related register fields to be logged later in dcn10_log_hw_state -- cgit From f638fe27b817c755e017b8a6ae4b9b4224461941 Mon Sep 17 00:00:00 2001 From: George Shen Date: Thu, 2 Jun 2022 11:10:25 -0400 Subject: drm/amd/display: Add missing SDP registers to DCN32 reglist [Why] Certain features require the additional DP SDP configuration registers DP_SEC_CNTL1 and DP_SEC_CNTL5 in order to function correctly. The DCN32 DIO stream encoder reglist is currently missing these two registers. [How] Add the missing registers to the DCN32 DIO stream encoder reglist. Reviewed-by: Rodrigo Siqueira Signed-off-by: George Shen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h index e80dd2b92503..20e5f016a45a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h @@ -71,7 +71,9 @@ SRI(DP_MSE_RATE_UPDATE, DP, id), \ SRI(DP_PIXEL_FORMAT, DP, id), \ SRI(DP_SEC_CNTL, DP, id), \ + SRI(DP_SEC_CNTL1, DP, id), \ SRI(DP_SEC_CNTL2, DP, id), \ + SRI(DP_SEC_CNTL5, DP, id), \ SRI(DP_SEC_CNTL6, DP, id), \ SRI(DP_STEER_FIFO, DP, id), \ SRI(DP_VID_M, DP, id), \ -- cgit From 46c87432e3d4cea8e1a7ac6e9e3ebd2462f47617 Mon Sep 17 00:00:00 2001 From: Wenjing Liu Date: Thu, 23 Jun 2022 16:09:25 -0400 Subject: drm/amd/display: Add missing mask sh for SYM32_TP_SQ_PULSE register There is a missing register mask in dcn32 causing the hardware programming is not executed when programming SQ_num test pattern for DP2. Reviewed-by: Rodrigo Siqueira Signed-off-by: Wenjing Liu Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hpo_dp_link_encoder.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hpo_dp_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hpo_dp_link_encoder.h index 9db1323e1933..176b1537d2a1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hpo_dp_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hpo_dp_link_encoder.h @@ -47,6 +47,7 @@ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_TP_CONFIG, TP_PRBS_SEL1, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_TP_CONFIG, TP_PRBS_SEL2, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_TP_CONFIG, TP_PRBS_SEL3, mask_sh),\ + SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_TP_SQ_PULSE, TP_SQ_PULSE_WIDTH, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_SAT_VC0, SAT_STREAM_SOURCE, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_SAT_VC0, SAT_SLOT_COUNT, mask_sh),\ SE_SF(DP_DPHY_SYM320_DP_DPHY_SYM32_VC_RATE_CNTL0, STREAM_VC_RATE_X, mask_sh),\ -- cgit From e626d9b9c6e038a6918aad1b5affd38f6b9deaed Mon Sep 17 00:00:00 2001 From: Sonny Jiang Date: Fri, 30 Sep 2022 16:23:32 -0400 Subject: drm/amdgpu: Enable VCN PG on GC11_0_1 Enable VCN PG on GC11_0_1 Signed-off-by: Sonny Jiang Reviewed-by: James Zhu Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0.x --- drivers/gpu/drm/amd/amdgpu/soc21.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 16b757664a35..795706b3b092 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -629,6 +629,7 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_JPEG_MGCG; adev->pg_flags = AMD_PG_SUPPORT_GFX_PG | + AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; adev->external_rev_id = adev->rev_id + 0x1; -- cgit From 11895d32ffddb50152f0a1e671d36b7f60e4daba Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 20 Sep 2022 15:46:58 -0400 Subject: drm/amd/display: Add PState change high hook for DCN32 For some reason, we missed the PState check for DCN32 which may cause issues for clock transition. This commit add that required hook. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c index f6d3da475835..9fbb72369c10 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubbub.c @@ -936,6 +936,7 @@ static const struct hubbub_funcs hubbub32_funcs = { .program_watermarks = hubbub32_program_watermarks, .allow_self_refresh_control = hubbub1_allow_self_refresh_control, .is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled, + .verify_allow_pstate_change_high = hubbub1_verify_allow_pstate_change_high, .force_wm_propagate_to_pipes = hubbub32_force_wm_propagate_to_pipes, .force_pstate_change_control = hubbub3_force_pstate_change_control, .init_watermarks = hubbub32_init_watermarks, -- cgit From 54fae65ff469a79fc0ca46f480c4e7fce50f3963 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 20 Sep 2022 16:06:36 -0400 Subject: drm/amd/display: Enable 2 to 1 ODM policy if supported If the current configuration supports 2 to 1 ODM policy, let's also enable the windowed MPO feature. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0.x --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 8012a48859b5..218927d6ecb2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -991,6 +991,10 @@ void dcn32_init_hw(struct dc *dc) dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub); dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr; } + + /* Enable support for ODM and windowed MPO if policy flag is set */ + if (dc->debug.enable_single_display_2to1_odm_policy) + dc->config.enable_windowed_mpo_odm = true; } static int calc_mpc_flow_ctrl_cnt(const struct dc_stream_state *stream, -- cgit From 36939c94689ae7e6aaa9a0fa37e5c41616f76665 Mon Sep 17 00:00:00 2001 From: Aric Cyr Date: Mon, 26 Sep 2022 10:21:48 -0400 Subject: drm/amd/display: 3.2.206 This version brings along the following: - ILR improvements - PSR fixes - DCN315 fixes - DCN32 fixes - ODM fixes - DSC fixes - SubVP fixes Reviewed-by: Hamza Mahfooz Signed-off-by: Aric Cyr Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 458a4f431ac6..66b7482d2e72 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -47,7 +47,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.205" +#define DC_VER "3.2.206" #define MAX_SURFACES 3 #define MAX_PLANES 6 -- cgit From 9691a7a776302c85c10294f1a92c15c7f57a5947 Mon Sep 17 00:00:00 2001 From: Martin Leung Date: Mon, 23 May 2022 14:57:30 -0400 Subject: drm/amd/display: unblock mcm_luts why and how: needed to fix bad assumption for enable mcm_luts Reviewed-by: Rodrigo Siqueira Signed-off-by: Martin Leung Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 218927d6ecb2..33bdf56b2b3a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -630,10 +630,9 @@ bool dcn32_set_input_transfer_func(struct dc *dc, params = &dpp_base->degamma_params; } - result = dpp_base->funcs->dpp_program_gamcor_lut(dpp_base, params); + dpp_base->funcs->dpp_program_gamcor_lut(dpp_base, params); - if (result && - pipe_ctx->stream_res.opp && + if (pipe_ctx->stream_res.opp && pipe_ctx->stream_res.opp->ctx && hws->funcs.set_mcm_luts) result = hws->funcs.set_mcm_luts(pipe_ctx, plane_state); -- cgit From 07ebc18c047adcd72905619e72ae7c48db28ab48 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Thu, 22 Sep 2022 09:24:12 -0400 Subject: drm/amd/display: Disconnect DSC for unused pipes during ODM transition [Why] During transition from ODM combine to ODM bypass, if DSC is enabled need to disconnect the DSC mux for pipes no longer in use. [How] During ODM update, detect pipes with DSC that are no longer being used for new state and call new DSC interface to disconnect. Add new DSC interface to disconnect from pipe Reviewed-by: Alvin Lee Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 33bdf56b2b3a..955ca273cfe1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -1148,16 +1148,19 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx * true); } - // Don't program pixel clock after link is already enabled -/* if (false == pipe_ctx->clock_source->funcs->program_pix_clk( - pipe_ctx->clock_source, - &pipe_ctx->stream_res.pix_clk_params, - &pipe_ctx->pll_settings)) { - BREAK_TO_DEBUGGER(); - }*/ + if (pipe_ctx->stream_res.dsc) { + struct pipe_ctx *current_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx]; - if (pipe_ctx->stream_res.dsc) update_dsc_on_stream(pipe_ctx, pipe_ctx->stream->timing.flags.DSC); + + /* Check if no longer using pipe for ODM, then need to disconnect DSC for that pipe */ + if (!pipe_ctx->next_odm_pipe && current_pipe_ctx->next_odm_pipe && + current_pipe_ctx->next_odm_pipe->stream_res.dsc) { + struct display_stream_compressor *dsc = current_pipe_ctx->next_odm_pipe->stream_res.dsc; + /* disconnect DSC block from stream */ + dsc->funcs->dsc_disconnect(dsc); + } + } } unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div) -- cgit From a3daede47576037ff7bbbe9cbd36e52a71d92bc8 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Thu, 22 Sep 2022 10:06:48 -0400 Subject: drm/amd/display: update DSC for DCN32 Update DSC checks in the DCN32 VBA. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 75be1e1ce543..8316b1b914c6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -2252,9 +2252,8 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (k = 0; k <= mode_lib->vba.NumberOfActiveSurfaces - 1; k++) { if (!(mode_lib->vba.DSCInputBitPerComponent[k] == 12.0 || mode_lib->vba.DSCInputBitPerComponent[k] == 10.0 - || mode_lib->vba.DSCInputBitPerComponent[k] == 8.0 - || mode_lib->vba.DSCInputBitPerComponent[k] > - mode_lib->vba.MaximumDSCBitsPerComponent)) { + || mode_lib->vba.DSCInputBitPerComponent[k] == 8.0) + || mode_lib->vba.DSCInputBitPerComponent[k] > mode_lib->vba.MaximumDSCBitsPerComponent) { mode_lib->vba.NonsupportedDSCInputBPC = true; } } @@ -2330,16 +2329,15 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l if (mode_lib->vba.OutputMultistreamId[k] == k && mode_lib->vba.ForcedOutputLinkBPP[k] == 0) mode_lib->vba.BPPForMultistreamNotIndicated = true; for (j = 0; j < mode_lib->vba.NumberOfActiveSurfaces; ++j) { - if (mode_lib->vba.OutputMultistreamId[k] == j && mode_lib->vba.OutputMultistreamEn[k] + if (mode_lib->vba.OutputMultistreamId[k] == j && mode_lib->vba.ForcedOutputLinkBPP[k] == 0) mode_lib->vba.BPPForMultistreamNotIndicated = true; } } if ((mode_lib->vba.Output[k] == dm_edp || mode_lib->vba.Output[k] == dm_hdmi)) { - if (mode_lib->vba.OutputMultistreamId[k] == k && mode_lib->vba.OutputMultistreamEn[k]) + if (mode_lib->vba.OutputMultistreamEn[k] == true && mode_lib->vba.OutputMultistreamId[k] == k) mode_lib->vba.MultistreamWithHDMIOreDP = true; - for (j = 0; j < mode_lib->vba.NumberOfActiveSurfaces; ++j) { if (mode_lib->vba.OutputMultistreamEn[k] == true && mode_lib->vba.OutputMultistreamId[k] == j) mode_lib->vba.MultistreamWithHDMIOreDP = true; -- cgit From 7e6d5cf8e3e3f8050de52a28236d5a172caf2da9 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Thu, 22 Sep 2022 10:08:11 -0400 Subject: drm/amd/display: Minor code style change This commit adds some minor code style changes just to reduce the merge conflicts we have when we upstream some of the VBA code. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 8316b1b914c6..11d5750e15af 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -2476,8 +2476,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.PixelClock[k], mode_lib->vba.PixelClockBackEnd[k]); } - m = 0; - for (k = 0; k <= mode_lib->vba.NumberOfActiveSurfaces - 1; k++) { for (m = 0; m <= mode_lib->vba.NumberOfActiveSurfaces - 1; m++) { for (j = 0; j <= mode_lib->vba.NumberOfActiveSurfaces - 1; j++) { @@ -2854,8 +2852,6 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } } - m = 0; - //Calculate Return BW for (i = 0; i < (int) v->soc.num_states; ++i) { for (j = 0; j <= 1; ++j) { @@ -3616,11 +3612,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.ModeIsSupported = mode_lib->vba.ModeSupport[i][0] == true || mode_lib->vba.ModeSupport[i][1] == true; - if (mode_lib->vba.ModeSupport[i][0] == true) { + if (mode_lib->vba.ModeSupport[i][0] == true) MaximumMPCCombine = 0; - } else { + else MaximumMPCCombine = 1; - } } } -- cgit From 95c985ffc63e2a7d8f6aa18f9351f5010a8d1adb Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 30 Sep 2022 13:38:58 +0800 Subject: drm/amd/display: clean up one inconsistent indenting clean up one inconsistent indenting Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=2238 Reported-by: Abaci Robot Signed-off-by: Yang Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index 6658849d5b4e..61087f2385a9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -1654,7 +1654,7 @@ static bool dcn321_resource_construct( #undef REG_STRUCT #define REG_STRUCT dccg_regs - dccg_regs_init(); + dccg_regs_init(); ctx->dc_bios->regs = &bios_regs; -- cgit From 8c39634d28fa460869702b9801d2efe06671b342 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 30 Sep 2022 13:38:59 +0800 Subject: drm/amd/display: clean up one inconsistent indenting clean up one inconsistent indenting Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=2321 Reported-by: Abaci Robot Signed-off-by: Yang Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index 559e563d5bc1..f04595b750ab 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -852,7 +852,7 @@ static struct hubbub *dcn301_hubbub_create(struct dc_context *ctx) vmid->masks = &vmid_masks; } - hubbub3->num_vmid = res_cap_dcn301.num_vmid; + hubbub3->num_vmid = res_cap_dcn301.num_vmid; return &hubbub3->base; } -- cgit From 525530ad9a7ec9aa34266e1429cc5ef9acb58e6c Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 29 Sep 2022 22:20:15 +0800 Subject: drm/amdgpu/sdma: add missing release_firmware() in amdgpu_sdma_init_microcode() In some error path in amdgpu_sdma_init_microcode(), release_firmware() is not called, the memory allocated in request_firmware() will be leaked, calling amdgpu_sdma_destroy_inst_ctx() which calls release_firmware() to avoid memory leak. Fixes: 15aa13056d11da ("drm/amdgpu: add function to init SDMA microcode") Signed-off-by: Yang Yingliang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 3949b7e3907f..43cf8632cc1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -222,8 +222,10 @@ int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, adev->sdma.instance[instance].fw->data; version_major = le16_to_cpu(header->header_version_major); - if ((duplicate && instance) || (!duplicate && version_major > 1)) - return -EINVAL; + if ((duplicate && instance) || (!duplicate && version_major > 1)) { + err = -EINVAL; + goto out; + } err = amdgpu_sdma_init_inst_ctx(&adev->sdma.instance[instance]); if (err) @@ -272,7 +274,7 @@ int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, ALIGN(le32_to_cpu(sdma_hdr->ctl_ucode_size_bytes), PAGE_SIZE); break; default: - return -EINVAL; + err = -EINVAL; } } -- cgit From 21a550de5faf9f54013334c9a6a7643b8fd80b36 Mon Sep 17 00:00:00 2001 From: Ruili Ji Date: Mon, 3 Oct 2022 17:39:45 +0800 Subject: drm/amdgpu: Enable F32_WPTR_POLL_ENABLE in mqd This patch is to fix the SDMA user queue doorbell missing issue on SDMA 6.0. F32_WPTR_POLL_ENABLE has to be set if doorbell mode is used. Otherwise ringing SDMA user queue doorbell can't wake up system from gfxoff. Signed-off-by: Ruili Ji Reviewed-by: Yifan Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0.x --- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 3 ++- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index db51230163c5..0150f66a5ae6 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -846,7 +846,8 @@ static int sdma_v6_0_mqd_init(struct amdgpu_device *adev, void *mqd, m->sdmax_rlcx_rb_cntl = order_base_2(prop->queue_size / 4) << SDMA0_QUEUE0_RB_CNTL__RB_SIZE__SHIFT | 1 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT | - 4 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT; + 4 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT | + 1 << SDMA0_QUEUE0_RB_CNTL__F32_WPTR_POLL_ENABLE__SHIFT; m->sdmax_rlcx_rb_base = lower_32_bits(prop->hqd_base_gpu_addr >> 8); m->sdmax_rlcx_rb_base_hi = upper_32_bits(prop->hqd_base_gpu_addr >> 8); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c index 26b53b6d673e..4f6390f3236e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c @@ -333,7 +333,8 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd, << SDMA0_QUEUE0_RB_CNTL__RB_SIZE__SHIFT | q->vmid << SDMA0_QUEUE0_RB_CNTL__RB_VMID__SHIFT | 1 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT | - 6 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT; + 6 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT | + 1 << SDMA0_QUEUE0_RB_CNTL__F32_WPTR_POLL_ENABLE__SHIFT; m->sdmax_rlcx_rb_base = lower_32_bits(q->queue_address >> 8); m->sdmax_rlcx_rb_base_hi = upper_32_bits(q->queue_address >> 8); -- cgit From f6aa84b83aee629fbbbc4ea16c2c142caf920d5a Mon Sep 17 00:00:00 2001 From: Roman Li Date: Thu, 29 Sep 2022 14:37:00 -0400 Subject: drm/amd/display: Enable dpia support for dcn314 [Why] DCN 3.1.4 supports DPIA. [How] - Set dpia_supported flag for dcn314 in dmub_hw_init() - Remove comment that becomes irrelevant after this change. Signed-off-by: Roman Li Reviewed-by: Nicholas Kazlauskas Reviewed-by: Mario Limonciello Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0.x --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 4c73727e0b7d..d5222d5e3a61 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1110,7 +1110,8 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev) hw_params.fb[i] = &fb_info->fb[i]; switch (adev->ip_versions[DCE_HWIP][0]) { - case IP_VERSION(3, 1, 3): /* Only for this asic hw internal rev B0 */ + case IP_VERSION(3, 1, 3): + case IP_VERSION(3, 1, 4): hw_params.dpia_supported = true; hw_params.disable_dpia = adev->dm.dc->debug.dpia_debug.bits.disable_dpia; break; -- cgit From 8799c0be89ebb99a16098bdf618f49f817bef76a Mon Sep 17 00:00:00 2001 From: Yunxiang Li Date: Wed, 21 Sep 2022 17:20:19 -0400 Subject: drm/amd/display: Fix vblank refcount in vrr transition manage_dm_interrupts disable/enable vblank using drm_crtc_vblank_off/on which causes drm_crtc_vblank_get in vrr_transition to fail, and later when drm_crtc_vblank_put is called the refcount on vblank will be messed up. Therefore move the call to after manage_dm_interrupts. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1247 Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1380 Tested-by: Daniel Wheeler Reviewed-by: Rodrigo Siqueira Signed-off-by: Yunxiang Li Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 55 +++++++++++------------ 1 file changed, 26 insertions(+), 29 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index d5222d5e3a61..b84aedb707b8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7479,15 +7479,15 @@ static void amdgpu_dm_handle_vrr_transition(struct dm_crtc_state *old_state, * We also need vupdate irq for the actual core vblank handling * at end of vblank. */ - dm_set_vupdate_irq(new_state->base.crtc, true); - drm_crtc_vblank_get(new_state->base.crtc); + WARN_ON(dm_set_vupdate_irq(new_state->base.crtc, true) != 0); + WARN_ON(drm_crtc_vblank_get(new_state->base.crtc) != 0); DRM_DEBUG_DRIVER("%s: crtc=%u VRR off->on: Get vblank ref\n", __func__, new_state->base.crtc->base.id); } else if (old_vrr_active && !new_vrr_active) { /* Transition VRR active -> inactive: * Allow vblank irq disable again for fixed refresh rate. */ - dm_set_vupdate_irq(new_state->base.crtc, false); + WARN_ON(dm_set_vupdate_irq(new_state->base.crtc, false) != 0); drm_crtc_vblank_put(new_state->base.crtc); DRM_DEBUG_DRIVER("%s: crtc=%u VRR on->off: Drop vblank ref\n", __func__, new_state->base.crtc->base.id); @@ -8243,23 +8243,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) mutex_unlock(&dm->dc_lock); } - /* Count number of newly disabled CRTCs for dropping PM refs later. */ - for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, - new_crtc_state, i) { - if (old_crtc_state->active && !new_crtc_state->active) - crtc_disable_count++; - - dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); - dm_old_crtc_state = to_dm_crtc_state(old_crtc_state); - - /* For freesync config update on crtc state and params for irq */ - update_stream_irq_parameters(dm, dm_new_crtc_state); - - /* Handle vrr on->off / off->on transitions */ - amdgpu_dm_handle_vrr_transition(dm_old_crtc_state, - dm_new_crtc_state); - } - /** * Enable interrupts for CRTCs that are newly enabled or went through * a modeset. It was intentionally deferred until after the front end @@ -8269,16 +8252,29 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); #ifdef CONFIG_DEBUG_FS - bool configure_crc = false; enum amdgpu_dm_pipe_crc_source cur_crc_src; #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) - struct crc_rd_work *crc_rd_wrk = dm->crc_rd_wrk; + struct crc_rd_work *crc_rd_wrk; +#endif +#endif + /* Count number of newly disabled CRTCs for dropping PM refs later. */ + if (old_crtc_state->active && !new_crtc_state->active) + crtc_disable_count++; + + dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); + dm_old_crtc_state = to_dm_crtc_state(old_crtc_state); + + /* For freesync config update on crtc state and params for irq */ + update_stream_irq_parameters(dm, dm_new_crtc_state); + +#ifdef CONFIG_DEBUG_FS +#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) + crc_rd_wrk = dm->crc_rd_wrk; #endif spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); cur_crc_src = acrtc->dm_irq_params.crc_src; spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); #endif - dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); if (new_crtc_state->active && (!old_crtc_state->active || @@ -8286,16 +8282,19 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) dc_stream_retain(dm_new_crtc_state->stream); acrtc->dm_irq_params.stream = dm_new_crtc_state->stream; manage_dm_interrupts(adev, acrtc, true); + } + /* Handle vrr on->off / off->on transitions */ + amdgpu_dm_handle_vrr_transition(dm_old_crtc_state, dm_new_crtc_state); #ifdef CONFIG_DEBUG_FS + if (new_crtc_state->active && + (!old_crtc_state->active || + drm_atomic_crtc_needs_modeset(new_crtc_state))) { /** * Frontend may have changed so reapply the CRC capture * settings for the stream. */ - dm_new_crtc_state = to_dm_crtc_state(new_crtc_state); - if (amdgpu_dm_is_valid_crc_source(cur_crc_src)) { - configure_crc = true; #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) if (amdgpu_dm_crc_window_is_activated(crtc)) { spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags); @@ -8307,12 +8306,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags); } #endif - } - - if (configure_crc) if (amdgpu_dm_crtc_configure_crc_source( crtc, dm_new_crtc_state, cur_crc_src)) DRM_DEBUG_DRIVER("Failed to configure crc source"); + } #endif } } -- cgit From 7d30ccc7761cfcd6756aa0b760c5f5493038d30a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 30 Sep 2022 21:33:54 -0700 Subject: drm/amd/display: clean up dcn32_fpu.c kernel-doc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rectify multiple kernel-doc warnings in dcn32_fpu.c. E.g.: drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/dcn32_fpu.c:247: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Finds dummy_latency_index when MCLK switching using firmware based drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/dcn32_fpu.c:484: warning: Function parameter or member 'phantom_stream' not described in 'dcn32_set_phantom_stream_timing' drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/dcn32_fpu.c:601: warning: Function parameter or member 'dc' not described in 'dcn32_assign_subvp_pipe' drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/dcn32_fpu.c:601: warning: Function parameter or member 'context' not described in 'dcn32_assign_subvp_pipe' drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/dcn32_fpu.c:601: warning: Function parameter or member 'index' not described in 'dcn32_assign_subvp_pipe' drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/dcn32_fpu.c:2140: warning: Function parameter or member 'dc' not described in 'dcn32_update_bw_bounding_box_fpu' drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/dcn32_fpu.c:2140: warning: Function parameter or member 'bw_params' not described in 'dcn32_update_bw_bounding_box_fpu' drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn32/dcn32_fpu.c:2140: warning: expecting prototype for dcn32_update_bw_bounding_box(). Prototype was for dcn32_update_bw_bounding_box_fpu() instead Reviewed-by: Rodrigo Siqueira Reported-by: kernel test robot Signed-off-by: Randy Dunlap Signed-off-by: Rodrigo Siqueira Cc: George Shen Cc: Alvin Lee Cc: Nevenko Stupar Cc: Harry Wentland Cc: Leo Li Cc: Rodrigo Siqueira Cc: amd-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Cc: Alex Deucher Cc: Christian König Cc: "Pan, Xinhui" Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 116 +++++++++------------ 1 file changed, 49 insertions(+), 67 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index f3f98e9a0ce6..6bdd509d292a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -243,7 +243,7 @@ void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) clk_mgr->base.bw_params->wm_table.nv_entries[WM_D].pmfw_breakdown.max_uclk = 0xFFFF; } -/** +/* * Finds dummy_latency_index when MCLK switching using firmware based * vblank stretch is enabled. This function will iterate through the * table of dummy pstate latencies until the lowest value that allows @@ -290,15 +290,14 @@ int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc, /** * dcn32_helper_populate_phantom_dlg_params - Get DLG params for phantom pipes * and populate pipe_ctx with those params. - * - * This function must be called AFTER the phantom pipes are added to context - * and run through DML (so that the DLG params for the phantom pipes can be - * populated), and BEFORE we program the timing for the phantom pipes. - * * @dc: [in] current dc state * @context: [in] new dc state * @pipes: [in] DML pipe params array * @pipe_cnt: [in] DML pipe count + * + * This function must be called AFTER the phantom pipes are added to context + * and run through DML (so that the DLG params for the phantom pipes can be + * populated), and BEFORE we program the timing for the phantom pipes. */ void dcn32_helper_populate_phantom_dlg_params(struct dc *dc, struct dc_state *context, @@ -331,8 +330,9 @@ void dcn32_helper_populate_phantom_dlg_params(struct dc *dc, } /** - * ******************************************************************************************* - * dcn32_predict_pipe_split: Predict if pipe split will occur for a given DML pipe + * dcn32_predict_pipe_split - Predict if pipe split will occur for a given DML pipe + * @context: [in] New DC state to be programmed + * @pipe_e2e: [in] DML pipe end to end context * * This function takes in a DML pipe (pipe_e2e) and predicts if pipe split is required (both * ODM and MPC). For pipe split, ODM combine is determined by the ODM mode, and MPC combine is @@ -343,12 +343,7 @@ void dcn32_helper_populate_phantom_dlg_params(struct dc *dc, * - MPC combine is only chosen if there is no ODM combine requirements / policy in place, and * MPC is required * - * @param [in]: context: New DC state to be programmed - * @param [in]: pipe_e2e: DML pipe end to end context - * - * @return: Number of splits expected (1 for 2:1 split, 3 for 4:1 split, 0 for no splits). - * - * ******************************************************************************************* + * Return: Number of splits expected (1 for 2:1 split, 3 for 4:1 split, 0 for no splits). */ uint8_t dcn32_predict_pipe_split(struct dc_state *context, display_e2e_pipe_params_st *pipe_e2e) @@ -504,7 +499,14 @@ void insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table, } /** - * dcn32_set_phantom_stream_timing: Set timing params for the phantom stream + * dcn32_set_phantom_stream_timing - Set timing params for the phantom stream + * @dc: current dc state + * @context: new dc state + * @ref_pipe: Main pipe for the phantom stream + * @phantom_stream: target phantom stream state + * @pipes: DML pipe params + * @pipe_cnt: number of DML pipes + * @dc_pipe_idx: DC pipe index for the main pipe (i.e. ref_pipe) * * Set timing params of the phantom stream based on calculated output from DML. * This function first gets the DML pipe index using the DC pipe index, then @@ -517,13 +519,6 @@ void insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table, * that separately. * * - Set phantom backporch = vstartup of main pipe - * - * @dc: current dc state - * @context: new dc state - * @ref_pipe: Main pipe for the phantom stream - * @pipes: DML pipe params - * @pipe_cnt: number of DML pipes - * @dc_pipe_idx: DC pipe index for the main pipe (i.e. ref_pipe) */ void dcn32_set_phantom_stream_timing(struct dc *dc, struct dc_state *context, @@ -592,16 +587,14 @@ void dcn32_set_phantom_stream_timing(struct dc *dc, } /** - * dcn32_get_num_free_pipes: Calculate number of free pipes + * dcn32_get_num_free_pipes - Calculate number of free pipes + * @dc: current dc state + * @context: new dc state * * This function assumes that a "used" pipe is a pipe that has * both a stream and a plane assigned to it. * - * @dc: current dc state - * @context: new dc state - * - * Return: - * Number of free pipes available in the context + * Return: Number of free pipes available in the context */ static unsigned int dcn32_get_num_free_pipes(struct dc *dc, struct dc_state *context) { @@ -625,7 +618,10 @@ static unsigned int dcn32_get_num_free_pipes(struct dc *dc, struct dc_state *con } /** - * dcn32_assign_subvp_pipe: Function to decide which pipe will use Sub-VP. + * dcn32_assign_subvp_pipe - Function to decide which pipe will use Sub-VP. + * @dc: current dc state + * @context: new dc state + * @index: [out] dc pipe index for the pipe chosen to have phantom pipes assigned * * We enter this function if we are Sub-VP capable (i.e. enough pipes available) * and regular P-State switching (i.e. VACTIVE/VBLANK) is not supported, or if @@ -639,12 +635,7 @@ static unsigned int dcn32_get_num_free_pipes(struct dc *dc, struct dc_state *con * for determining which should be the SubVP pipe (need a way to determine if a pipe / plane doesn't * support MCLK switching naturally [i.e. ACTIVE or VBLANK]). * - * @param dc: current dc state - * @param context: new dc state - * @param index: [out] dc pipe index for the pipe chosen to have phantom pipes assigned - * - * Return: - * True if a valid pipe assignment was found for Sub-VP. Otherwise false. + * Return: True if a valid pipe assignment was found for Sub-VP. Otherwise false. */ static bool dcn32_assign_subvp_pipe(struct dc *dc, struct dc_state *context, @@ -711,7 +702,9 @@ static bool dcn32_assign_subvp_pipe(struct dc *dc, } /** - * dcn32_enough_pipes_for_subvp: Function to check if there are "enough" pipes for SubVP. + * dcn32_enough_pipes_for_subvp - Function to check if there are "enough" pipes for SubVP. + * @dc: current dc state + * @context: new dc state * * This function returns true if there are enough free pipes * to create the required phantom pipes for any given stream @@ -723,9 +716,6 @@ static bool dcn32_assign_subvp_pipe(struct dc *dc, * pipe which can be used as the phantom pipe for the non pipe * split pipe. * - * @dc: current dc state - * @context: new dc state - * * Return: * True if there are enough free pipes to assign phantom pipes to at least one * stream that does not already have phantom pipes assigned. Otherwise false. @@ -764,7 +754,9 @@ static bool dcn32_enough_pipes_for_subvp(struct dc *dc, struct dc_state *context } /** - * subvp_subvp_schedulable: Determine if SubVP + SubVP config is schedulable + * subvp_subvp_schedulable - Determine if SubVP + SubVP config is schedulable + * @dc: current dc state + * @context: new dc state * * High level algorithm: * 1. Find longest microschedule length (in us) between the two SubVP pipes @@ -772,11 +764,7 @@ static bool dcn32_enough_pipes_for_subvp(struct dc *dc, struct dc_state *context * pipes still allows for the maximum microschedule to fit in the active * region for both pipes. * - * @dc: current dc state - * @context: new dc state - * - * Return: - * bool - True if the SubVP + SubVP config is schedulable, false otherwise + * Return: True if the SubVP + SubVP config is schedulable, false otherwise */ static bool subvp_subvp_schedulable(struct dc *dc, struct dc_state *context) { @@ -836,7 +824,10 @@ static bool subvp_subvp_schedulable(struct dc *dc, struct dc_state *context) } /** - * subvp_drr_schedulable: Determine if SubVP + DRR config is schedulable + * subvp_drr_schedulable - Determine if SubVP + DRR config is schedulable + * @dc: current dc state + * @context: new dc state + * @drr_pipe: DRR pipe_ctx for the SubVP + DRR config * * High level algorithm: * 1. Get timing for SubVP pipe, phantom pipe, and DRR pipe @@ -845,12 +836,7 @@ static bool subvp_subvp_schedulable(struct dc *dc, struct dc_state *context) * 3.If (SubVP Active - Prefetch > Stretched DRR frame + max(MALL region, Stretched DRR frame)) * then report the configuration as supported * - * @dc: current dc state - * @context: new dc state - * @drr_pipe: DRR pipe_ctx for the SubVP + DRR config - * - * Return: - * bool - True if the SubVP + DRR config is schedulable, false otherwise + * Return: True if the SubVP + DRR config is schedulable, false otherwise */ static bool subvp_drr_schedulable(struct dc *dc, struct dc_state *context, struct pipe_ctx *drr_pipe) { @@ -914,7 +900,9 @@ static bool subvp_drr_schedulable(struct dc *dc, struct dc_state *context, struc /** - * subvp_vblank_schedulable: Determine if SubVP + VBLANK config is schedulable + * subvp_vblank_schedulable - Determine if SubVP + VBLANK config is schedulable + * @dc: current dc state + * @context: new dc state * * High level algorithm: * 1. Get timing for SubVP pipe, phantom pipe, and VBLANK pipe @@ -922,11 +910,7 @@ static bool subvp_drr_schedulable(struct dc *dc, struct dc_state *context, struc * then report the configuration as supported * 3. If the VBLANK display is DRR, then take the DRR static schedulability path * - * @dc: current dc state - * @context: new dc state - * - * Return: - * bool - True if the SubVP + VBLANK/DRR config is schedulable, false otherwise + * Return: True if the SubVP + VBLANK/DRR config is schedulable, false otherwise */ static bool subvp_vblank_schedulable(struct dc *dc, struct dc_state *context) { @@ -1003,20 +987,18 @@ static bool subvp_vblank_schedulable(struct dc *dc, struct dc_state *context) } /** - * subvp_validate_static_schedulability: Check which SubVP case is calculated and handle - * static analysis based on the case. + * subvp_validate_static_schedulability - Check which SubVP case is calculated + * and handle static analysis based on the case. + * @dc: current dc state + * @context: new dc state + * @vlevel: Voltage level calculated by DML * * Three cases: * 1. SubVP + SubVP * 2. SubVP + VBLANK (DRR checked internally) * 3. SubVP + VACTIVE (currently unsupported) * - * @dc: current dc state - * @context: new dc state - * @vlevel: Voltage level calculated by DML - * - * Return: - * bool - True if statically schedulable, false otherwise + * Return: True if statically schedulable, false otherwise */ static bool subvp_validate_static_schedulability(struct dc *dc, struct dc_state *context, @@ -2281,7 +2263,7 @@ static int build_synthetic_soc_states(struct clk_bw_params *bw_params, return 0; } -/** +/* * dcn32_update_bw_bounding_box * * This would override some dcn3_2 ip_or_soc initial parameters hardcoded from -- cgit From 5e69732d4a89928b7daaa651ad869cebee28bfff Mon Sep 17 00:00:00 2001 From: Dong Chenchen Date: Fri, 30 Sep 2022 14:38:27 +0800 Subject: drm/amd/display: Removed unused variable 'sdp_stream_enable' Kernel test robot throws below warning -> drivers/gpu/drm/amd/amdgpu/../display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c: In function 'dcn31_hpo_dp_stream_enc_update_dp_info_packets': drivers/gpu/drm/amd/amdgpu/../display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c:439:14: warning: variable 'sdp_stream_enable' set but not used [-Wunused-but-set-variable] 439 | bool sdp_stream_enable = false; Removed unused variable 'sdp_stream_enable'. Reviewed-by: Rodrigo Siqueira Reported-by: kernel test robot Signed-off-by: Dong Chenchen Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- .../amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c index d71d89268a07..814f401db3b3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hpo_dp_stream_encoder.c @@ -436,32 +436,28 @@ static void dcn31_hpo_dp_stream_enc_update_dp_info_packets( { struct dcn31_hpo_dp_stream_encoder *enc3 = DCN3_1_HPO_DP_STREAM_ENC_FROM_HPO_STREAM_ENC(enc); uint32_t dmdata_packet_enabled = 0; - bool sdp_stream_enable = false; - if (info_frame->vsc.valid) { + if (info_frame->vsc.valid) enc->vpg->funcs->update_generic_info_packet( enc->vpg, 0, /* packetIndex */ &info_frame->vsc, true); - sdp_stream_enable = true; - } - if (info_frame->spd.valid) { + + if (info_frame->spd.valid) enc->vpg->funcs->update_generic_info_packet( enc->vpg, 2, /* packetIndex */ &info_frame->spd, true); - sdp_stream_enable = true; - } - if (info_frame->hdrsmd.valid) { + + if (info_frame->hdrsmd.valid) enc->vpg->funcs->update_generic_info_packet( enc->vpg, 3, /* packetIndex */ &info_frame->hdrsmd, true); - sdp_stream_enable = true; - } + /* enable/disable transmission of packet(s). * If enabled, packet transmission begins on the next frame */ -- cgit From 7e4ab9fb2b9449ef01977e79157d06c8900f73fd Mon Sep 17 00:00:00 2001 From: Yuan Can Date: Tue, 27 Sep 2022 13:39:08 +0000 Subject: drm/amd/display: Remove unused struct i2c_id_config_access After commit 5a8132b9f606 ("drm/amd/display: remove dead dc vbios code"), no one use struct i2c_id_config_access, so remove it. Reviewed-by: Rodrigo Siqueira Signed-off-by: Yuan Can Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 53b077b40d72..ee0456b5e14e 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -51,13 +51,6 @@ #define LAST_RECORD_TYPE 0xff #define SMU9_SYSPLL0_ID 0 -struct i2c_id_config_access { - uint8_t bfI2C_LineMux:4; - uint8_t bfHW_EngineID:3; - uint8_t bfHW_Capable:1; - uint8_t ucAccess; -}; - static enum bp_result get_gpio_i2c_info(struct bios_parser *bp, struct atom_i2c_record *record, struct graphics_object_i2c_info *info); -- cgit From 312b4dc11d4f74bfe03ea25ffe04c1f2fdd13cb9 Mon Sep 17 00:00:00 2001 From: Arunpravin Paneer Selvam Date: Tue, 4 Oct 2022 07:33:39 -0700 Subject: drm/amdgpu: Fix VRAM BO swap issue MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DRM buddy manager allocates the contiguous memory requests in a single block or multiple blocks. So for the ttm move operation (incase of low vram memory) we should consider all the blocks to compute the total memory size which compared with the struct ttm_resource num_pages in order to verify that the blocks are contiguous for the eviction process. v2: Added a Fixes tag v3: Rewrite the code to save a bit of calculations and variables (Christian) Fixes: c9cad937c0c5 ("drm/amdgpu: add drm buddy support to amdgpu") Signed-off-by: Arunpravin Paneer Selvam Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index b1c455329023..dc262d2c2925 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -424,8 +424,9 @@ error: static bool amdgpu_mem_visible(struct amdgpu_device *adev, struct ttm_resource *mem) { - uint64_t mem_size = (u64)mem->num_pages << PAGE_SHIFT; + u64 mem_size = (u64)mem->num_pages << PAGE_SHIFT; struct amdgpu_res_cursor cursor; + u64 end; if (mem->mem_type == TTM_PL_SYSTEM || mem->mem_type == TTM_PL_TT) @@ -434,12 +435,18 @@ static bool amdgpu_mem_visible(struct amdgpu_device *adev, return false; amdgpu_res_first(mem, 0, mem_size, &cursor); + end = cursor.start + cursor.size; + while (cursor.remaining) { + amdgpu_res_next(&cursor, cursor.size); - /* ttm_resource_ioremap only supports contiguous memory */ - if (cursor.size != mem_size) - return false; + /* ttm_resource_ioremap only supports contiguous memory */ + if (end != cursor.start) + return false; + + end = cursor.start + cursor.size; + } - return cursor.start + cursor.size <= adev->gmc.visible_vram_size; + return end <= adev->gmc.visible_vram_size; } /* -- cgit From 9a3c6067bd2ee2ca2652fbb0679f422f3c9109f9 Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Mon, 3 Oct 2022 13:03:26 -0400 Subject: drm/amdgpu: Set vmbo destroy after pt bo is created MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Under VRAM usage pression, map to GPU may fail to create pt bo and vmbo->shadow_list is not initialized, then ttm_bo_release calling amdgpu_bo_vm_destroy to access vmbo->shadow_list generates below dmesg and NULL pointer access backtrace: Set vmbo destroy callback to amdgpu_bo_vm_destroy only after creating pt bo successfully, otherwise use default callback amdgpu_bo_destroy. amdgpu: amdgpu_vm_bo_update failed amdgpu: update_gpuvm_pte() failed amdgpu: Failed to map bo to gpuvm amdgpu 0000:43:00.0: amdgpu: Failed to map peer:0000:43:00.0 mem_domain:2 BUG: kernel NULL pointer dereference, address: RIP: 0010:amdgpu_bo_vm_destroy+0x4d/0x80 [amdgpu] Call Trace: ttm_bo_release+0x207/0x320 [amdttm] amdttm_bo_init_reserved+0x1d6/0x210 [amdttm] amdgpu_bo_create+0x1ba/0x520 [amdgpu] amdgpu_bo_create_vm+0x3a/0x80 [amdgpu] amdgpu_vm_pt_create+0xde/0x270 [amdgpu] amdgpu_vm_ptes_update+0x63b/0x710 [amdgpu] amdgpu_vm_update_range+0x2e7/0x6e0 [amdgpu] amdgpu_vm_bo_update+0x2bd/0x600 [amdgpu] update_gpuvm_pte+0x160/0x420 [amdgpu] amdgpu_amdkfd_gpuvm_map_memory_to_gpu+0x313/0x1130 [amdgpu] kfd_ioctl_map_memory_to_gpu+0x115/0x390 [amdgpu] kfd_ioctl+0x24a/0x5b0 [amdgpu] Signed-off-by: Philip Yang Reviewed-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e6a9b9fc9e0b..2e8f6cd7a729 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -688,13 +688,16 @@ int amdgpu_bo_create_vm(struct amdgpu_device *adev, * num of amdgpu_vm_pt entries. */ BUG_ON(bp->bo_ptr_size < sizeof(struct amdgpu_bo_vm)); - bp->destroy = &amdgpu_bo_vm_destroy; r = amdgpu_bo_create(adev, bp, &bo_ptr); if (r) return r; *vmbo_ptr = to_amdgpu_bo_vm(bo_ptr); INIT_LIST_HEAD(&(*vmbo_ptr)->shadow_list); + /* Set destroy callback to amdgpu_bo_vm_destroy after vmbo->shadow_list + * is initialized. + */ + bo_ptr->tbo.destroy = &amdgpu_bo_vm_destroy; return r; } -- cgit From 2302d507149f0ae7cc697089ab5675a2d4cf9d2a Mon Sep 17 00:00:00 2001 From: Philip Yang Date: Mon, 3 Oct 2022 17:53:25 -0400 Subject: drm/amdgpu: Correct amdgpu_amdkfd_total_mem_size calculation amdkfd_total_mem_size is the size of total GPUs vram plus system memory to estimate page tables memory usage and leave enough VRAM room for page tables allocation. Calculate amdkfd_total_mem_size in amdgpu_amdkfd_device_probe is incorrect because adev->gmc.real_vram_size is still 0 called from amdgpu_device_ip_early_init. Move the calculation to amdgpu_amdkfd_device_init to get the correct VRAM size. Do reverse calculation in amdgpu_amdkfd_device_fini_sw to support hot-unplugging GPUs. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 9e98f3866edc..03bbfaa51cbc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -75,9 +75,6 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev) return; adev->kfd.dev = kgd2kfd_probe(adev, vf); - - if (adev->kfd.dev) - amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size; } /** @@ -201,6 +198,8 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev) adev->kfd.init_complete = kgd2kfd_device_init(adev->kfd.dev, adev_to_drm(adev), &gpu_resources); + amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size; + INIT_WORK(&adev->kfd.reset_work, amdgpu_amdkfd_reset_work); } } @@ -210,6 +209,7 @@ void amdgpu_amdkfd_device_fini_sw(struct amdgpu_device *adev) if (adev->kfd.dev) { kgd2kfd_device_exit(adev->kfd.dev); adev->kfd.dev = NULL; + amdgpu_amdkfd_total_mem_size -= adev->gmc.real_vram_size; } } -- cgit From 17d819e2828cacca2e4c909044eb9798ed379cd2 Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Wed, 5 Oct 2022 11:30:38 -0400 Subject: Revert "drm/amdgpu: use dirty framebuffer helper" This reverts commit 66f99628eb24409cb8feb5061f78283c8b65f820. Unfortunately, that commit causes performance regressions on non-PSR setups. So, just revert it until FB_DAMAGE_CLIPS support can be added. Cc: stable@vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2189 Link: https://bugzilla.kernel.org/show_bug.cgi?id=216554 Fixes: 66f99628eb2440 ("drm/amdgpu: use dirty framebuffer helper") Fixes: abbc7a3dafb91b ("drm/amdgpu: don't register a dirty callback for non-atomic") Signed-off-by: Hamza Mahfooz Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 23998f727c7f..1a06b8d724f3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -38,8 +38,6 @@ #include #include #include -#include -#include #include #include #include @@ -500,12 +498,6 @@ static const struct drm_framebuffer_funcs amdgpu_fb_funcs = { .create_handle = drm_gem_fb_create_handle, }; -static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = { - .destroy = drm_gem_fb_destroy, - .create_handle = drm_gem_fb_create_handle, - .dirty = drm_atomic_helper_dirtyfb, -}; - uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, uint64_t bo_flags) { @@ -1108,10 +1100,8 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev, if (ret) goto err; - if (drm_drv_uses_atomic_modeset(dev)) - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs_atomic); - else - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + if (ret) goto err; -- cgit From f0c00454bf78975925eccc9737faaa4d4951edbf Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 28 Sep 2022 12:07:55 +0100 Subject: mmc: renesas_sdhi: Fix rounding errors Due to clk rounding errors on RZ/G2L platforms, it selects a clock source with a lower clock rate compared to a higher one. For eg: The rounding error (533333333 Hz / 4 * 4 = 533333332 Hz < 5333333 33 Hz) selects a clk source of 400 MHz instead of 533.333333 MHz. This patch fixes this issue by adding a margin of (1/1024) higher to the clock rate. Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Reviewed-by: Wolfram Sang Tested-by: Wolfram Sang Fixes: bb6d3fa98a41 ("clk: renesas: rcar-gen3: Switch to new SD clock handling") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220928110755.849275-1-biju.das.jz@bp.renesas.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/renesas_sdhi_core.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 6edbf5c161ab..b970699743e0 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -128,6 +128,7 @@ static unsigned int renesas_sdhi_clk_update(struct tmio_mmc_host *host, struct clk *ref_clk = priv->clk; unsigned int freq, diff, best_freq = 0, diff_min = ~0; unsigned int new_clock, clkh_shift = 0; + unsigned int new_upper_limit; int i; /* @@ -153,13 +154,20 @@ static unsigned int renesas_sdhi_clk_update(struct tmio_mmc_host *host, * greater than, new_clock. As we can divide by 1 << i for * any i in [0, 9] we want the input clock to be as close as * possible, but no greater than, new_clock << i. + * + * Add an upper limit of 1/1024 rate higher to the clock rate to fix + * clk rate jumping to lower rate due to rounding error (eg: RZ/G2L has + * 3 clk sources 533.333333 MHz, 400 MHz and 266.666666 MHz. The request + * for 533.333333 MHz will selects a slower 400 MHz due to rounding + * error (533333333 Hz / 4 * 4 = 533333332 Hz < 533333333 Hz)). */ for (i = min(9, ilog2(UINT_MAX / new_clock)); i >= 0; i--) { freq = clk_round_rate(ref_clk, new_clock << i); - if (freq > (new_clock << i)) { + new_upper_limit = (new_clock << i) + ((new_clock << i) >> 10); + if (freq > new_upper_limit) { /* Too fast; look for a slightly slower option */ freq = clk_round_rate(ref_clk, (new_clock << i) / 4 * 3); - if (freq > (new_clock << i)) + if (freq > new_upper_limit) continue; } @@ -181,6 +189,7 @@ static unsigned int renesas_sdhi_clk_update(struct tmio_mmc_host *host, static void renesas_sdhi_set_clock(struct tmio_mmc_host *host, unsigned int new_clock) { + unsigned int clk_margin; u32 clk = 0, clock; sd_ctrl_write16(host, CTL_SD_CARD_CLK_CTL, ~CLK_CTL_SCLKEN & @@ -194,7 +203,13 @@ static void renesas_sdhi_set_clock(struct tmio_mmc_host *host, host->mmc->actual_clock = renesas_sdhi_clk_update(host, new_clock); clock = host->mmc->actual_clock / 512; - for (clk = 0x80000080; new_clock >= (clock << 1); clk >>= 1) + /* + * Add a margin of 1/1024 rate higher to the clock rate in order + * to avoid clk variable setting a value of 0 due to the margin + * provided for actual_clock in renesas_sdhi_clk_update(). + */ + clk_margin = new_clock >> 10; + for (clk = 0x80000080; new_clock + clk_margin >= (clock << 1); clk >>= 1) clock <<= 1; /* 1/1 clock is option */ -- cgit From b78870e7f41534cc719c295d1f8809aca93aeeab Mon Sep 17 00:00:00 2001 From: Prathamesh Shete Date: Thu, 6 Oct 2022 18:36:22 +0530 Subject: mmc: sdhci-tegra: Use actual clock rate for SW tuning correction Ensure tegra_host member "curr_clk_rate" holds the actual clock rate instead of requested clock rate for proper use during tuning correction algorithm. Actual clk rate may not be the same as the requested clk frequency depending on the parent clock source set. Tuning correction algorithm depends on certain parameters which are sensitive to current clk rate. If the host clk is selected instead of the actual clock rate, tuning correction algorithm may end up applying invalid correction, which could result in errors Fixes: ea8fc5953e8b ("mmc: tegra: update hw tuning process") Signed-off-by: Aniruddha TVS Rao Signed-off-by: Prathamesh Shete Acked-by: Adrian Hunter Acked-by: Thierry Reding Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221006130622.22900-4-pshete@nvidia.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-tegra.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 2d2d8260c681..413925bce0ca 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -773,7 +773,7 @@ static void tegra_sdhci_set_clock(struct sdhci_host *host, unsigned int clock) dev_err(dev, "failed to set clk rate to %luHz: %d\n", host_clk, err); - tegra_host->curr_clk_rate = host_clk; + tegra_host->curr_clk_rate = clk_get_rate(pltfm_host->clk); if (tegra_host->ddr_signaling) host->max_clk = host_clk; else -- cgit From c210b91818e81068ca2573c20684644b8e110a07 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 20 Sep 2022 10:37:35 +0100 Subject: riscv: dts: microchip: fix fabric i2c reg size The size of the reg should've been changed when the address was changed, but obviously I forgot to do so. Fixes: ab291621a8b8 ("riscv: dts: microchip: icicle: re-jig fabric peripheral addresses") Signed-off-by: Conor Dooley --- arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index b6bfe177ccb2..24b1cfb9a73e 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -16,7 +16,7 @@ i2c2: i2c@40000200 { compatible = "microchip,corei2c-rtl-v7"; - reg = <0x0 0x40000200 0x0 0x1000>; + reg = <0x0 0x40000200 0x0 0x100>; #address-cells = <1>; #size-cells = <0>; clocks = <&fabric_clk3>; -- cgit From e1567b4f0eec779af99b372773ddeb5be9b6208b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 5 Oct 2022 19:16:42 +0100 Subject: arm64/sysreg: Fix typo in SCTR_EL1.SPINTMASK SPINTMASK was typoed as SPINMASK, fix it. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20221005181642.711734-1-broonie@kernel.org Signed-off-by: Catalin Marinas --- arch/arm64/tools/sysreg | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 7f1fb36f208c..384757a7eda9 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -732,7 +732,7 @@ EndSysreg Sysreg SCTLR_EL1 3 0 1 0 0 Field 63 TIDCP -Field 62 SPINMASK +Field 62 SPINTMASK Field 61 NMI Field 60 EnTP2 Res0 59:58 -- cgit From 171df58028bf4649460fb146a56a58dcb0c8f75a Mon Sep 17 00:00:00 2001 From: James Morse Date: Fri, 30 Sep 2022 14:19:59 +0100 Subject: arm64: errata: Add Cortex-A55 to the repeat tlbi list Cortex-A55 is affected by an erratum where in rare circumstances the CPUs may not handle a race between a break-before-make sequence on one CPU, and another CPU accessing the same page. This could allow a store to a page that has been unmapped. Work around this by adding the affected CPUs to the list that needs TLB sequences to be done twice. Signed-off-by: James Morse Cc: Link: https://lore.kernel.org/r/20220930131959.3082594-1-james.morse@arm.com Signed-off-by: Catalin Marinas --- Documentation/arm64/silicon-errata.rst | 2 ++ arch/arm64/Kconfig | 17 +++++++++++++++++ arch/arm64/kernel/cpu_errata.c | 5 +++++ 3 files changed, 24 insertions(+) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 17d9fc5d14fb..808ade4cc008 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -76,6 +76,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A55 | #1530923 | ARM64_ERRATUM_1530923 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A55 | #2441007 | ARM64_ERRATUM_2441007 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #852523 | N/A | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1675310f1791..20d082d54bd8 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -634,6 +634,23 @@ config ARM64_ERRATUM_1530923 config ARM64_WORKAROUND_REPEAT_TLBI bool +config ARM64_ERRATUM_2441007 + bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI" + default y + select ARM64_WORKAROUND_REPEAT_TLBI + help + This option adds a workaround for ARM Cortex-A55 erratum #2441007. + + Under very rare circumstances, affected Cortex-A55 CPUs + may not handle a race between a break-before-make sequence on one + CPU, and another CPU accessing the same page. This could allow a + store to a page that has been unmapped. + + Work around this by adding the affected CPUs to the list that needs + TLB sequences to be done twice. + + If unsure, say Y. + config ARM64_ERRATUM_1286807 bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation" default y diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 58ca4f6b25d6..89ac00084f38 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -230,6 +230,11 @@ static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2441007 + { + ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2441009 { /* Cortex-A510 r0p0 -> r1p1. Fixed in r1p2 */ -- cgit From ad0112f2d54cafee839e2ee99ec0b5fb9ce5c4b8 Mon Sep 17 00:00:00 2001 From: Sun Ke Date: Sat, 24 Sep 2022 11:21:27 +0800 Subject: drivers/perf: fix return value check in ali_drw_pmu_probe() In case of error, devm_ioremap_resource() returns ERR_PTR(), and never returns NULL. The NULL test in the return value check should be replaced with IS_ERR(). Fixes: cf7b61073e45 ("drivers/perf: add DDR Sub-System Driveway PMU driver for Yitian 710 SoC") Signed-off-by: Sun Ke Acked-by: Will Deacon Reviewed-by: Shuai Xue Link: https://lore.kernel.org/r/20220924032127.313156-1-sunke32@huawei.com Signed-off-by: Catalin Marinas --- drivers/perf/alibaba_uncore_drw_pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c index 82729b874f09..a7689fecb49d 100644 --- a/drivers/perf/alibaba_uncore_drw_pmu.c +++ b/drivers/perf/alibaba_uncore_drw_pmu.c @@ -658,8 +658,8 @@ static int ali_drw_pmu_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); drw_pmu->cfg_base = devm_ioremap_resource(&pdev->dev, res); - if (!drw_pmu->cfg_base) - return -ENOMEM; + if (IS_ERR(drw_pmu->cfg_base)) + return PTR_ERR(drw_pmu->cfg_base); name = devm_kasprintf(drw_pmu->dev, GFP_KERNEL, "ali_drw_%llx", (u64) (res->start >> ALI_DRW_PMU_PA_SHIFT)); -- cgit From e08d07dd9f80e997ad36a088eb276509ca484e97 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 27 Sep 2022 15:37:16 +0200 Subject: drivers/perf: ALIBABA_UNCORE_DRW_PMU should depend on ACPI The Alibaba T-Head Yitian 710 DDR Sub-system Driveway PMU driver relies solely on ACPI for matching. Hence add a dependency on ACPI, to prevent asking the user about this driver when configuring a kernel without ACPI support. Fixes: cf7b61073e45 ("drivers/perf: add DDR Sub-System Driveway PMU driver for Yitian 710 SoC") Signed-off-by: Geert Uytterhoeven Acked-by: Will Deacon Link: https://lore.kernel.org/r/2a4407bb598285660fa5e604e56823ddb12bb0aa.1664285774.git.geert+renesas@glider.be Signed-off-by: Catalin Marinas --- drivers/perf/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index 44c07ea487f4..341010f20b77 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -185,7 +185,7 @@ config APPLE_M1_CPU_PMU config ALIBABA_UNCORE_DRW_PMU tristate "Alibaba T-Head Yitian 710 DDR Sub-system Driveway PMU driver" - depends on ARM64 || COMPILE_TEST + depends on (ARM64 && ACPI) || COMPILE_TEST help Support for Driveway PMU events monitoring on Yitian 710 DDR Sub-system. -- cgit From 5f4853e810943af5e45fcc040cbbcbba07d8fc25 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 29 Sep 2022 14:29:37 +0200 Subject: MAINTAINERS: rectify file entry in ALIBABA PMU DRIVER Commit cf7b61073e45 ("drivers/perf: add DDR Sub-System Driveway PMU driver for Yitian 710 SoC") adds the DDR Sub-System Driveway PMU driver here: drivers/perf/alibaba_uncore_drw_pmu.c The file entry in MAINTAINERS for the ALIBABA PMU DRIVER, introduced with commit d813a19e7d2e ("MAINTAINERS: add maintainers for Alibaba' T-Head PMU driver"), however refers to: drivers/perf/alibaba_uncore_dwr_pmu.c Note the swapping of characters. Hence, ./scripts/get_maintainer.pl --self-test=patterns complains about a broken file pattern. Repair this file entry in ALIBABA PMU DRIVER. Signed-off-by: Lukas Bulwahn Acked-by: Will Deacon Link: https://lore.kernel.org/r/20220929122937.20132-1-lukas.bulwahn@gmail.com Signed-off-by: Catalin Marinas --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 58d0aefead54..a8e0f73747cf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -753,7 +753,7 @@ ALIBABA PMU DRIVER M: Shuai Xue S: Supported F: Documentation/admin-guide/perf/alibaba_pmu.rst -F: drivers/perf/alibaba_uncore_dwr_pmu.c +F: drivers/perf/alibaba_uncore_drw_pmu.c ALIENWARE WMI DRIVER L: Dell.Client.Kernel@dell.com -- cgit From 96dbcc0072acf4f9565a16e8da96e57e5cee1068 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 3 Oct 2022 15:57:30 +0100 Subject: btrfs: add missing path cache update during fiemap When looking the stored result for a cached path node, if the stored result is valid and has a value of true, we must update all the nodes for all levels below it with a result of true as well. This is necessary when moving from one leaf in the fs tree to the next one, as well as when moving from a node at any level to the next node at the same level. Currently this logic is missing as it was somehow forgotten by a recent patch with the subject: "btrfs: speedup checking for extent sharedness during fiemap". This adds the missing logic, which is the counter part to what we do when adding a shared node to the cache at store_backref_shared_cache(). Fixes: 12a824dc67a6 ("btrfs: speedup checking for extent sharedness during fiemap") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/backref.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index dce3a16996b9..3c0c1f626c75 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1557,6 +1557,19 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_shared_cache *cache return false; *is_shared = entry->is_shared; + /* + * If the node at this level is shared, than all nodes below are also + * shared. Currently some of the nodes below may be marked as not shared + * because we have just switched from one leaf to another, and switched + * also other nodes above the leaf and below the current level, so mark + * them as shared. + */ + if (*is_shared) { + for (int i = 0; i < level; i++) { + cache->entries[i].is_shared = true; + cache->entries[i].gen = entry->gen; + } + } return true; } -- cgit From 97c96e9fa36616d7890a6f3438172fc501927f01 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Mon, 26 Sep 2022 10:09:26 -0700 Subject: io_uring: simplify __io_uring_add_tctx_node Remove submitter parameter from __io_uring_add_tctx_node. It was only called from one place, and we can do that logic in that one place. Signed-off-by: Dylan Yudaken Fixes: 97bbdc06a444 ("io_uring: add IORING_SETUP_SINGLE_ISSUER") Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 2 +- io_uring/tctx.c | 30 ++++++++++++++++++++---------- io_uring/tctx.h | 6 ++++-- 3 files changed, 25 insertions(+), 13 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 99a52f34b7d3..fe6ef64c873e 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3355,7 +3355,7 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) if (fd < 0) return fd; - ret = __io_uring_add_tctx_node(ctx, false); + ret = __io_uring_add_tctx_node(ctx); if (ret) { put_unused_fd(fd); return ret; diff --git a/io_uring/tctx.c b/io_uring/tctx.c index 7f97d97fef0a..dd0205fcdb13 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -105,18 +105,12 @@ static int io_register_submitter(struct io_ring_ctx *ctx) return ret; } -int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter) +int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; int ret; - if ((ctx->flags & IORING_SETUP_SINGLE_ISSUER) && submitter) { - ret = io_register_submitter(ctx); - if (ret) - return ret; - } - if (unlikely(!tctx)) { ret = io_uring_alloc_task_context(current, ctx); if (unlikely(ret)) @@ -150,8 +144,24 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter) list_add(&node->ctx_node, &ctx->tctx_list); mutex_unlock(&ctx->uring_lock); } - if (submitter) - tctx->last = ctx; + return 0; +} + +int __io_uring_add_tctx_node_from_submit(struct io_ring_ctx *ctx) +{ + int ret; + + if (ctx->flags & IORING_SETUP_SINGLE_ISSUER) { + ret = io_register_submitter(ctx); + if (ret) + return ret; + } + + ret = __io_uring_add_tctx_node(ctx); + if (ret) + return ret; + + current->io_uring->last = ctx; return 0; } @@ -259,7 +269,7 @@ int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, return -EINVAL; mutex_unlock(&ctx->uring_lock); - ret = __io_uring_add_tctx_node(ctx, false); + ret = __io_uring_add_tctx_node(ctx); mutex_lock(&ctx->uring_lock); if (ret) return ret; diff --git a/io_uring/tctx.h b/io_uring/tctx.h index 25974beed4d6..608e96de70a2 100644 --- a/io_uring/tctx.h +++ b/io_uring/tctx.h @@ -9,7 +9,8 @@ struct io_tctx_node { int io_uring_alloc_task_context(struct task_struct *task, struct io_ring_ctx *ctx); void io_uring_del_tctx_node(unsigned long index); -int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter); +int __io_uring_add_tctx_node(struct io_ring_ctx *ctx); +int __io_uring_add_tctx_node_from_submit(struct io_ring_ctx *ctx); void io_uring_clean_tctx(struct io_uring_task *tctx); void io_uring_unreg_ringfd(void); @@ -27,5 +28,6 @@ static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) if (likely(tctx && tctx->last == ctx)) return 0; - return __io_uring_add_tctx_node(ctx, true); + + return __io_uring_add_tctx_node_from_submit(ctx); } -- cgit From 4add705e4eebbdd919741de0548d7029c8c92b68 Mon Sep 17 00:00:00 2001 From: Dylan Yudaken Date: Mon, 26 Sep 2022 10:09:27 -0700 Subject: io_uring: remove io_register_submitter this is no longer needed, as submitter_task is set at creation time. Signed-off-by: Dylan Yudaken Fixes: 97bbdc06a444 ("io_uring: add IORING_SETUP_SINGLE_ISSUER") Signed-off-by: Jens Axboe --- io_uring/tctx.c | 22 +++------------------- 1 file changed, 3 insertions(+), 19 deletions(-) diff --git a/io_uring/tctx.c b/io_uring/tctx.c index dd0205fcdb13..4324b1cf1f6a 100644 --- a/io_uring/tctx.c +++ b/io_uring/tctx.c @@ -91,20 +91,6 @@ __cold int io_uring_alloc_task_context(struct task_struct *task, return 0; } -static int io_register_submitter(struct io_ring_ctx *ctx) -{ - int ret = 0; - - mutex_lock(&ctx->uring_lock); - if (!ctx->submitter_task) - ctx->submitter_task = get_task_struct(current); - else if (ctx->submitter_task != current) - ret = -EEXIST; - mutex_unlock(&ctx->uring_lock); - - return ret; -} - int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; @@ -151,11 +137,9 @@ int __io_uring_add_tctx_node_from_submit(struct io_ring_ctx *ctx) { int ret; - if (ctx->flags & IORING_SETUP_SINGLE_ISSUER) { - ret = io_register_submitter(ctx); - if (ret) - return ret; - } + if (ctx->flags & IORING_SETUP_SINGLE_ISSUER + && ctx->submitter_task != current) + return -EEXIST; ret = __io_uring_add_tctx_node(ctx); if (ret) -- cgit From d7cce96c449e35bbfd41e830b341b95973891eed Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 27 Sep 2022 01:13:30 +0100 Subject: io_uring: limit registration w/ SINGLE_ISSUER IORING_SETUP_SINGLE_ISSUER restricts what tasks can submit requests. Extend it to registration as well, so non-owning task can't do registrations. It's not necessary at the moment but might be useful in the future. Cc: # 6.0 Fixes: 97bbdc06a444 ("io_uring: add IORING_SETUP_SINGLE_ISSUER") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/f52a6a9c8a8990d4a831f73c0571e7406aac2bba.1664237592.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index fe6ef64c873e..63f6ce5e5355 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3890,6 +3890,9 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, if (WARN_ON_ONCE(percpu_ref_is_dying(&ctx->refs))) return -ENXIO; + if (ctx->submitter_task && ctx->submitter_task != current) + return -EEXIST; + if (ctx->restricted) { if (opcode >= IORING_REGISTER_LAST) return -EINVAL; -- cgit From 28148a17c988b614534f457da86893f83664ad43 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 6 Oct 2022 20:33:01 +0200 Subject: openrisc: Fix pagewalk usage in arch_dma_{clear, set}_uncached Since commit 8782fb61cc848 ("mm: pagewalk: Fix race between unmap and page walker"), walk_page_range() on kernel ranges won't work anymore, walk_page_range_novma() must be used instead. Note: I don't have an openrisc development setup, so this is completely untested. Fixes: 8782fb61cc848 ("mm: pagewalk: Fix race between unmap and page walker") Signed-off-by: Jann Horn Signed-off-by: Stafford Horne --- arch/openrisc/kernel/dma.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index a82b2caaa560..b3edbb33b621 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -74,10 +74,10 @@ void *arch_dma_set_uncached(void *cpu_addr, size_t size) * We need to iterate through the pages, clearing the dcache for * them and setting the cache-inhibit bit. */ - mmap_read_lock(&init_mm); - error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops, - NULL); - mmap_read_unlock(&init_mm); + mmap_write_lock(&init_mm); + error = walk_page_range_novma(&init_mm, va, va + size, + &set_nocache_walk_ops, NULL, NULL); + mmap_write_unlock(&init_mm); if (error) return ERR_PTR(error); @@ -88,11 +88,11 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size) { unsigned long va = (unsigned long)cpu_addr; - mmap_read_lock(&init_mm); + mmap_write_lock(&init_mm); /* walk_page_range shouldn't be able to fail here */ - WARN_ON(walk_page_range(&init_mm, va, va + size, - &clear_nocache_walk_ops, NULL)); - mmap_read_unlock(&init_mm); + WARN_ON(walk_page_range_novma(&init_mm, va, va + size, + &clear_nocache_walk_ops, NULL, NULL)); + mmap_write_unlock(&init_mm); } void arch_sync_dma_for_device(phys_addr_t addr, size_t size, -- cgit From 556a11a082ee208455ed42e7c460849cc3dbd68c Mon Sep 17 00:00:00 2001 From: Amadeusz Sławiński Date: Fri, 7 Oct 2022 10:48:56 +0200 Subject: ALSA: hda: Update register polling macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Recent commit d91857059def ("ALSA: hda: Rework snd_hdac_stream_reset() to use macros") missed that on some devices register access needs to be done with unaligned access helper. Change polling macros to use read_poll_timeout_atomic() in order to specify register read function. Fixes: d91857059def ("ALSA: hda: Rework snd_hdac_stream_reset() to use macros") Reported-by: Jon Hunter Link: https://lore.kernel.org/alsa-devel/20220818141517.109280-1-amadeuszx.slawinski@linux.intel.com/T/#m1270737db52b5ef163eff73cb5f862d16a07a428 Reviewed-by: Cezary Rojewski Signed-off-by: Amadeusz Sławiński Link: https://lore.kernel.org/r/20221007084856.1638302-1-amadeuszx.slawinski@linux.intel.com Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index ddff03e546e9..35778f953a3f 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -592,11 +592,11 @@ int snd_hdac_get_stream_stripe_ctl(struct hdac_bus *bus, #define snd_hdac_stream_readb(dev, reg) \ snd_hdac_reg_readb((dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readb_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readb_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readb, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) #define snd_hdac_stream_readl_poll(dev, reg, val, cond, delay_us, timeout_us) \ - readl_poll_timeout((dev)->sd_addr + AZX_REG_ ## reg, val, cond, \ - delay_us, timeout_us) + read_poll_timeout_atomic(snd_hdac_reg_readl, val, cond, delay_us, timeout_us, \ + false, (dev)->bus, (dev)->sd_addr + AZX_REG_ ## reg) /* update a register, pass without AZX_REG_ prefix */ #define snd_hdac_stream_updatel(dev, reg, mask, val) \ -- cgit From 9902b303b5ade208b58f0dd38a09831813582211 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 9 Oct 2022 12:42:09 +0200 Subject: ALSA: usb-audio: Avoid unnecessary interface change at EP close We toggle USB interface at PCM prepare and reset at close. When the PCM isn't prepared, resetting again makes little sense. Check the current altset and avoid unnecessary interface reset at EP close. Link: https://lore.kernel.org/r/20221009104212.18877-2-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/endpoint.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 48a3843a08f1..f21acbc9f4f4 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -32,6 +32,7 @@ struct snd_usb_iface_ref { unsigned char iface; bool need_setup; int opened; + int altset; struct list_head list; }; @@ -899,6 +900,9 @@ static int endpoint_set_interface(struct snd_usb_audio *chip, int altset = set ? ep->altsetting : 0; int err; + if (ep->iface_ref->altset == altset) + return 0; + usb_audio_dbg(chip, "Setting usb interface %d:%d for EP 0x%x\n", ep->iface, altset, ep->ep_num); err = usb_set_interface(chip->dev, ep->iface, altset); @@ -910,6 +914,7 @@ static int endpoint_set_interface(struct snd_usb_audio *chip, if (chip->quirk_flags & QUIRK_FLAG_IFACE_DELAY) msleep(50); + ep->iface_ref->altset = altset; return 0; } -- cgit From a74f8d0aa902ca494676b79226e0b5a1747b81d4 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 9 Oct 2022 12:42:10 +0200 Subject: ALSA: usb-audio: Apply mutex around snd_usb_endpoint_set_params() The protection with chip->mutex was lost after splitting snd_usb_endpoint_set_params() and snd_usb_endpoint_prepare(). Apply the same mutex again to the former function. Fixes: 2be79d586454 ("ALSA: usb-audio: Split endpoint setups for hw_params and prepare (take#2)") Link: https://lore.kernel.org/r/20221009104212.18877-3-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/endpoint.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index f21acbc9f4f4..da378e565ef8 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -1337,10 +1337,11 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, const struct audioformat *fmt = ep->cur_audiofmt; int err; + mutex_lock(&chip->mutex); /* release old buffers, if any */ err = release_urbs(ep, false); if (err < 0) - return err; + goto unlock; ep->datainterval = fmt->datainterval; ep->maxpacksize = fmt->maxpacksize; @@ -1378,13 +1379,16 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, usb_audio_dbg(chip, "Set up %d URBS, ret=%d\n", ep->nurbs, err); if (err < 0) - return err; + goto unlock; /* some unit conversions in runtime */ ep->maxframesize = ep->maxpacksize / ep->cur_frame_bytes; ep->curframesize = ep->curpacksize / ep->cur_frame_bytes; - return update_clock_ref_rate(chip, ep); + err = update_clock_ref_rate(chip, ep); + unlock: + mutex_unlock(&chip->mutex); + return err; } static int init_sample_rate(struct snd_usb_audio *chip, -- cgit From 9355b60e401d825590d37f04ea873c58efe9b7bf Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 9 Oct 2022 12:42:11 +0200 Subject: ALSA: usb-audio: Correct the return code from snd_usb_endpoint_set_params() snd_usb_endpoint_set_params() should return zero for a success, but currently it returns the sample rate. Correct it. Fixes: 2be79d586454 ("ALSA: usb-audio: Split endpoint setups for hw_params and prepare (take#2)") Link: https://lore.kernel.org/r/20221009104212.18877-4-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/endpoint.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index da378e565ef8..44cce6cec9da 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -1386,6 +1386,8 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, ep->curframesize = ep->curpacksize / ep->cur_frame_bytes; err = update_clock_ref_rate(chip, ep); + if (err >= 0) + err = 0; unlock: mutex_unlock(&chip->mutex); return err; -- cgit From 1045f5f1ff0751423aeb65648e5e1abd7a7a8672 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Sun, 9 Oct 2022 12:42:12 +0200 Subject: ALSA: usb-audio: Avoid superfluous endpoint setup After splitting to snd_usb_endpoint_set_params() and *_prepare(), the skip of each function should be checked with different flags, while we still use ep->need_setup as the single one. Introduce ep->need_prepare for indicating the need of prepare, and also add the missing check of ep->need_setup at the set_params. Fixes: 2be79d586454 ("ALSA: usb-audio: Split endpoint setups for hw_params and prepare (take#2)") Link: https://lore.kernel.org/r/20221009104212.18877-5-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/card.h | 3 ++- sound/usb/endpoint.c | 17 ++++++++++++----- 2 files changed, 14 insertions(+), 6 deletions(-) diff --git a/sound/usb/card.h b/sound/usb/card.h index ca75f2206170..40061550105a 100644 --- a/sound/usb/card.h +++ b/sound/usb/card.h @@ -129,7 +129,8 @@ struct snd_usb_endpoint { in a stream */ bool implicit_fb_sync; /* syncs with implicit feedback */ bool lowlatency_playback; /* low-latency playback mode */ - bool need_setup; /* (re-)need for configure? */ + bool need_setup; /* (re-)need for hw_params? */ + bool need_prepare; /* (re-)need for prepare? */ /* for hw constraints */ const struct audioformat *cur_audiofmt; diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 44cce6cec9da..d0b8d61d1d22 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -824,6 +824,7 @@ snd_usb_endpoint_open(struct snd_usb_audio *chip, ep->implicit_fb_sync = fp->implicit_fb; ep->need_setup = true; + ep->need_prepare = true; usb_audio_dbg(chip, " channels=%d, rate=%d, format=%s, period_bytes=%d, periods=%d, implicit_fb=%d\n", ep->cur_channels, ep->cur_rate, @@ -952,7 +953,7 @@ void snd_usb_endpoint_close(struct snd_usb_audio *chip, /* Prepare for suspening EP, called from the main suspend handler */ void snd_usb_endpoint_suspend(struct snd_usb_endpoint *ep) { - ep->need_setup = true; + ep->need_prepare = true; if (ep->iface_ref) ep->iface_ref->need_setup = true; if (ep->clock_ref) @@ -1335,9 +1336,12 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, struct snd_usb_endpoint *ep) { const struct audioformat *fmt = ep->cur_audiofmt; - int err; + int err = 0; mutex_lock(&chip->mutex); + if (!ep->need_setup) + goto unlock; + /* release old buffers, if any */ err = release_urbs(ep, false); if (err < 0) @@ -1386,8 +1390,11 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, ep->curframesize = ep->curpacksize / ep->cur_frame_bytes; err = update_clock_ref_rate(chip, ep); - if (err >= 0) + if (err >= 0) { + ep->need_setup = false; err = 0; + } + unlock: mutex_unlock(&chip->mutex); return err; @@ -1437,7 +1444,7 @@ int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, mutex_lock(&chip->mutex); if (WARN_ON(!ep->iface_ref)) goto unlock; - if (!ep->need_setup) + if (!ep->need_prepare) goto unlock; /* If the interface has been already set up, just set EP parameters */ @@ -1491,7 +1498,7 @@ int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, ep->iface_ref->need_setup = false; done: - ep->need_setup = false; + ep->need_prepare = false; err = 1; unlock: -- cgit From 285febabac4a16655372d23ff43e89ff6f216691 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Sun, 9 Oct 2022 18:10:38 +0800 Subject: blk-wbt: fix that 'rwb->wc' is always set to 1 in wbt_init() commit 8c5035dfbb94 ("blk-wbt: call rq_qos_add() after wb_normal is initialized") moves wbt_set_write_cache() before rq_qos_add(), which is wrong because wbt_rq_qos() is still NULL. Fix the problem by removing wbt_set_write_cache() and setting 'rwb->wc' directly. Noted that this patch also remove the redundant setting of 'rab->wc'. Fixes: 8c5035dfbb94 ("blk-wbt: call rq_qos_add() after wb_normal is initialized") Reported-by: kernel test robot Link: https://lore.kernel.org/r/202210081045.77ddf59b-yujie.liu@intel.com Signed-off-by: Yu Kuai Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20221009101038.1692875-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe --- block/blk-wbt.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 246467926253..c293e08b301f 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -841,12 +841,11 @@ int wbt_init(struct request_queue *q) rwb->last_comp = rwb->last_issue = jiffies; rwb->win_nsec = RWB_WINDOW_NSEC; rwb->enable_state = WBT_STATE_ON_DEFAULT; - rwb->wc = 1; + rwb->wc = test_bit(QUEUE_FLAG_WC, &q->queue_flags); rwb->rq_depth.default_depth = RWB_DEF_DEPTH; rwb->min_lat_nsec = wbt_default_latency_nsec(q); wbt_queue_depth_changed(&rwb->rqos); - wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); /* * Assign rwb and add the stats callback. -- cgit From 7023472834a39341460dae5c9b506c76c5940cad Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Mon, 3 Oct 2022 13:16:30 +0100 Subject: drm/i915/guc: Fix revocation of non-persistent contexts Patch which added graceful exit for non-persistent contexts missed the fact it is not enough to set the exiting flag on a context and let the backend handle it from there. GuC backend cannot handle it because it runs independently in the firmware and driver might not see the requests ever again. Patch also missed the fact some usages of intel_context_is_banned in the GuC backend needed replacing with newly introduced intel_context_is_schedulable. Fix the first issue by calling into backend revoke when we know this is the last chance to do it. Fix the second issue by replacing intel_context_is_banned with intel_context_is_schedulable, which should always be safe since latter is a superset of the former. v2: * Just call ce->ops->revoke unconditionally. (Andrzej) Signed-off-by: Tvrtko Ursulin Fixes: 45c64ecf97ee ("drm/i915: Improve user experience and driver robustness under SIGINT or similar") Cc: Andrzej Hajda Cc: John Harrison Cc: Daniele Ceraolo Spurio Cc: # v6.0+ Reviewed-by: Andrzej Hajda Acked-by: Daniele Ceraolo Spurio Link: https://patchwork.freedesktop.org/patch/msgid/20221003121630.694249-1-tvrtko.ursulin@linux.intel.com (cherry picked from commit 0add082cebac8555ee3972ba768ae5c01db7a498) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 8 +------ drivers/gpu/drm/i915/gt/intel_context.c | 5 ++--- drivers/gpu/drm/i915/gt/intel_context.h | 3 +-- drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 26 +++++++++++------------ 4 files changed, 17 insertions(+), 25 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index dabdfe09f5e5..e7148a994b3a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -1383,14 +1383,8 @@ kill_engines(struct i915_gem_engines *engines, bool exit, bool persistent) */ for_each_gem_engine(ce, engines, it) { struct intel_engine_cs *engine; - bool skip = false; - if (exit) - skip = intel_context_set_exiting(ce); - else if (!persistent) - skip = intel_context_exit_nonpersistent(ce, NULL); - - if (skip) + if ((exit || !persistent) && intel_context_revoke(ce)) continue; /* Already marked. */ /* diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 654a092ed3d6..e94365b08f1e 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -614,13 +614,12 @@ bool intel_context_ban(struct intel_context *ce, struct i915_request *rq) return ret; } -bool intel_context_exit_nonpersistent(struct intel_context *ce, - struct i915_request *rq) +bool intel_context_revoke(struct intel_context *ce) { bool ret = intel_context_set_exiting(ce); if (ce->ops->revoke) - ce->ops->revoke(ce, rq, ce->engine->props.preempt_timeout_ms); + ce->ops->revoke(ce, NULL, ce->engine->props.preempt_timeout_ms); return ret; } diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index 8e2d70630c49..be09fb2e883a 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -329,8 +329,7 @@ static inline bool intel_context_set_exiting(struct intel_context *ce) return test_and_set_bit(CONTEXT_EXITING, &ce->flags); } -bool intel_context_exit_nonpersistent(struct intel_context *ce, - struct i915_request *rq); +bool intel_context_revoke(struct intel_context *ce); static inline bool intel_context_force_single_submission(const struct intel_context *ce) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 22ba66e48a9b..1db59eeb34db 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -684,7 +684,7 @@ static int __guc_add_request(struct intel_guc *guc, struct i915_request *rq) * Corner case where requests were sitting in the priority list or a * request resubmitted after the context was banned. */ - if (unlikely(intel_context_is_banned(ce))) { + if (unlikely(!intel_context_is_schedulable(ce))) { i915_request_put(i915_request_mark_eio(rq)); intel_engine_signal_breadcrumbs(ce->engine); return 0; @@ -870,15 +870,15 @@ static int guc_wq_item_append(struct intel_guc *guc, struct i915_request *rq) { struct intel_context *ce = request_to_scheduling_context(rq); - int ret = 0; + int ret; - if (likely(!intel_context_is_banned(ce))) { - ret = __guc_wq_item_append(rq); + if (unlikely(!intel_context_is_schedulable(ce))) + return 0; - if (unlikely(ret == -EBUSY)) { - guc->stalled_request = rq; - guc->submission_stall_reason = STALL_MOVE_LRC_TAIL; - } + ret = __guc_wq_item_append(rq); + if (unlikely(ret == -EBUSY)) { + guc->stalled_request = rq; + guc->submission_stall_reason = STALL_MOVE_LRC_TAIL; } return ret; @@ -897,7 +897,7 @@ static bool multi_lrc_submit(struct i915_request *rq) * submitting all the requests generated in parallel. */ return test_bit(I915_FENCE_FLAG_SUBMIT_PARALLEL, &rq->fence.flags) || - intel_context_is_banned(ce); + !intel_context_is_schedulable(ce); } static int guc_dequeue_one_context(struct intel_guc *guc) @@ -966,7 +966,7 @@ register_context: struct intel_context *ce = request_to_scheduling_context(last); if (unlikely(!ctx_id_mapped(guc, ce->guc_id.id) && - !intel_context_is_banned(ce))) { + intel_context_is_schedulable(ce))) { ret = try_context_registration(ce, false); if (unlikely(ret == -EPIPE)) { goto deadlk; @@ -1576,7 +1576,7 @@ static void guc_reset_state(struct intel_context *ce, u32 head, bool scrub) { struct intel_engine_cs *engine = __context_to_physical_engine(ce); - if (intel_context_is_banned(ce)) + if (!intel_context_is_schedulable(ce)) return; GEM_BUG_ON(!intel_context_is_pinned(ce)); @@ -4424,12 +4424,12 @@ static void guc_handle_context_reset(struct intel_guc *guc, { trace_intel_context_reset(ce); - if (likely(!intel_context_is_banned(ce))) { + if (likely(intel_context_is_schedulable(ce))) { capture_error_state(guc, ce); guc_context_replay(ce); } else { drm_info(&guc_to_gt(guc)->i915->drm, - "Ignoring context reset notification of banned context 0x%04X on %s", + "Ignoring context reset notification of exiting context 0x%04X on %s", ce->guc_id.id, ce->engine->name); } } -- cgit From c5e595e752b3a1c68cca57c3559521237332fbec Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 4 Oct 2022 14:19:13 +0100 Subject: drm/i915/display: handle migration for dpt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On platforms like DG2, it looks like the dpt path here is missing the migrate-to-lmem step on discrete platforms. v2: - Move the vma_pin() under the for_i915_gem_ww(), otherwise the object can be moved after dropping the lock and then doing the pin. Fixes: 33e7a975103c ("drm/i915/xelpd: First stab at DPT support") Signed-off-by: Matthew Auld Cc: Jianshui Yu Cc: Ville Syrjälä Cc: Nirmoy Das Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20221004131916.233474-2-matthew.auld@intel.com (cherry picked from commit 5769f64ff09aab23a9045fa13b464fb5070d3fb2) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_fb_pin.c | 51 +++++++++++++++++++---------- 1 file changed, 33 insertions(+), 18 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c index c86e5d4ee016..733972fab07f 100644 --- a/drivers/gpu/drm/i915/display/intel_fb_pin.c +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c @@ -26,10 +26,17 @@ intel_pin_fb_obj_dpt(struct drm_framebuffer *fb, struct drm_device *dev = fb->dev; struct drm_i915_private *dev_priv = to_i915(dev); struct drm_i915_gem_object *obj = intel_fb_obj(fb); + struct i915_gem_ww_ctx ww; struct i915_vma *vma; u32 alignment; int ret; + /* + * We are not syncing against the binding (and potential migrations) + * below, so this vm must never be async. + */ + GEM_WARN_ON(vm->bind_async_flags); + if (WARN_ON(!i915_gem_object_is_framebuffer(obj))) return ERR_PTR(-EINVAL); @@ -37,29 +44,37 @@ intel_pin_fb_obj_dpt(struct drm_framebuffer *fb, atomic_inc(&dev_priv->gpu_error.pending_fb_pin); - ret = i915_gem_object_lock_interruptible(obj, NULL); - if (!ret) { + for_i915_gem_ww(&ww, ret, true) { + ret = i915_gem_object_lock(obj, &ww); + if (ret) + continue; + + if (HAS_LMEM(dev_priv)) { + ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0); + if (ret) + continue; + } + ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE); - i915_gem_object_unlock(obj); - } - if (ret) { - vma = ERR_PTR(ret); - goto err; - } + if (ret) + continue; - vma = i915_vma_instance(obj, vm, view); - if (IS_ERR(vma)) - goto err; + vma = i915_vma_instance(obj, vm, view); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + continue; + } - if (i915_vma_misplaced(vma, 0, alignment, 0)) { - ret = i915_vma_unbind_unlocked(vma); - if (ret) { - vma = ERR_PTR(ret); - goto err; + if (i915_vma_misplaced(vma, 0, alignment, 0)) { + ret = i915_vma_unbind(vma); + if (ret) + continue; } - } - ret = i915_vma_pin(vma, 0, alignment, PIN_GLOBAL); + ret = i915_vma_pin_ww(vma, &ww, 0, alignment, PIN_GLOBAL); + if (ret) + continue; + } if (ret) { vma = ERR_PTR(ret); goto err; -- cgit From f3e59ff348c077a6afd4edb23d7e69e9cba62fdc Mon Sep 17 00:00:00 2001 From: Peter Oberparleiter Date: Wed, 28 Sep 2022 15:34:33 +0200 Subject: s390/vmur: remove unnecessary BUG statement An existing BUG statement in vmur's interrupt handler triggers if: 1. An online vmur device is removed (e.g. due to driver unload, manual unbind or channel-report words indicating hypervisor-side device removal) 2. Device deactivation fails due to firmware/hypervisor error, leaving subchannel enabled for interrupts + drvdata=NULL 3. Interrupt occurs This situation is highly unlikely and not a clear indication of a general system error that would warrant stopping the full Linux system. Also it can be prevented completely by clearing the interrupt handler when unsetting a vmur device's drvdata. Replace the BUG statement in vmur's interrupt handler by clearing the interrupt handler callback during device removal. Also move the initial setting of the interrupt handler callback under lock for consistency reasons. Reviewed-by: Sven Schnelle Reviewed-by: Heiko Carstens Signed-off-by: Peter Oberparleiter Signed-off-by: Vasily Gorbik --- drivers/s390/char/vmur.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c index 68f49e2e964c..471f07ca5066 100644 --- a/drivers/s390/char/vmur.c +++ b/drivers/s390/char/vmur.c @@ -293,7 +293,6 @@ static void ur_int_handler(struct ccw_device *cdev, unsigned long intparm, return; } urd = dev_get_drvdata(&cdev->dev); - BUG_ON(!urd); /* On special conditions irb is an error pointer */ if (IS_ERR(irb)) urd->io_request_rc = PTR_ERR(irb); @@ -809,7 +808,6 @@ static int ur_probe(struct ccw_device *cdev) rc = -ENOMEM; goto fail_urdev_put; } - cdev->handler = ur_int_handler; /* validate virtual unit record device */ urd->class = get_urd_class(urd); @@ -823,6 +821,7 @@ static int ur_probe(struct ccw_device *cdev) } spin_lock_irq(get_ccwdev_lock(cdev)); dev_set_drvdata(&cdev->dev, urd); + cdev->handler = ur_int_handler; spin_unlock_irq(get_ccwdev_lock(cdev)); mutex_unlock(&vmur_mutex); @@ -963,6 +962,7 @@ static void ur_remove(struct ccw_device *cdev) spin_lock_irqsave(get_ccwdev_lock(cdev), flags); urdev_put(dev_get_drvdata(&cdev->dev)); dev_set_drvdata(&cdev->dev, NULL); + cdev->handler = NULL; spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); mutex_unlock(&vmur_mutex); -- cgit From bf18140d30541c2c1e5c0f57879634f3d0d04912 Mon Sep 17 00:00:00 2001 From: Peter Oberparleiter Date: Mon, 26 Sep 2022 16:56:04 +0200 Subject: s390/vmur: generate uevent on unsolicited device end When a traditional channel-attached device transitions from not-ready to ready state, an unsolicited DEVICE END I/O interrupt is raised. This happens for example when a new file arrives in the z/VM virtual reader device. Change the Linux kernel to generate a change uevent when such an interrupt occurs for any online unit record devices supported by the vmur driver. This can be useful to automatically trigger processing of files as they arrive in the reader device. A sample udev rule for running a program when this event occurs looks as follows: ENV{DRIVER}=="vmur", ACTION=="change", ENV{EVENT}=="unsol_de", \ RUN{program}="/path/to/program" The rule can be tested using the following steps: 1. Set reader device online (assuming default reader device number 000c) $ chzdev -ea 0.0.000c 2. Force a ready-state transition using z/VM's READY CP command $ vmcp ready 000c Suggested-by: Alan Altmark Reviewed-by: Heiko Carstens Reviewed-by: Sven Schnelle Signed-off-by: Peter Oberparleiter Signed-off-by: Vasily Gorbik --- drivers/s390/char/vmur.c | 33 ++++++++++++++++++++++++++++++++- drivers/s390/char/vmur.h | 2 ++ 2 files changed, 34 insertions(+), 1 deletion(-) diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c index 471f07ca5066..131293f7f152 100644 --- a/drivers/s390/char/vmur.c +++ b/drivers/s390/char/vmur.c @@ -15,12 +15,14 @@ #include #include #include +#include #include #include #include #include #include +#include #include "vmur.h" @@ -78,6 +80,8 @@ static struct ccw_driver ur_driver = { static DEFINE_MUTEX(vmur_mutex); +static void ur_uevent(struct work_struct *ws); + /* * Allocation, freeing, getting and putting of urdev structures * @@ -108,6 +112,7 @@ static struct urdev *urdev_alloc(struct ccw_device *cdev) ccw_device_get_id(cdev, &urd->dev_id); mutex_init(&urd->io_mutex); init_waitqueue_head(&urd->wait); + INIT_WORK(&urd->uevent_work, ur_uevent); spin_lock_init(&urd->open_lock); refcount_set(&urd->ref_count, 1); urd->cdev = cdev; @@ -275,6 +280,18 @@ out: return rc; } +static void ur_uevent(struct work_struct *ws) +{ + struct urdev *urd = container_of(ws, struct urdev, uevent_work); + char *envp[] = { + "EVENT=unsol_de", /* Unsolicited device-end interrupt */ + NULL + }; + + kobject_uevent_env(&urd->cdev->dev.kobj, KOBJ_CHANGE, envp); + urdev_put(urd); +} + /* * ur interrupt handler, called from the ccw_device layer */ @@ -288,11 +305,21 @@ static void ur_int_handler(struct ccw_device *cdev, unsigned long intparm, intparm, irb->scsw.cmd.cstat, irb->scsw.cmd.dstat, irb->scsw.cmd.count); } + urd = dev_get_drvdata(&cdev->dev); if (!intparm) { TRACE("ur_int_handler: unsolicited interrupt\n"); + + if (scsw_dstat(&irb->scsw) & DEV_STAT_DEV_END) { + /* + * Userspace might be interested in a transition to + * device-ready state. + */ + urdev_get(urd); + schedule_work(&urd->uevent_work); + } + return; } - urd = dev_get_drvdata(&cdev->dev); /* On special conditions irb is an error pointer */ if (IS_ERR(irb)) urd->io_request_rc = PTR_ERR(irb); @@ -927,6 +954,10 @@ static int ur_set_offline_force(struct ccw_device *cdev, int force) rc = -EBUSY; goto fail_urdev_put; } + if (cancel_work_sync(&urd->uevent_work)) { + /* Work not run yet - need to release reference here */ + urdev_put(urd); + } device_destroy(vmur_class, urd->char_device->dev); cdev_del(urd->char_device); urd->char_device = NULL; diff --git a/drivers/s390/char/vmur.h b/drivers/s390/char/vmur.h index 608b0719ce17..92d17d7cb47b 100644 --- a/drivers/s390/char/vmur.h +++ b/drivers/s390/char/vmur.h @@ -13,6 +13,7 @@ #define _VMUR_H_ #include +#include #define DEV_CLASS_UR_I 0x20 /* diag210 unit record input device class */ #define DEV_CLASS_UR_O 0x10 /* diag210 unit record output device class */ @@ -76,6 +77,7 @@ struct urdev { wait_queue_head_t wait; /* wait queue to serialize open */ int open_flag; /* "urdev is open" flag */ spinlock_t open_lock; /* serialize critical sections */ + struct work_struct uevent_work; /* work to send uevent */ }; /* -- cgit From 2e21c1575208786f667cb66d8cf87a52160b81db Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 10 Oct 2022 10:33:38 +0200 Subject: alpha: fix marvel_ioread8 build regression The previous build fix contained a small typo that led to another regression: arch/alpha/kernel/core_marvel.c:807:1: error: expected '=', ',', ';', 'asm' or '__attribute__' before 'marvel_ioread8' Reported-by: kernel test robot Fixes: e19d4ebc536d ("alpha: add full ioread64/iowrite64 implementation") Signed-off-by: Arnd Bergmann --- arch/alpha/kernel/core_marvel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 6d0b3baf97ff..e9348aec4649 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -803,7 +803,7 @@ void __iomem *marvel_ioportmap (unsigned long addr) return (void __iomem *)addr; } -unsigned u8 +u8 marvel_ioread8(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; -- cgit From 9afd20a5a1b3558950b5e12f3ed057ef93c64a05 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 10 Oct 2022 09:52:37 +0530 Subject: clk: spear: Move prototype to accessible header Fixes the following W=1 kernel build warning(s): drivers/clk/spear/spear6xx_clock.c:116:13: warning: no previous prototype for function 'spear6xx_clk_init' [-Wmissing-prototypes] Reported-by: kernel test robot Signed-off-by: Viresh Kumar Signed-off-by: Arnd Bergmann --- arch/arm/mach-spear/generic.h | 3 --- arch/arm/mach-spear/spear3xx.c | 1 + arch/arm/mach-spear/spear6xx.c | 1 + drivers/clk/spear/spear3xx_clock.c | 1 + drivers/clk/spear/spear6xx_clock.c | 1 + include/linux/clk/spear.h | 14 ++++++++++++++ 6 files changed, 18 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-spear/generic.h b/arch/arm/mach-spear/generic.h index 43b7996ab754..9e36920d4cfd 100644 --- a/arch/arm/mach-spear/generic.h +++ b/arch/arm/mach-spear/generic.h @@ -25,11 +25,8 @@ extern struct pl022_ssp_controller pl022_plat_data; extern struct pl08x_platform_data pl080_plat_data; void __init spear_setup_of_timer(void); -void __init spear3xx_clk_init(void __iomem *misc_base, - void __iomem *soc_config_base); void __init spear3xx_map_io(void); void __init spear3xx_dt_init_irq(void); -void __init spear6xx_clk_init(void __iomem *misc_base); void __init spear13xx_map_io(void); void __init spear13xx_l2x0_init(void); diff --git a/arch/arm/mach-spear/spear3xx.c b/arch/arm/mach-spear/spear3xx.c index 2ba406e92c41..7ef9670d3029 100644 --- a/arch/arm/mach-spear/spear3xx.c +++ b/arch/arm/mach-spear/spear3xx.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include "pl080.h" diff --git a/arch/arm/mach-spear/spear6xx.c b/arch/arm/mach-spear/spear6xx.c index 58183493e06d..98d9f2ad6b74 100644 --- a/arch/arm/mach-spear/spear6xx.c +++ b/arch/arm/mach-spear/spear6xx.c @@ -12,6 +12,7 @@ #include #include +#include #include #include #include diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c index 41717ff707f6..ba8791303156 100644 --- a/drivers/clk/spear/spear3xx_clock.c +++ b/drivers/clk/spear/spear3xx_clock.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include diff --git a/drivers/clk/spear/spear6xx_clock.c b/drivers/clk/spear/spear6xx_clock.c index 490701ac9e93..c192a9141b86 100644 --- a/drivers/clk/spear/spear6xx_clock.c +++ b/drivers/clk/spear/spear6xx_clock.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include "clk.h" diff --git a/include/linux/clk/spear.h b/include/linux/clk/spear.h index a64d034ceddd..eaf95ca656f8 100644 --- a/include/linux/clk/spear.h +++ b/include/linux/clk/spear.h @@ -8,6 +8,20 @@ #ifndef __LINUX_CLK_SPEAR_H #define __LINUX_CLK_SPEAR_H +#ifdef CONFIG_ARCH_SPEAR3XX +void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base); +#else +static inline void __init spear3xx_clk_init(void __iomem *misc_base, + void __iomem *soc_config_base) {} +#endif + +#ifdef CONFIG_ARCH_SPEAR6XX +void __init spear6xx_clk_init(void __iomem *misc_base); +#else +static inline void __init spear6xx_clk_init(void __iomem *misc_base) {} +#endif + #ifdef CONFIG_MACH_SPEAR1310 void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base); #else -- cgit From 390ca5bca7cdb95042dcb445375db0d9eba7aa4a Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Mon, 10 Oct 2022 09:41:07 +0530 Subject: ARM: spear6xx: Staticize few definitions Fix warnings with clang like: arch/arm/mach-spear/spear6xx.c:365:13: warning: no previous prototype for function 'spear6xx_map_io' [-Wmissing-prototypes] by making few definitions static. Reported-by: kernel test robot Signed-off-by: Viresh Kumar Signed-off-by: Arnd Bergmann --- arch/arm/mach-spear/spear6xx.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/mach-spear/spear6xx.c b/arch/arm/mach-spear/spear6xx.c index 98d9f2ad6b74..f0a1e704cceb 100644 --- a/arch/arm/mach-spear/spear6xx.c +++ b/arch/arm/mach-spear/spear6xx.c @@ -340,7 +340,7 @@ static struct pl08x_platform_data spear6xx_pl080_plat_data = { * 0xD0000000 0xFD000000 * 0xFC000000 0xFC000000 */ -struct map_desc spear6xx_io_desc[] __initdata = { +static struct map_desc spear6xx_io_desc[] __initdata = { { .virtual = (unsigned long)VA_SPEAR6XX_ML_CPU_BASE, .pfn = __phys_to_pfn(SPEAR_ICM3_ML1_2_BASE), @@ -360,12 +360,12 @@ struct map_desc spear6xx_io_desc[] __initdata = { }; /* This will create static memory mapping for selected devices */ -void __init spear6xx_map_io(void) +static void __init spear6xx_map_io(void) { iotable_init(spear6xx_io_desc, ARRAY_SIZE(spear6xx_io_desc)); } -void __init spear6xx_timer_init(void) +static void __init spear6xx_timer_init(void) { char pclk_name[] = "pll3_clk"; struct clk *gpt_clk, *pclk; @@ -395,7 +395,7 @@ void __init spear6xx_timer_init(void) } /* Add auxdata to pass platform data */ -struct of_dev_auxdata spear6xx_auxdata_lookup[] __initdata = { +static struct of_dev_auxdata spear6xx_auxdata_lookup[] __initdata = { OF_DEV_AUXDATA("arm,pl080", SPEAR_ICM3_DMA_BASE, NULL, &spear6xx_pl080_plat_data), {} -- cgit From bd60aafce5e1943fd395b8bf726e9824fa621eca Mon Sep 17 00:00:00 2001 From: Chen Lifu Date: Wed, 17 Aug 2022 16:14:20 +0800 Subject: ARM: mmp: Make some symbols static These symbols pxa168_usb_phy_resources, pxa168_u2o_resources, pxa168_u2oehci_resources and pxa168_u2ootg_resources are not used outside of arch/arm/mach-mmp/devices.c, so mark them static. Fixes the following sparse warning: arch/arm/mach-mmp/devices.c:241:17: warning: symbol 'pxa168_usb_phy_resources' was not declared. Should it be static? arch/arm/mach-mmp/devices.c:262:17: warning: symbol 'pxa168_u2o_resources' was not declared. Should it be static? arch/arm/mach-mmp/devices.c:297:17: warning: symbol 'pxa168_u2oehci_resources' was not declared. Should it be static? arch/arm/mach-mmp/devices.c:324:17: warning: symbol 'pxa168_u2ootg_resources' was not declared. Should it be static? Reported-by: kernel test robot Signed-off-by: Chen Lifu Signed-off-by: Arnd Bergmann --- arch/arm/mach-mmp/devices.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/mach-mmp/devices.c b/arch/arm/mach-mmp/devices.c index 79f4a2aa5475..9968239d8041 100644 --- a/arch/arm/mach-mmp/devices.c +++ b/arch/arm/mach-mmp/devices.c @@ -238,7 +238,7 @@ void pxa_usb_phy_deinit(void __iomem *phy_reg) static u64 __maybe_unused usb_dma_mask = ~(u32)0; #if IS_ENABLED(CONFIG_PHY_PXA_USB) -struct resource pxa168_usb_phy_resources[] = { +static struct resource pxa168_usb_phy_resources[] = { [0] = { .start = PXA168_U2O_PHYBASE, .end = PXA168_U2O_PHYBASE + USB_PHY_RANGE, @@ -259,7 +259,7 @@ struct platform_device pxa168_device_usb_phy = { #endif /* CONFIG_PHY_PXA_USB */ #if IS_ENABLED(CONFIG_USB_MV_UDC) -struct resource pxa168_u2o_resources[] = { +static struct resource pxa168_u2o_resources[] = { /* regbase */ [0] = { .start = PXA168_U2O_REGBASE + U2x_CAPREGS_OFFSET, @@ -294,7 +294,7 @@ struct platform_device pxa168_device_u2o = { #endif /* CONFIG_USB_MV_UDC */ #if IS_ENABLED(CONFIG_USB_EHCI_MV_U2O) -struct resource pxa168_u2oehci_resources[] = { +static struct resource pxa168_u2oehci_resources[] = { [0] = { .start = PXA168_U2O_REGBASE, .end = PXA168_U2O_REGBASE + USB_REG_RANGE, @@ -321,7 +321,7 @@ struct platform_device pxa168_device_u2oehci = { #endif #if IS_ENABLED(CONFIG_USB_MV_OTG) -struct resource pxa168_u2ootg_resources[] = { +static struct resource pxa168_u2ootg_resources[] = { /* regbase */ [0] = { .start = PXA168_U2O_REGBASE + U2x_CAPREGS_OFFSET, -- cgit From 66ba7c88507344dee68ad1acbdb630473ab36114 Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Mon, 10 Oct 2022 19:57:02 +1300 Subject: ALSA: hda/realtek: Correct pin configs for ASUS G533Z The initial fix for ASUS G533Z was based on faulty information. This fixes the pincfg to values that have been verified with no existing module options or other hacks enabled. Enables headphone jack, and 5.1 surround. [ corrected the indent level by tiwai ] Fixes: bc2c23549ccd ("ALSA: hda/realtek: Add pincfg for ASUS G533Z HP jack") Signed-off-by: Luke D. Jones Cc: Link: https://lore.kernel.org/r/20221010065702.35190-1-luke@ljones.dev Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index d89f95ae0efc..77a308a71cd4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8449,11 +8449,13 @@ static const struct hda_fixup alc269_fixups[] = { [ALC285_FIXUP_ASUS_G533Z_PINS] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { - { 0x14, 0x90170120 }, + { 0x14, 0x90170152 }, /* Speaker Surround Playback Switch */ + { 0x19, 0x03a19020 }, /* Mic Boost Volume */ + { 0x1a, 0x03a11c30 }, /* Mic Boost Volume */ + { 0x1e, 0x90170151 }, /* Rear jack, IN OUT EAPD Detect */ + { 0x21, 0x03211420 }, { } }, - .chained = true, - .chain_id = ALC294_FIXUP_ASUS_G513_PINS, }, [ALC294_FIXUP_ASUS_COEF_1B] = { .type = HDA_FIXUP_VERBS, -- cgit From 2ea8e1297801f7b0220ebf6ae61a5b74ca83981e Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Mon, 10 Oct 2022 20:03:47 +1300 Subject: ALSA: hda/realtek: Add quirk for ASUS GV601R laptop The ASUS ROG X16 (GV601R) series laptop has the same node-to-DAC pairs as early models and the G14, this includes bass speakers which are by default mapped incorrectly to the 0x06 node. Add a quirk to use the same DAC pairs as the G14. Signed-off-by: Luke D. Jones Cc: Link: https://lore.kernel.org/r/20221010070347.36883-1-luke@ljones.dev 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 77a308a71cd4..54a0f6b4ffc7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9423,6 +9423,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), -- cgit From ca5eebda3e1c1a58a1c5a337da393ed6734593e3 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Mon, 3 Oct 2022 09:35:34 -0400 Subject: block: avoid sign extend problem with default queue flags mask request_queue->queue_flags is unsigned long, which is 8-bytes on 64-bit architectures. Most queue flag modifications occur through bit field helpers, but default flags can be logically OR'd via the QUEUE_FLAG_MQ_DEFAULT mask. If this mask happens to include bit 31, the assignment can sign extend the field and set all upper 32 bits. This exact problem has been observed on a downstream kernel that happens to use bit 31 for QUEUE_FLAG_NOWAIT. This is not an immediate problem for current upstream because bit 31 is not included in the default flag assignment (and is not used at all, actually). Regardless, fix up the QUEUE_FLAG_MQ_DEFAULT mask definition to avoid the landmine in the future. Signed-off-by: Brian Foster Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20221003133534.1075582-1-bfoster@redhat.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 49373d002631..e4fb47753177 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -580,9 +580,9 @@ struct request_queue { #define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ #define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */ -#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP) | \ - (1 << QUEUE_FLAG_NOWAIT)) +#define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_IO_STAT) | \ + (1UL << QUEUE_FLAG_SAME_COMP) | \ + (1UL << QUEUE_FLAG_NOWAIT)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); -- cgit From a0a6314ae774f8a5e52a599946aa2ad0db867b83 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 10 Oct 2022 15:18:57 +0200 Subject: block: fix leaking minors of hidden disks The major/minor of a hidden gendisk is not propagated to the block device because it is never registered using bdev_add. But the lack of bd_dev also causes the dynamic major minor number not to be freed. Assign bd_dev manually to ensure the dynamic major minor gets freed. Based on a patch by Keith Busch. Fixes: 8ddcd653257c ("block: introduce GENHD_FL_HIDDEN") Reported-by: Daniel Wagner Signed-off-by: Christoph Hellwig Tested-by: Daniel Wagner Reviewed-by: Keith Busch Link: https://lore.kernel.org/r/20221010131857.748129-1-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/block/genhd.c b/block/genhd.c index d6a21803a57e..dc9b61dfb692 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -507,6 +507,13 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, */ dev_set_uevent_suppress(ddev, 0); disk_uevent(disk, KOBJ_ADD); + } else { + /* + * Even if the block_device for a hidden gendisk is not + * registered, it needs to have a valid bd_dev so that the + * freeing of the dynamic major works. + */ + disk->part0->bd_dev = MKDEV(disk->major, disk->first_minor); } disk_update_readahead(disk); -- cgit From 9c1ab6d54a2e9e59b8922d12145d895e7f88b62c Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Sat, 8 Oct 2022 08:32:50 +0000 Subject: docs: ftrace: Correct access mode The documentation gives an example for opening trace marker with write-only mode, but the flag WR_ONLY is not defined by glibc. Use O_WRONLY to replace it. Signed-off-by: Leo Yan Acked-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20221008083250.3160-1-leo.yan@linaro.org Signed-off-by: Jonathan Corbet --- Documentation/trace/ftrace.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index b37dc19e4d40..60bceb018d6a 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -564,7 +564,7 @@ of ftrace. Here is a list of some of the key files: start:: - trace_fd = open("trace_marker", WR_ONLY); + trace_fd = open("trace_marker", O_WRONLY); Note: Writing into the trace_marker file can also initiate triggers that are written into /sys/kernel/tracing/events/ftrace/print/trigger -- cgit From a0a6859f8330e007e014ae6f7187766786745e74 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Sat, 8 Oct 2022 17:41:39 +0800 Subject: docs/zh_CN: Fix build warning Since a patch set in my translation devicetree introduce some build warnings: Warning: Documentation/translations/zh_CN/devicetree/changesets.rst references a file that doesn't exist: Documentation/Devicetree/changesets.rst ... Change the first letter of Devicetree to lowercase. Fixes: 9485acfded20 ("docs/zh_CN: add dt kernel-api translation") Fixes: f773455ce59d ("docs/zh_CN: add dt overlay-notes translation") Fixes: 5e38432db8f3 ("docs/zh_CN: add dt dynamic-resolution-notes translation") Fixes: 330f5a300548 ("docs/zh_CN: add dt changesets translation") Reported-by: kernel test robot Signed-off-by: Yanteng Si Reviewed-by: Wu XiangCheng Link: https://lore.kernel.org/r/20221008094139.314151-1-siyanteng@loongson.cn Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/devicetree/changesets.rst | 2 +- .../translations/zh_CN/devicetree/dynamic-resolution-notes.rst | 2 +- Documentation/translations/zh_CN/devicetree/kernel-api.rst | 2 +- Documentation/translations/zh_CN/devicetree/overlay-notes.rst | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/Documentation/translations/zh_CN/devicetree/changesets.rst b/Documentation/translations/zh_CN/devicetree/changesets.rst index 2ace05f3c377..3df1b03c5695 100644 --- a/Documentation/translations/zh_CN/devicetree/changesets.rst +++ b/Documentation/translations/zh_CN/devicetree/changesets.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/Devicetree/changesets.rst +:Original: Documentation/devicetree/changesets.rst :翻译: diff --git a/Documentation/translations/zh_CN/devicetree/dynamic-resolution-notes.rst b/Documentation/translations/zh_CN/devicetree/dynamic-resolution-notes.rst index 115190341305..6dfd946d7093 100644 --- a/Documentation/translations/zh_CN/devicetree/dynamic-resolution-notes.rst +++ b/Documentation/translations/zh_CN/devicetree/dynamic-resolution-notes.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/Devicetree/dynamic-resolution-notes.rst +:Original: Documentation/devicetree/dynamic-resolution-notes.rst :翻译: diff --git a/Documentation/translations/zh_CN/devicetree/kernel-api.rst b/Documentation/translations/zh_CN/devicetree/kernel-api.rst index 6aa3b685494e..2fb729368b40 100644 --- a/Documentation/translations/zh_CN/devicetree/kernel-api.rst +++ b/Documentation/translations/zh_CN/devicetree/kernel-api.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/Devicetree/kernel-api.rst +:Original: Documentation/devicetree/kernel-api.rst :翻译: diff --git a/Documentation/translations/zh_CN/devicetree/overlay-notes.rst b/Documentation/translations/zh_CN/devicetree/overlay-notes.rst index 1bd482cb0a1b..43e3c0bc5a9f 100644 --- a/Documentation/translations/zh_CN/devicetree/overlay-notes.rst +++ b/Documentation/translations/zh_CN/devicetree/overlay-notes.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 .. include:: ../disclaimer-zh_CN.rst -:Original: Documentation/Devicetree/overlay-notes.rst +:Original: Documentation/devicetree/overlay-notes.rst :翻译: -- cgit From 0719fdba54836b6d7acbe7d74f81df2153a40810 Mon Sep 17 00:00:00 2001 From: Yixuan Cao Date: Wed, 5 Oct 2022 22:55:25 +0800 Subject: Documentation/mm/page_owner.rst: delete frequently changing experimental data The kernel size changes due to many factors, such as compiler version, configuration, and the build environment. This makes size comparison figures irrelevant to reader's setup. Remove these figures and describe the effects of page owner to the kernel size in general instead. Thanks for Jonathan Corbet, Bagas Sanjaya and Mike Rapoport's constructive suggestions. Signed-off-by: Yixuan Cao Link: https://lore.kernel.org/r/20221005145525.10359-1-caoyixuan2019@email.szu.edu.cn Signed-off-by: Jonathan Corbet --- Documentation/mm/page_owner.rst | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) diff --git a/Documentation/mm/page_owner.rst b/Documentation/mm/page_owner.rst index f5c954afe97c..f1efbb414ea6 100644 --- a/Documentation/mm/page_owner.rst +++ b/Documentation/mm/page_owner.rst @@ -38,22 +38,10 @@ not affect to allocation performance, especially if the static keys jump label patching functionality is available. Following is the kernel's code size change due to this facility. -- Without page owner:: - - text data bss dec hex filename - 48392 2333 644 51369 c8a9 mm/page_alloc.o - -- With page owner:: - - text data bss dec hex filename - 48800 2445 644 51889 cab1 mm/page_alloc.o - 6662 108 29 6799 1a8f mm/page_owner.o - 1025 8 8 1041 411 mm/page_ext.o - -Although, roughly, 8 KB code is added in total, page_alloc.o increase by -520 bytes and less than half of it is in hotpath. Building the kernel with -page owner and turning it on if needed would be great option to debug -kernel memory problem. +Although enabling page owner increases kernel size by several kilobytes, +most of this code is outside page allocator and its hot path. Building +the kernel with page owner and turning it on if needed would be great +option to debug kernel memory problem. There is one notice that is caused by implementation detail. page owner stores information into the memory from struct page extension. This memory -- cgit From 5f5cae9b0e815c27b614e761b065129b8481821a Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Wed, 5 Oct 2022 13:39:04 +1030 Subject: Documentation: ubifs: Fix compression idiom Clearly the author meant 'on the fly'. Signed-off-by: Joel Stanley Link: https://lore.kernel.org/r/20221005030904.65604-1-joel@jms.id.au Signed-off-by: Jonathan Corbet --- Documentation/filesystems/ubifs.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/filesystems/ubifs.rst b/Documentation/filesystems/ubifs.rst index e6ee99762534..ced2f7679ddb 100644 --- a/Documentation/filesystems/ubifs.rst +++ b/Documentation/filesystems/ubifs.rst @@ -59,7 +59,7 @@ differences. * JFFS2 is a write-through file-system, while UBIFS supports write-back, which makes UBIFS much faster on writes. -Similarly to JFFS2, UBIFS supports on-the-flight compression which makes +Similarly to JFFS2, UBIFS supports on-the-fly compression which makes it possible to fit quite a lot of data to the flash. Similarly to JFFS2, UBIFS is tolerant of unclean reboots and power-cuts. -- cgit From 7cc395312a364777ed428257c014cb7569fe3f48 Mon Sep 17 00:00:00 2001 From: Akira Yokosawa Date: Fri, 30 Sep 2022 11:19:36 +0900 Subject: docs/howto: Replace abundoned URL of gmane.org Somehow, there remains a link to gmane.org, which stopped working in 2016, in howto.rst. Replace it with the one at lore.kernel.org. Do the same changes under translations/ as well. Signed-off-by: Akira Yokosawa Cc: Federico Vaga Cc: Alex Shi Cc: Yanteng Si Cc: Hu Haowen Reviewed-by: Alex Shi Link: https://lore.kernel.org/r/20220930021936.26238-1-akiyks@gmail.com Signed-off-by: Jonathan Corbet --- Documentation/process/howto.rst | 2 +- Documentation/translations/it_IT/process/howto.rst | 2 +- Documentation/translations/ja_JP/howto.rst | 2 +- Documentation/translations/ko_KR/howto.rst | 2 +- Documentation/translations/zh_CN/process/howto.rst | 2 +- Documentation/translations/zh_TW/process/howto.rst | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) diff --git a/Documentation/process/howto.rst b/Documentation/process/howto.rst index cd6997a9d203..bd15c393ba3c 100644 --- a/Documentation/process/howto.rst +++ b/Documentation/process/howto.rst @@ -379,7 +379,7 @@ to subscribe and unsubscribe from the list can be found at: There are archives of the mailing list on the web in many different places. Use a search engine to find these archives. For example: - http://dir.gmane.org/gmane.linux.kernel + https://lore.kernel.org/lkml/ It is highly recommended that you search the archives about the topic you want to bring up, before you post it to the list. A lot of things diff --git a/Documentation/translations/it_IT/process/howto.rst b/Documentation/translations/it_IT/process/howto.rst index 16ad5622d549..15c08aea1dfe 100644 --- a/Documentation/translations/it_IT/process/howto.rst +++ b/Documentation/translations/it_IT/process/howto.rst @@ -394,7 +394,7 @@ trovati al sito: Ci sono diversi archivi della lista di discussione. Usate un qualsiasi motore di ricerca per trovarli. Per esempio: - http://dir.gmane.org/gmane.linux.kernel + https://lore.kernel.org/lkml/ É caldamente consigliata una ricerca in questi archivi sul tema che volete sollevare, prima di pubblicarlo sulla lista. Molte cose sono già state diff --git a/Documentation/translations/ja_JP/howto.rst b/Documentation/translations/ja_JP/howto.rst index 649e2ff2a407..b47a682d8ded 100644 --- a/Documentation/translations/ja_JP/howto.rst +++ b/Documentation/translations/ja_JP/howto.rst @@ -410,7 +410,7 @@ https://bugzilla.kernel.org に行ってください。もし今後のバグレ このメーリングリストのアーカイブは web 上の多数の場所に存在します。こ れらのアーカイブを探すにはサーチエンジンを使いましょう。例えば- - http://dir.gmane.org/gmane.linux.kernel + https://lore.kernel.org/lkml/ リストに投稿する前にすでにその話題がアーカイブに存在するかどうかを検索 することを是非やってください。多数の事がすでに詳細に渡って議論されてお diff --git a/Documentation/translations/ko_KR/howto.rst b/Documentation/translations/ko_KR/howto.rst index e43970584ca4..df53fafd1b10 100644 --- a/Documentation/translations/ko_KR/howto.rst +++ b/Documentation/translations/ko_KR/howto.rst @@ -386,7 +386,7 @@ https://bugzilla.kernel.org 를 체크하고자 할 수도 있다; 소수의 커 웹상의 많은 다른 곳에도 메일링 리스트의 아카이브들이 있다. 이러한 아카이브들을 찾으려면 검색 엔진을 사용하라. 예를 들어: - http://dir.gmane.org/gmane.linux.kernel + https://lore.kernel.org/lkml/ 여러분이 새로운 문제에 관해 리스트에 올리기 전에 말하고 싶은 주제에 관한 것을 아카이브에서 먼저 찾아보기를 강력히 권장한다. 이미 상세하게 토론된 많은 diff --git a/Documentation/translations/zh_CN/process/howto.rst b/Documentation/translations/zh_CN/process/howto.rst index 1455190dc087..5bf953146929 100644 --- a/Documentation/translations/zh_CN/process/howto.rst +++ b/Documentation/translations/zh_CN/process/howto.rst @@ -306,7 +306,7 @@ bugzilla.kernel.org是Linux内核开发者们用来跟踪内核Bug的网站。 网上很多地方都有这个邮件列表的存档(archive)。可以使用搜索引擎来找到这些 存档。比如： - http://dir.gmane.org/gmane.linux.kernel + https://lore.kernel.org/lkml/ 在发信之前，我们强烈建议你先在存档中搜索你想要讨论的问题。很多已经被详细 讨论过的问题只在邮件列表的存档中可以找到。 diff --git a/Documentation/translations/zh_TW/process/howto.rst b/Documentation/translations/zh_TW/process/howto.rst index 68ae4411285b..86b0d4c6d6f9 100644 --- a/Documentation/translations/zh_TW/process/howto.rst +++ b/Documentation/translations/zh_TW/process/howto.rst @@ -309,7 +309,7 @@ bugzilla.kernel.org是Linux內核開發者們用來跟蹤內核Bug的網站。 網上很多地方都有這個郵件列表的存檔(archive)。可以使用搜尋引擎來找到這些 存檔。比如： - http://dir.gmane.org/gmane.linux.kernel + https://lore.kernel.org/lkml/ 在發信之前，我們強烈建議你先在存檔中搜索你想要討論的問題。很多已經被詳細 討論過的問題只在郵件列表的存檔中可以找到。 -- cgit From 84bed8a8bf3133ace08d6fb62a4d14d129f6ff8e Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 28 Sep 2022 18:31:29 +0800 Subject: docs/zh_CN: Update the translation of ksm to 6.0-rc7 Update to commit bc6a2828a963 ("ksm: add the ksm prefix to the names of the ksm private structures") Signed-off-by: Yanteng Si Reviewed-by: Alex Shi Link: https://lore.kernel.org/r/60017007349357dc1fd8fa849a5ddb5672f8ab5b.1664360331.git.siyanteng@loongson.cn Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/mm/ksm.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/translations/zh_CN/mm/ksm.rst b/Documentation/translations/zh_CN/mm/ksm.rst index d1f82e857ad7..f0f458753d0c 100644 --- a/Documentation/translations/zh_CN/mm/ksm.rst +++ b/Documentation/translations/zh_CN/mm/ksm.rst @@ -30,7 +30,7 @@ KSM的用户空间的接口在Documentation/translations/zh_CN/admin-guide/mm/ks KSM维护着稳定树中的KSM页的逆映射信息。 当KSM页面的共享数小于 ``max_page_sharing`` 的虚拟内存区域(VMAs)时，则代表了 -KSM页的稳定树其中的节点指向了一个rmap_item结构体类型的列表。同时，这个KSM页 +KSM页的稳定树其中的节点指向了一个ksm_rmap_item结构体类型的列表。同时，这个KSM页 的 ``page->mapping`` 指向了该稳定树节点。 如果共享数超过了阈值，KSM将给稳定树添加第二个维度。稳定树就变成链接一个或多 -- cgit From 4e3ce6d04da3d1058ad887000440e81ce34c0149 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 28 Sep 2022 18:31:30 +0800 Subject: docs/zh_CN: Update the translation of page_owner to 6.0-rc7 1)Update to commit 8f0efa81dfbc ("mm/page_owner.c: add llseek for page_owner") 2)Translate some words into Chinese. Signed-off-by: Yanteng Si Reviewed-by: Alex Shi Link: https://lore.kernel.org/r/52bc8df87618af951b34759487f05775416cb4d4.1664360331.git.siyanteng@loongson.cn Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/mm/page_owner.rst | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/Documentation/translations/zh_CN/mm/page_owner.rst b/Documentation/translations/zh_CN/mm/page_owner.rst index b7f81d7a6589..21a6a0837d42 100644 --- a/Documentation/translations/zh_CN/mm/page_owner.rst +++ b/Documentation/translations/zh_CN/mm/page_owner.rst @@ -74,15 +74,19 @@ page owner在默认情况下是禁用的。所以，如果你想使用它，你 cat /sys/kernel/debug/page_owner > page_owner_full.txt ./page_owner_sort page_owner_full.txt sorted_page_owner.txt - ``page_owner_full.txt`` 的一般输出情况如下(输出信息无翻译价值):: + ``page_owner_full.txt`` 的一般输出情况如下:: Page allocated via order XXX, ... PFN XXX ... - // Detailed stack + // 栈详情 Page allocated via order XXX, ... PFN XXX ... - // Detailed stack + // 栈详情 + 默认情况下，它将以一个给定的pfn开始，做完整的pfn转储，且page_owner支持fseek。 + + FILE *fp = fopen("/sys/kernel/debug/page_owner", "r"); + fseek(fp, pfn_start, SEEK_SET); ``page_owner_sort`` 工具忽略了 ``PFN`` 行，将剩余的行放在buf中，使用regexp提 取页序值，计算buf的次数和页数，最后根据参数进行排序。 -- cgit From 46307fd6e27a3f678a1678b02e667678c22aa8cc Mon Sep 17 00:00:00 2001 From: Michal Koutný Date: Mon, 10 Oct 2022 10:29:18 +0200 Subject: cgroup: Reorganize css_set_lock and kernfs path processing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The commit 74e4b956eb1c incorrectly wrapped kernfs_walk_and_get (might_sleep) under css_set_lock (spinlock). css_set_lock is needed by __cset_cgroup_from_root to ensure stable cset->cgrp_links but not for kernfs_walk_and_get. We only need to make sure that the returned root_cgrp won't be freed under us. This is given in the case of global root because it is static (cgrp_dfl_root.cgrp). When the root_cgrp is lower in the hierarchy, it is pinned by cgroup_ns->root_cset (and `current` task cannot switch namespace asynchronously so ns_proxy pins cgroup_ns). Note this reasoning won't hold for root cgroups in v1 hierarchies, therefore create a special-cased helper function just for the default hierarchy. Fixes: 74e4b956eb1c ("cgroup: Honor caller's cgroup NS when resolving path") Reported-by: Dan Carpenter Signed-off-by: Michal Koutný Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 40 +++++++++++++++++++++++++++------------- 1 file changed, 27 insertions(+), 13 deletions(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 764bdd5fd8d1..ecf409e3c3a7 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1392,6 +1392,9 @@ static void cgroup_destroy_root(struct cgroup_root *root) cgroup_free_root(root); } +/* + * Returned cgroup is without refcount but it's valid as long as cset pins it. + */ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { @@ -1403,6 +1406,7 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, res_cgroup = cset->dfl_cgrp; } else { struct cgrp_cset_link *link; + lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; @@ -1414,6 +1418,7 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, } } + BUG_ON(!res_cgroup); return res_cgroup; } @@ -1436,23 +1441,36 @@ current_cgns_cgroup_from_root(struct cgroup_root *root) rcu_read_unlock(); - BUG_ON(!res); return res; } +/* + * Look up cgroup associated with current task's cgroup namespace on the default + * hierarchy. + * + * Unlike current_cgns_cgroup_from_root(), this doesn't need locks: + * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu + * pointers. + * - css_set_lock is not needed because we just read cset->dfl_cgrp. + * - As a bonus returned cgrp is pinned with the current because it cannot + * switch cgroup_ns asynchronously. + */ +static struct cgroup *current_cgns_cgroup_dfl(void) +{ + struct css_set *cset; + + cset = current->nsproxy->cgroup_ns->root_cset; + return __cset_cgroup_from_root(cset, &cgrp_dfl_root); +} + /* look up cgroup associated with given css_set on the specified hierarchy */ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { - struct cgroup *res = NULL; - lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); - res = __cset_cgroup_from_root(cset, root); - - BUG_ON(!res); - return res; + return __cset_cgroup_from_root(cset, root); } /* @@ -6105,9 +6123,7 @@ struct cgroup *cgroup_get_from_id(u64 id) if (!cgrp) return ERR_PTR(-ENOENT); - spin_lock_irq(&css_set_lock); - root_cgrp = current_cgns_cgroup_from_root(&cgrp_dfl_root); - spin_unlock_irq(&css_set_lock); + root_cgrp = current_cgns_cgroup_dfl(); if (!cgroup_is_descendant(cgrp, root_cgrp)) { cgroup_put(cgrp); return ERR_PTR(-ENOENT); @@ -6686,10 +6702,8 @@ struct cgroup *cgroup_get_from_path(const char *path) struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup *root_cgrp; - spin_lock_irq(&css_set_lock); - root_cgrp = current_cgns_cgroup_from_root(&cgrp_dfl_root); + root_cgrp = current_cgns_cgroup_dfl(); kn = kernfs_walk_and_get(root_cgrp->kn, path); - spin_unlock_irq(&css_set_lock); if (!kn) goto out; -- cgit From 03db7716159477b595e9af01be8003b7e994cc79 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 10 Oct 2022 11:08:17 -1000 Subject: Revert "cgroup: enable cgroup_get_from_file() on cgroup1" This reverts commit f3a2aebdd6fb90e444d595e46de64e822af419da. The commit enabled looking up v1 cgroups via cgroup_get_from_file(). However, there are multiple users, including CLONE_INTO_CGROUP, which have been assuming that it would only look up v2 cgroups. Returning v1 cgroups breaks them. Let's revert the commit and retry later with a separate lookup interface which allows both v1 and v2. Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/r/000000000000385cbf05ea3f1862@google.com Cc: Yosry Ahmed --- kernel/cgroup/cgroup.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index ecf409e3c3a7..6d8a5a40c24d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6234,6 +6234,11 @@ static struct cgroup *cgroup_get_from_file(struct file *f) return ERR_CAST(css); cgrp = css->cgroup; + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + return cgrp; } -- cgit From 6094b9136ca9038b61e9c4b5d25cd5512ce50b34 Mon Sep 17 00:00:00 2001 From: Shirish S Date: Fri, 7 Oct 2022 20:31:49 +0530 Subject: drm/amd/display: explicitly disable psr_feature_enable appropriately [Why] If psr_feature_enable is set to true by default, it continues to be enabled for non capable links. [How] explicitly disable the feature on links that are not capable of the same. Fixes: 8c322309e48e9 ("drm/amd/display: Enable PSR") Signed-off-by: Shirish S Reviewed-by: Leo Li Reviewed-by: Mario Limonciello Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 5.15+ --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c index 8ca10ab3dfc1..26291db0a3cf 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -60,11 +60,15 @@ static bool link_supports_psrsu(struct dc_link *link) */ void amdgpu_dm_set_psr_caps(struct dc_link *link) { - if (!(link->connector_signal & SIGNAL_TYPE_EDP)) + if (!(link->connector_signal & SIGNAL_TYPE_EDP)) { + link->psr_settings.psr_feature_enabled = false; return; + } - if (link->type == dc_connection_none) + if (link->type == dc_connection_none) { + link->psr_settings.psr_feature_enabled = false; return; + } if (link->dpcd_caps.psr_info.psr_version == 0) { link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED; -- cgit From 4f5bdde386d3b8e9317df5562950e1b4fa177599 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Fri, 9 Sep 2022 15:24:55 -0400 Subject: drm/amd/display: Update PMFW z-state interface for DCN314 [Why] Request from PMFW to change the messaging format to specify whether we support z-state via individual bits. [How] Update the args we pass in the support message. Fixes: d5c6909e7460 ("drm/amd/display: Add DCN314 clock manager") Tested-by: Daniel Wheeler Reviewed-by: Charlene Liu Reviewed-by: Mario Limonciello Acked-by: Qingqing Zhuo Signed-off-by: Nicholas Kazlauskas Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0 --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c | 11 +++-------- drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c | 3 ++- 2 files changed, 5 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c index 897105d1c111..ef0795b14a1f 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c @@ -339,29 +339,24 @@ void dcn314_smu_set_zstate_support(struct clk_mgr_internal *clk_mgr, enum dcn_zs if (!clk_mgr->smu_present) return; - if (!clk_mgr->base.ctx->dc->debug.enable_z9_disable_interface && - (support == DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY)) - support = DCN_ZSTATE_SUPPORT_DISALLOW; - - // Arg[15:0] = 8/9/0 for Z8/Z9/disallow -> existing bits // Arg[16] = Disallow Z9 -> new bit switch (support) { case DCN_ZSTATE_SUPPORT_ALLOW: msg_id = VBIOSSMC_MSG_AllowZstatesEntry; - param = 9; + param = (1 << 10) | (1 << 9) | (1 << 8); break; case DCN_ZSTATE_SUPPORT_DISALLOW: msg_id = VBIOSSMC_MSG_AllowZstatesEntry; - param = 8; + param = 0; break; case DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY: msg_id = VBIOSSMC_MSG_AllowZstatesEntry; - param = 0x00010008; + param = (1 << 10); break; default: //DCN_ZSTATE_SUPPORT_UNKNOWN diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 70b647b9b4d3..d0ad72caead2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -881,7 +881,8 @@ static const struct dc_plane_cap plane_cap = { }; static const struct dc_debug_options debug_defaults_drv = { - .disable_z10 = true, /*hw not support it*/ + .disable_z10 = false, + .enable_z9_disable_interface = true, .disable_dmcu = true, .force_abm_enable = false, .timing_trace = false, -- cgit From 99243fd1f3ca40d487209ac76241de0478962a9d Mon Sep 17 00:00:00 2001 From: Dillon Varone Date: Tue, 27 Sep 2022 12:35:10 -0400 Subject: Revert "drm/amd/display: skip commit minimal transition state" This reverts commit e4e481e4d838f30985dd46d43ed195110ed265f5. [Why & How] The reverted commit creates memory leak and causes issue upon driver install. Tested-by: Daniel Wheeler Reviewed-by: Martin Leung Acked-by: Qingqing Zhuo Signed-off-by: Dillon Varone Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 20 -------------------- 1 file changed, 20 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 40a34b600c8e..b5058a2ce7e8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3650,30 +3650,10 @@ static bool commit_minimal_transition_state(struct dc *dc, bool temp_subvp_policy; enum dc_status ret = DC_ERROR_UNEXPECTED; unsigned int i, j; - unsigned int pipe_in_use = 0; if (!transition_context) return false; - /* check current pipes in use*/ - for (i = 0; i < dc->res_pool->pipe_count; i++) { - struct pipe_ctx *pipe = &transition_base_context->res_ctx.pipe_ctx[i]; - - if (pipe->plane_state) - pipe_in_use++; - } - - /* When the OS add a new surface if we have been used all of pipes with odm combine - * and mpc split feature, it need use commit_minimal_transition_state to transition safely. - * After OS exit MPO, it will back to use odm and mpc split with all of pipes, we need - * call it again. Otherwise return true to skip. - * - * Reduce the scenarios to use dc_commit_state_no_check in the stage of flip. Especially - * enter/exit MPO when DCN still have enough resources. - */ - if (pipe_in_use != dc->res_pool->pipe_count) - return true; - if (!dc->config.is_vmin_only_asic) { tmp_mpc_policy = dc->debug.pipe_split_policy; dc->debug.pipe_split_policy = MPC_SPLIT_AVOID; -- cgit From eae2331899f9dcc923d37d1d753f2de847c92359 Mon Sep 17 00:00:00 2001 From: Vladimir Stempen Date: Thu, 22 Sep 2022 15:03:05 -0400 Subject: drm/amd/display: properly configure DCFCLK when enable/disable Freesync [Why] Bandwidth validation is using Freesync parameters from previous Freesync state. Bandwidth validation ignores DCFCLK calculated after Freesync parameters are configured [How] Set Freesync bandwidth parameters to its default state before running bandwidth validation. Take DCFCLK calculated after Freesync bandwidth parameters are assigned and bandwidth is recalculated. Tested-by: Daniel Wheeler Reviewed-by: Martin Leung Reviewed-by: Nevenko Stupar Reviewed-by: Jun Lei Acked-by: Qingqing Zhuo Signed-off-by: Vladimir Stempen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c | 7 +++++++ drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 7 ++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 9585b25f10e5..a88dd7b3d1c1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -1805,6 +1805,13 @@ bool dcn32_validate_bandwidth(struct dc *dc, int pipe_cnt = 0; display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL); struct mall_temp_config mall_temp_config; + + /* To handle Freesync properly, setting FreeSync DML parameters + * to its default state for the first stage of validation + */ + context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching = false; + context->bw_ctx.dml.soc.dram_clock_change_requirement_final = true; + DC_LOGGER_INIT(dc->ctx->logger); /* For fast validation, there are situations where a shallow copy of diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 6bdd509d292a..819de0f11012 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1769,6 +1769,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, int i, pipe_idx, vlevel_temp = 0; double dcfclk = dcn3_2_soc.clock_limits[0].dcfclk_mhz; double dcfclk_from_validation = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; + double dcfclk_from_fw_based_mclk_switching = dcfclk_from_validation; bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != dm_dram_clock_change_unsupported; unsigned int dummy_latency_index = 0; @@ -1804,7 +1805,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, false); maxMpcComb = context->bw_ctx.dml.vba.maxMpcComb; - dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; + dcfclk_from_fw_based_mclk_switching = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][maxMpcComb] != dm_dram_clock_change_unsupported; } @@ -1890,6 +1891,10 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, pipes[0].clks_cfg.dcfclk_mhz = dcfclk_from_validation; pipes[0].clks_cfg.socclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].socclk_mhz; + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { + pipes[0].clks_cfg.dcfclk_mhz = dcfclk_from_fw_based_mclk_switching; + } + if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) { min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed; min_dram_speed_mts_margin = 160; -- cgit From 5ff32b52995155f91de582124485d0f0f8881363 Mon Sep 17 00:00:00 2001 From: Martin Leung Date: Tue, 27 Sep 2022 18:13:38 -0400 Subject: drm/amd/display: zeromem mypipe heap struct before using it [Why & How] bug was caused when moving variable from stack to heap because it was reusable and garbage was left over, so we need to zero mem Fixes: 7acc487ab57e ("drm/amd/display: reduce stack size in dcn32 dml (v2)") Tested-by: Daniel Wheeler Reviewed-by: Rodrigo Siqueira Acked-by: Qingqing Zhuo Signed-off-by: Martin Leung Cc: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 11d5750e15af..5b91660a6496 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -733,6 +733,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman mode_lib->vba.FCLKChangeLatency, v->UrgentLatency, mode_lib->vba.SREnterPlusExitTime); + memset(&v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe, 0, sizeof(DmlPipe)); + v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.Dppclk = mode_lib->vba.DPPCLK[k]; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.Dispclk = mode_lib->vba.DISPCLK; v->dummy_vars.DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation.myPipe.PixelClock = mode_lib->vba.PixelClock[k]; -- cgit From 2fd23d467d4fb4e9bb3c3758ee49799f690f5f72 Mon Sep 17 00:00:00 2001 From: Josip Pavic Date: Fri, 23 Sep 2022 15:29:07 -0400 Subject: drm/amd/display: do not compare integers of different widths [Why & How] Increase width of some variables to avoid comparing integers of different widths Reviewed-by: Alvin Lee Tested-by: Daniel Wheeler Acked-by: Qingqing Zhuo Signed-off-by: Josip Pavic Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 955ca273cfe1..426b07edb426 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -206,8 +206,7 @@ static bool dcn32_check_no_memory_request_for_cab(struct dc *dc) */ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *ctx) { - uint8_t i; - int j; + int i, j; struct dc_stream_state *stream = NULL; struct dc_plane_state *plane = NULL; uint32_t cursor_size = 0; -- cgit From c19d3eace484ca5627817a1de85af1de06d538b6 Mon Sep 17 00:00:00 2001 From: Dillon Varone Date: Wed, 28 Sep 2022 16:33:47 -0400 Subject: drm/amd/display: Use correct pixel clock to program DTBCLK DTO's [Why?] Currently phy_pix_clk is used to program DTO's which is incorrect. [How?] Use the timing pixel clock to program DTO's correctly. Reviewed-by: Martin Leung Tested-by: Daniel Wheeler Acked-by: Qingqing Zhuo Signed-off-by: Dillon Varone Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c index 7d3147175ca2..153a88381f2c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_hwss_hpo_dp.c @@ -111,7 +111,7 @@ static void setup_hpo_dp_stream_encoder(struct pipe_ctx *pipe_ctx) enum phyd32clk_clock_source phyd32clk = get_phyd32clk_src(pipe_ctx->stream->link); dto_params.otg_inst = tg->inst; - dto_params.pixclk_khz = pipe_ctx->stream->phy_pix_clk; + dto_params.pixclk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10; dto_params.num_odm_segments = get_odm_segment_count(pipe_ctx); dto_params.timing = &pipe_ctx->stream->timing; dto_params.ref_dtbclk_khz = dc->clk_mgr->funcs->get_dtb_ref_clk_frequency(dc->clk_mgr); -- cgit From e50f67cf5e168d92e24cfb61fb11f2f0a35708cd Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Thu, 29 Sep 2022 11:15:12 -0400 Subject: drm/amd/display: Do not trigger timing sync for phantom pipes [Why&How] Doing timing sync seqence for phantom pipes will not go through since they are not fully programmed like normal pipes. Skip the sequence on such pipes Tested-by: Daniel Wheeler Reviewed-by: Alvin Lee Acked-by: Qingqing Zhuo Signed-off-by: Aurabindo Pillai Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 26 +++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index f4b3ec32a331..305e0c545374 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -2244,6 +2244,9 @@ void dcn10_enable_timing_synchronization( DC_SYNC_INFO("Setting up OTG reset trigger\n"); for (i = 1; i < group_size; i++) { + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + opp = grouped_pipes[i]->stream_res.opp; tg = grouped_pipes[i]->stream_res.tg; tg->funcs->get_otg_active_size(tg, &width, &height); @@ -2254,13 +2257,21 @@ void dcn10_enable_timing_synchronization( for (i = 0; i < group_size; i++) { if (grouped_pipes[i]->stream == NULL) continue; + + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + grouped_pipes[i]->stream->vblank_synchronized = false; } - for (i = 1; i < group_size; i++) + for (i = 1; i < group_size; i++) { + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + grouped_pipes[i]->stream_res.tg->funcs->enable_reset_trigger( grouped_pipes[i]->stream_res.tg, grouped_pipes[0]->stream_res.tg->inst); + } DC_SYNC_INFO("Waiting for trigger\n"); @@ -2268,12 +2279,21 @@ void dcn10_enable_timing_synchronization( * synchronized. Look at last pipe programmed to reset. */ - wait_for_reset_trigger_to_occur(dc_ctx, grouped_pipes[1]->stream_res.tg); - for (i = 1; i < group_size; i++) + if (grouped_pipes[1]->stream && grouped_pipes[1]->stream->mall_stream_config.type != SUBVP_PHANTOM) + wait_for_reset_trigger_to_occur(dc_ctx, grouped_pipes[1]->stream_res.tg); + + for (i = 1; i < group_size; i++) { + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + grouped_pipes[i]->stream_res.tg->funcs->disable_reset_trigger( grouped_pipes[i]->stream_res.tg); + } for (i = 1; i < group_size; i++) { + if (grouped_pipes[i]->stream && grouped_pipes[i]->stream->mall_stream_config.type == SUBVP_PHANTOM) + continue; + opp = grouped_pipes[i]->stream_res.opp; tg = grouped_pipes[i]->stream_res.tg; tg->funcs->get_otg_active_size(tg, &width, &height); -- cgit From fa28030a83a6302f8724cdbf0c477536b2101033 Mon Sep 17 00:00:00 2001 From: Vladimir Stempen Date: Thu, 29 Sep 2022 13:32:50 -0400 Subject: drm/amd/display: increase hardware status wait time [Why] Diagnostics reports exceptions generated when timeout waiting for DISPCLK frequency divider change expires when testing ODM4to1. Diagnostics reports exceptions generated when timeout waiting for OTG busy status expires when disabling OTG during ODM4to1 test. [How] Increase HW status waiting time for DISPCLK frequency divider change and OTG busy status when disable OTG. Tested-by: Daniel Wheeler Reviewed-by: Ariel Bernstein Acked-by: Qingqing Zhuo Signed-off-by: Vladimir Stempen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c | 4 ++-- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c index 0d30d1d9d67e..650f3b4b562e 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c @@ -179,7 +179,7 @@ void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr, struct } else if (dispclk_wdivider == 127 && current_dispclk_wdivider != 127) { REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, 126); - REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 100); + REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 2000); for (i = 0; i < clk_mgr->base.ctx->dc->res_pool->pipe_count; i++) { struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; struct dccg *dccg = clk_mgr->base.ctx->dc->res_pool->dccg; @@ -206,7 +206,7 @@ void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr, struct REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, dispclk_wdivider); - REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 1000); + REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 2000); REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, dppclk_wdivider); REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, 1, 5, 100); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c index ec3989d37086..2b33eeb213e2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_optc.c @@ -151,7 +151,7 @@ static bool optc32_disable_crtc(struct timing_generator *optc) /* CRTC disabled, so disable clock. */ REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, - 1, 100000); + 1, 150000); return true; } -- cgit From 20dad3813b3c15d118bda0496711eb7dff98e74a Mon Sep 17 00:00:00 2001 From: Jun Lei Date: Thu, 29 Sep 2022 15:47:31 -0400 Subject: drm/amd/display: Add a helper to map ODM/MPC/Multi-Plane resources [Why & How] Add a helper to map ODM/MPC/Multi-Plane resources from DC Tested-by: Daniel Wheeler Reviewed-by: Nevenko Stupar Reviewed-by: Chaitanya Dhere Acked-by: Qingqing Zhuo Signed-off-by: Jun Lei Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 49 +++++++++++++++++++++- drivers/gpu/drm/amd/display/dc/dc.h | 2 + .../gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 2 +- drivers/gpu/drm/amd/display/dc/inc/core_types.h | 4 ++ drivers/gpu/drm/amd/display/dc/inc/resource.h | 6 +++ 5 files changed, 61 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 8ee0d946bb2f..4a6e867369b8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1747,7 +1747,6 @@ bool dc_remove_plane_from_context( for (i = 0; i < stream_status->plane_count; i++) { if (stream_status->plane_states[i] == plane_state) { - dc_plane_state_release(stream_status->plane_states[i]); break; } @@ -3683,4 +3682,52 @@ bool is_h_timing_divisible_by_2(struct dc_stream_state *stream) (stream->timing.h_sync_width % 2 == 0); } return divisible; +} + +bool dc_resource_acquire_secondary_pipe_for_mpc_odm( + const struct dc *dc, + struct dc_state *state, + struct pipe_ctx *pri_pipe, + struct pipe_ctx *sec_pipe, + bool odm) +{ + int pipe_idx = sec_pipe->pipe_idx; + struct pipe_ctx *sec_top, *sec_bottom, *sec_next, *sec_prev; + const struct resource_pool *pool = dc->res_pool; + + sec_top = sec_pipe->top_pipe; + sec_bottom = sec_pipe->bottom_pipe; + sec_next = sec_pipe->next_odm_pipe; + sec_prev = sec_pipe->prev_odm_pipe; + + *sec_pipe = *pri_pipe; + + sec_pipe->top_pipe = sec_top; + sec_pipe->bottom_pipe = sec_bottom; + sec_pipe->next_odm_pipe = sec_next; + sec_pipe->prev_odm_pipe = sec_prev; + + sec_pipe->pipe_idx = pipe_idx; + sec_pipe->plane_res.mi = pool->mis[pipe_idx]; + sec_pipe->plane_res.hubp = pool->hubps[pipe_idx]; + sec_pipe->plane_res.ipp = pool->ipps[pipe_idx]; + sec_pipe->plane_res.xfm = pool->transforms[pipe_idx]; + sec_pipe->plane_res.dpp = pool->dpps[pipe_idx]; + sec_pipe->plane_res.mpcc_inst = pool->dpps[pipe_idx]->inst; + sec_pipe->stream_res.dsc = NULL; + if (odm) { + if (!sec_pipe->top_pipe) + sec_pipe->stream_res.opp = pool->opps[pipe_idx]; + else + sec_pipe->stream_res.opp = sec_pipe->top_pipe->stream_res.opp; + if (sec_pipe->stream->timing.flags.DSC == 1) { + dcn20_acquire_dsc(dc, &state->res_ctx, &sec_pipe->stream_res.dsc, pipe_idx); + ASSERT(sec_pipe->stream_res.dsc); + if (sec_pipe->stream_res.dsc == NULL) + return false; + } + dcn20_build_mapped_resource(dc, state, sec_pipe->stream); + } + + return true; } \ No newline at end of file diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 66b7482d2e72..b0afcff94591 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1191,6 +1191,8 @@ struct dc_plane_state { enum dc_irq_source irq_source; struct kref refcount; struct tg_color visual_confirm_color; + + bool is_statically_allocated; }; struct dc_plane_info { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 819de0f11012..2a3f5a485b2b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1372,7 +1372,7 @@ static struct pipe_ctx *dcn32_find_split_pipe( return pipe; } -static bool dcn32_split_stream_for_mpc_or_odm( +bool dcn32_split_stream_for_mpc_or_odm( const struct dc *dc, struct resource_context *res_ctx, struct pipe_ctx *pri_pipe, diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 1fd7ad853210..9498105c98ab 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -39,6 +39,8 @@ #include "panel_cntl.h" #define MAX_CLOCK_SOURCES 7 +#define MAX_SVP_PHANTOM_STREAMS 2 +#define MAX_SVP_PHANTOM_PLANES 2 void enable_surface_flip_reporting(struct dc_plane_state *plane_state, uint32_t controller_id); @@ -492,6 +494,8 @@ struct dcn_bw_output { struct dcn_watermark_set watermarks; struct dcn_bw_writeback bw_writeback; int compbuf_size_kb; + unsigned int legacy_svp_drr_stream_index; + bool legacy_svp_drr_stream_index_valid; }; union bw_output { diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index c37d1141febe..5040836f404d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -230,4 +230,10 @@ const struct link_hwss *get_link_hwss(const struct dc_link *link, bool is_h_timing_divisible_by_2(struct dc_stream_state *stream); +bool dc_resource_acquire_secondary_pipe_for_mpc_odm( + const struct dc *dc, + struct dc_state *state, + struct pipe_ctx *pri_pipe, + struct pipe_ctx *sec_pipe, + bool odm); #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_RESOURCE_H_ */ -- cgit From 876fcc4222e1d0e5b73343f4010a8b66be058f48 Mon Sep 17 00:00:00 2001 From: Fangzhi Zuo Date: Tue, 30 Aug 2022 12:12:53 -0400 Subject: drm/amd/display: Validate DSC After Enable All New CRTCs Before enabling new crtc, stream_count in dc_state does not sync with that in drm_atomic_state. Validating dsc in such case would leave newly added stream not jointly participating in dsc optimization with existing streams, but simply using default initialized vcpi all the time which gives wrong dsc determination decision. Consider the scenaio where one 4k60 connected to the dock under dp-alt mode. Since dp-alt mode is 2-lane setup, stream 1 consumes 63 slots with dsc needed. Then hook up a second 4k60 to the dock. stream 2 connected with 65 slot initialized by default without dsc. dsc pre validate will not jointly optimize stream 2 with stream 1 before crtc 2 added into the dc_state. That leads to stream 2 not getting dsc optimization, and trigger atomic_check failure all the time, as 65 > 63 limit. After getting all new crtcs added into the state, stream_count in dc_state correctly reflect that in drm_atomic_state which comes up with correct dsc decision. Fixes: 71be4b16d39a ("drm/amd/display: dsc validate fail not pass to atomic check") Tested-by: Daniel Wheeler Reviewed-by: Roman Li Acked-by: Qingqing Zhuo Signed-off-by: Fangzhi Zuo Tested-by: Mark Broadworth Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b84aedb707b8..f6a9e8fdd87d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9390,10 +9390,6 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, } } } - if (!pre_validate_dsc(state, &dm_state, vars)) { - ret = -EINVAL; - goto fail; - } } #endif for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { @@ -9527,6 +9523,15 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, } } +#if defined(CONFIG_DRM_AMD_DC_DCN) + if (dc_resource_is_dsc_encoding_supported(dc)) { + if (!pre_validate_dsc(state, &dm_state, vars)) { + ret = -EINVAL; + goto fail; + } + } +#endif + /* Run this here since we want to validate the streams we created */ ret = drm_atomic_helper_check_planes(dev, state); if (ret) { -- cgit From d6170e418d1d3ae7e98cb6d96d1444e880131bbf Mon Sep 17 00:00:00 2001 From: Dillon Varone Date: Wed, 28 Sep 2022 15:44:38 -0400 Subject: drm/amd/display: Acquire FCLK DPM levels on DCN32 [Why & How] Acquire FCLK DPM levels to properly construct DML clock limits. Further add new logic to keep number of indices for each clock in clk_mgr. Tested-by: Daniel Wheeler Reviewed-by: Jun Lei Acked-by: Qingqing Zhuo Signed-off-by: Dillon Varone Signed-off-by: Alex Deucher --- .../amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c | 41 ++++++++++++++-------- drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h | 15 +++++++- 2 files changed, 41 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index 96d5e0d5b3ce..99ae3255dcb9 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -156,7 +156,7 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) { struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); unsigned int num_levels; - unsigned int num_dcfclk_levels, num_dtbclk_levels, num_dispclk_levels; + struct clk_limit_num_entries *num_entries_per_clk = &clk_mgr_base->bw_params->clk_table.num_entries_per_clk; memset(&(clk_mgr_base->clks), 0, sizeof(struct dc_clocks)); clk_mgr_base->clks.p_state_change_support = true; @@ -180,27 +180,28 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) /* DCFCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_DCFCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dcfclk_mhz, - &num_levels); - num_dcfclk_levels = num_levels; + &num_entries_per_clk->num_dcfclk_levels); /* SOCCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_SOCCLK, &clk_mgr_base->bw_params->clk_table.entries[0].socclk_mhz, - &num_levels); + &num_entries_per_clk->num_socclk_levels); + /* DTBCLK */ if (!clk_mgr->base.ctx->dc->debug.disable_dtb_ref_clk_switch) dcn32_init_single_clock(clk_mgr, PPCLK_DTBCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz, - &num_levels); - num_dtbclk_levels = num_levels; + &num_entries_per_clk->num_dtbclk_levels); /* DISPCLK */ dcn32_init_single_clock(clk_mgr, PPCLK_DISPCLK, &clk_mgr_base->bw_params->clk_table.entries[0].dispclk_mhz, - &num_levels); - num_dispclk_levels = num_levels; + &num_entries_per_clk->num_dispclk_levels); + num_levels = num_entries_per_clk->num_dispclk_levels; - if (num_dcfclk_levels && num_dtbclk_levels && num_dispclk_levels) + if (num_entries_per_clk->num_dcfclk_levels && + num_entries_per_clk->num_dtbclk_levels && + num_entries_per_clk->num_dispclk_levels) clk_mgr->dpm_present = true; if (clk_mgr_base->ctx->dc->debug.min_disp_clk_khz) { @@ -383,7 +384,7 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, /* to disable P-State switching, set UCLK min = max */ if (!clk_mgr_base->clks.p_state_change_support) dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, - clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries - 1].memclk_mhz); + clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1].memclk_mhz); } /* Always update saved value, even if new value not set due to P-State switching unsupported. Also check safe_to_lower for FCLK */ @@ -634,7 +635,7 @@ static void dcn32_set_hard_min_memclk(struct clk_mgr *clk_mgr_base, bool current khz_to_mhz_ceil(clk_mgr_base->clks.dramclk_khz)); else dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, - clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries - 1].memclk_mhz); + clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1].memclk_mhz); } else { dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, clk_mgr_base->bw_params->clk_table.entries[0].memclk_mhz); @@ -650,22 +651,34 @@ static void dcn32_set_hard_max_memclk(struct clk_mgr *clk_mgr_base) return; dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, - clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries - 1].memclk_mhz); + clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1].memclk_mhz); } /* Get current memclk states, update bounding box */ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base) { struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); + struct clk_limit_num_entries *num_entries_per_clk = &clk_mgr_base->bw_params->clk_table.num_entries_per_clk; unsigned int num_levels; if (!clk_mgr->smu_present) return; - /* Refresh memclk states */ + /* Refresh memclk and fclk states */ dcn32_init_single_clock(clk_mgr, PPCLK_UCLK, &clk_mgr_base->bw_params->clk_table.entries[0].memclk_mhz, - &num_levels); + &num_entries_per_clk->num_memclk_levels); + + dcn32_init_single_clock(clk_mgr, PPCLK_FCLK, + &clk_mgr_base->bw_params->clk_table.entries[0].fclk_mhz, + &num_entries_per_clk->num_fclk_levels); + + if (num_entries_per_clk->num_memclk_levels >= num_entries_per_clk->num_fclk_levels) { + num_levels = num_entries_per_clk->num_memclk_levels; + } else { + num_levels = num_entries_per_clk->num_fclk_levels; + } + clk_mgr_base->bw_params->clk_table.num_entries = num_levels ? num_levels : 1; if (clk_mgr->dpm_present && !num_levels) diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h index d9f1b0a4fbd4..591ab1389e3b 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h @@ -95,10 +95,23 @@ struct clk_limit_table_entry { unsigned int wck_ratio; }; +struct clk_limit_num_entries { + unsigned int num_dcfclk_levels; + unsigned int num_fclk_levels; + unsigned int num_memclk_levels; + unsigned int num_socclk_levels; + unsigned int num_dtbclk_levels; + unsigned int num_dispclk_levels; + unsigned int num_dppclk_levels; + unsigned int num_phyclk_levels; + unsigned int num_phyclk_d18_levels; +}; + /* This table is contiguous */ struct clk_limit_table { struct clk_limit_table_entry entries[MAX_NUM_DPM_LVL]; - unsigned int num_entries; + struct clk_limit_num_entries num_entries_per_clk; + unsigned int num_entries; /* highest populated dpm level for back compatibility */ }; struct wm_range_table_entry { -- cgit From 3867bbd44f2894a4e2b01286b3b378c058992cd7 Mon Sep 17 00:00:00 2001 From: Dillon Varone Date: Sat, 1 Oct 2022 11:51:48 -0400 Subject: drm/amd/display: Fix bug preventing FCLK Pstate allow message being sent [Why & How] FCLK pstate allow message should not be dependent on local "update_fclk". Tested-by: Daniel Wheeler Reviewed-by: Martin Leung Acked-by: Qingqing Zhuo Signed-off-by: Dillon Varone Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index 99ae3255dcb9..1c612ccf1944 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -342,8 +342,8 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base, if (should_update_pstate_support(safe_to_lower, fclk_p_state_change_support, clk_mgr_base->clks.fclk_p_state_change_support)) { clk_mgr_base->clks.fclk_p_state_change_support = fclk_p_state_change_support; - /* To enable FCLK P-state switching, send FCLK_PSTATE_NOTSUPPORTED message to PMFW */ - if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && clk_mgr_base->clks.fclk_p_state_change_support && update_fclk) { + /* To enable FCLK P-state switching, send FCLK_PSTATE_SUPPORTED message to PMFW */ + if (clk_mgr_base->ctx->dce_version != DCN_VERSION_3_21 && clk_mgr_base->clks.fclk_p_state_change_support) { /* Handle the code for sending a message to PMFW that FCLK P-state change is supported */ dcn32_smu_send_fclk_pstate_message(clk_mgr, FCLK_PSTATE_SUPPORTED); } -- cgit From b73353f7f3d434e90da9f0e127bba1fe26cb1287 Mon Sep 17 00:00:00 2001 From: Max Tseng Date: Sun, 2 Oct 2022 20:45:37 +0800 Subject: drm/amd/display: Use the same cursor info across features Since different features would need to update cursor registers, However, they would use different approaches. To unify varied methods, this refactor is implemented the same update cursor info method for current varied features. Tested-by: Daniel Wheeler Reviewed-by: Anthony Koo Reviewed-by: Jun Lei Acked-by: Qingqing Zhuo Signed-off-by: Max Tseng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 4 + drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c | 145 +++++++++++++++++++++ drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h | 1 + drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c | 1 + .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 141 -------------------- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c | 30 +++++ drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c | 4 + .../drm/amd/display/dc/inc/hw/cursor_reg_cache.h | 98 ++++++++++++++ drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h | 4 + drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h | 5 + drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 115 +++++++++++++++- 11 files changed, 400 insertions(+), 148 deletions(-) create mode 100644 drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index ae13887756bf..9998f58c14b9 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -276,6 +276,8 @@ static void program_cursor_attributes( } dc->hwss.set_cursor_attribute(pipe_ctx); + + dc_send_update_cursor_info_to_dmu(pipe_ctx, i); if (dc->hwss.set_cursor_sdr_white_level) dc->hwss.set_cursor_sdr_white_level(pipe_ctx); } @@ -382,6 +384,8 @@ static void program_cursor_position( } dc->hwss.set_cursor_position(pipe_ctx); + + dc_send_update_cursor_info_to_dmu(pipe_ctx, i); } if (pipe_to_program) diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index 89d7d3fd3321..bbde635c56fc 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -30,6 +30,7 @@ #include "dc_hw_types.h" #include "core_types.h" #include "../basics/conversion.h" +#include "cursor_reg_cache.h" #define CTX dc_dmub_srv->ctx #define DC_LOGGER CTX->logger @@ -880,3 +881,147 @@ void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv) diag_data.is_cw0_enabled, diag_data.is_cw6_enabled); } + +static bool dc_dmub_should_update_cursor_data(struct pipe_ctx *pipe_ctx) +{ + if (pipe_ctx->plane_state != NULL) { + if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) + return false; + } + + if ((pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1 || + pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) && + pipe_ctx->stream->ctx->dce_version >= DCN_VERSION_3_1) + return true; + + return false; +} + +static void dc_build_cursor_update_payload0( + struct pipe_ctx *pipe_ctx, uint8_t p_idx, + struct dmub_cmd_update_cursor_payload0 *payload) +{ + struct hubp *hubp = pipe_ctx->plane_res.hubp; + unsigned int panel_inst = 0; + + if (!dc_get_edp_link_panel_inst(hubp->ctx->dc, + pipe_ctx->stream->link, &panel_inst)) + return; + + /* Payload: Cursor Rect is built from position & attribute + * x & y are obtained from postion + */ + payload->cursor_rect.x = hubp->cur_rect.x; + payload->cursor_rect.y = hubp->cur_rect.y; + /* w & h are obtained from attribute */ + payload->cursor_rect.width = hubp->cur_rect.w; + payload->cursor_rect.height = hubp->cur_rect.h; + + payload->enable = hubp->pos.cur_ctl.bits.cur_enable; + payload->pipe_idx = p_idx; + payload->cmd_version = DMUB_CMD_PSR_CONTROL_VERSION_1; + payload->panel_inst = panel_inst; +} + +static void dc_send_cmd_to_dmu(struct dc_dmub_srv *dmub_srv, + union dmub_rb_cmd *cmd) +{ + dc_dmub_srv_cmd_queue(dmub_srv, cmd); + dc_dmub_srv_cmd_execute(dmub_srv); + dc_dmub_srv_wait_idle(dmub_srv); +} + +static void dc_build_cursor_position_update_payload0( + struct dmub_cmd_update_cursor_payload0 *pl, const uint8_t p_idx, + const struct hubp *hubp, const struct dpp *dpp) +{ + /* Hubp */ + pl->position_cfg.pHubp.cur_ctl.raw = hubp->pos.cur_ctl.raw; + pl->position_cfg.pHubp.position.raw = hubp->pos.position.raw; + pl->position_cfg.pHubp.hot_spot.raw = hubp->pos.hot_spot.raw; + pl->position_cfg.pHubp.dst_offset.raw = hubp->pos.dst_offset.raw; + + /* dpp */ + pl->position_cfg.pDpp.cur0_ctl.raw = dpp->pos.cur0_ctl.raw; + pl->position_cfg.pipe_idx = p_idx; +} + +static void dc_build_cursor_attribute_update_payload1( + struct dmub_cursor_attributes_cfg *pl_A, const uint8_t p_idx, + const struct hubp *hubp, const struct dpp *dpp) +{ + /* Hubp */ + pl_A->aHubp.SURFACE_ADDR_HIGH = hubp->att.SURFACE_ADDR_HIGH; + pl_A->aHubp.SURFACE_ADDR = hubp->att.SURFACE_ADDR; + pl_A->aHubp.cur_ctl.raw = hubp->att.cur_ctl.raw; + pl_A->aHubp.size.raw = hubp->att.size.raw; + pl_A->aHubp.settings.raw = hubp->att.settings.raw; + + /* dpp */ + pl_A->aDpp.cur0_ctl.raw = dpp->att.cur0_ctl.raw; +} + +/** + * *************************************************************************************** + * dc_send_update_cursor_info_to_dmu: Populate the DMCUB Cursor update info command + * + * This function would store the cursor related information and pass it into dmub + * + * @param [in] pCtx: pipe context + * @param [in] pipe_idx: pipe index + * + * @return: void + * + * *************************************************************************************** + */ + +void dc_send_update_cursor_info_to_dmu( + struct pipe_ctx *pCtx, uint8_t pipe_idx) +{ + union dmub_rb_cmd cmd = { 0 }; + union dmub_cmd_update_cursor_info_data *update_cursor_info = + &cmd.update_cursor_info.update_cursor_info_data; + + if (!dc_dmub_should_update_cursor_data(pCtx)) + return; + /* + * Since we use multi_cmd_pending for dmub command, the 2nd command is + * only assigned to store cursor attributes info. + * 1st command can view as 2 parts, 1st is for PSR/Replay data, the other + * is to store cursor position info. + * + * Command heaer type must be the same type if using multi_cmd_pending. + * Besides, while process 2nd command in DMU, the sub type is useless. + * So it's meanless to pass the sub type header with different type. + */ + + { + /* Build Payload#0 Header */ + cmd.update_cursor_info.header.type = DMUB_CMD__UPDATE_CURSOR_INFO; + cmd.update_cursor_info.header.payload_bytes = + sizeof(cmd.update_cursor_info.update_cursor_info_data); + cmd.update_cursor_info.header.multi_cmd_pending = 1; /* To combine multi dmu cmd, 1st cmd */ + + /* Prepare Payload */ + dc_build_cursor_update_payload0(pCtx, pipe_idx, &update_cursor_info->payload0); + + dc_build_cursor_position_update_payload0(&update_cursor_info->payload0, pipe_idx, + pCtx->plane_res.hubp, pCtx->plane_res.dpp); + /* Send update_curosr_info to queue */ + dc_dmub_srv_cmd_queue(pCtx->stream->ctx->dmub_srv, &cmd); + } + { + /* Build Payload#1 Header */ + memset(update_cursor_info, 0, sizeof(union dmub_cmd_update_cursor_info_data)); + cmd.update_cursor_info.header.type = DMUB_CMD__UPDATE_CURSOR_INFO; + cmd.update_cursor_info.header.payload_bytes = sizeof(struct cursor_attributes_cfg); + cmd.update_cursor_info.header.multi_cmd_pending = 0; /* Indicate it's the last command. */ + + dc_build_cursor_attribute_update_payload1( + &cmd.update_cursor_info.update_cursor_info_data.payload1.attribute_cfg, + pipe_idx, pCtx->plane_res.hubp, pCtx->plane_res.dpp); + + /* Combine 2nd cmds update_curosr_info to DMU */ + dc_send_cmd_to_dmu(pCtx->stream->ctx->dmub_srv, &cmd); + } +} diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h index 7e438345b1a8..d34f5563df2e 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h @@ -88,4 +88,5 @@ bool dc_dmub_srv_get_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv, struct dmu void dc_dmub_setup_subvp_dmub_command(struct dc *dc, struct dc_state *context, bool enable); void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv); +void dc_send_update_cursor_info_to_dmu(struct pipe_ctx *pCtx, uint8_t pipe_idx); #endif /* _DMUB_DC_SRV_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c index 897f412f539e..b9765b3899e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c @@ -469,6 +469,7 @@ void dpp1_set_cursor_position( REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, cur_en); + dpp_base->pos.cur0_ctl.bits.cur0_enable = cur_en; } void dpp1_cnv_set_optional_cursor_attributes( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 305e0c545374..11e4c4e46947 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3372,127 +3372,6 @@ static bool dcn10_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx) return false; } -static bool dcn10_dmub_should_update_cursor_data( - struct pipe_ctx *pipe_ctx, - struct dc_debug_options *debug) -{ - if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) - return false; - - if (dcn10_can_pipe_disable_cursor(pipe_ctx)) - return false; - - if ((pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_SU_1 || pipe_ctx->stream->link->psr_settings.psr_version == DC_PSR_VERSION_1) - && pipe_ctx->stream->ctx->dce_version >= DCN_VERSION_3_1) - return true; - - return false; -} - -static void dcn10_dmub_update_cursor_data( - struct pipe_ctx *pipe_ctx, - struct hubp *hubp, - const struct dc_cursor_mi_param *param, - const struct dc_cursor_position *cur_pos, - const struct dc_cursor_attributes *cur_attr) -{ - union dmub_rb_cmd cmd; - struct dmub_cmd_update_cursor_info_data *update_cursor_info; - const struct dc_cursor_position *pos; - const struct dc_cursor_attributes *attr; - int src_x_offset = 0; - int src_y_offset = 0; - int x_hotspot = 0; - int cursor_height = 0; - int cursor_width = 0; - uint32_t cur_en = 0; - unsigned int panel_inst = 0; - - struct dc_debug_options *debug = &hubp->ctx->dc->debug; - - if (!dcn10_dmub_should_update_cursor_data(pipe_ctx, debug)) - return; - /** - * if cur_pos == NULL means the caller is from cursor_set_attribute - * then driver use previous cursor position data - * if cur_attr == NULL means the caller is from cursor_set_position - * then driver use previous cursor attribute - * if cur_pos or cur_attr is not NULL then update it - */ - if (cur_pos != NULL) - pos = cur_pos; - else - pos = &hubp->curs_pos; - - if (cur_attr != NULL) - attr = cur_attr; - else - attr = &hubp->curs_attr; - - if (!dc_get_edp_link_panel_inst(hubp->ctx->dc, pipe_ctx->stream->link, &panel_inst)) - return; - - src_x_offset = pos->x - pos->x_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->y_hotspot - param->viewport.y; - x_hotspot = pos->x_hotspot; - cursor_height = (int)attr->height; - cursor_width = (int)attr->width; - cur_en = pos->enable ? 1:0; - - // Rotated cursor width/height and hotspots tweaks for offset calculation - if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) { - swap(cursor_height, cursor_width); - if (param->rotation == ROTATION_ANGLE_90) { - src_x_offset = pos->x - pos->y_hotspot - param->viewport.x; - src_y_offset = pos->y - pos->x_hotspot - param->viewport.y; - } - } else if (param->rotation == ROTATION_ANGLE_180) { - src_x_offset = pos->x - param->viewport.x; - src_y_offset = pos->y - param->viewport.y; - } - - if (param->mirror) { - x_hotspot = param->viewport.width - x_hotspot; - src_x_offset = param->viewport.x + param->viewport.width - src_x_offset; - } - - if (src_x_offset >= (int)param->viewport.width) - cur_en = 0; /* not visible beyond right edge*/ - - if (src_x_offset + cursor_width <= 0) - cur_en = 0; /* not visible beyond left edge*/ - - if (src_y_offset >= (int)param->viewport.height) - cur_en = 0; /* not visible beyond bottom edge*/ - - if (src_y_offset + cursor_height <= 0) - cur_en = 0; /* not visible beyond top edge*/ - - // Cursor bitmaps have different hotspot values - // There's a possibility that the above logic returns a negative value, so we clamp them to 0 - if (src_x_offset < 0) - src_x_offset = 0; - if (src_y_offset < 0) - src_y_offset = 0; - - memset(&cmd, 0x0, sizeof(cmd)); - cmd.update_cursor_info.header.type = DMUB_CMD__UPDATE_CURSOR_INFO; - cmd.update_cursor_info.header.payload_bytes = - sizeof(cmd.update_cursor_info.update_cursor_info_data); - update_cursor_info = &cmd.update_cursor_info.update_cursor_info_data; - update_cursor_info->cursor_rect.x = src_x_offset + param->viewport.x; - update_cursor_info->cursor_rect.y = src_y_offset + param->viewport.y; - update_cursor_info->cursor_rect.width = attr->width; - update_cursor_info->cursor_rect.height = attr->height; - update_cursor_info->enable = cur_en; - update_cursor_info->pipe_idx = pipe_ctx->pipe_idx; - update_cursor_info->cmd_version = DMUB_CMD_PSR_CONTROL_VERSION_1; - update_cursor_info->panel_inst = panel_inst; - dc_dmub_srv_cmd_queue(pipe_ctx->stream->ctx->dmub_srv, &cmd); - dc_dmub_srv_cmd_execute(pipe_ctx->stream->ctx->dmub_srv); - dc_dmub_srv_wait_idle(pipe_ctx->stream->ctx->dmub_srv); -} - void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) { struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position; @@ -3727,7 +3606,6 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.y; } - dcn10_dmub_update_cursor_data(pipe_ctx, hubp, ¶m, &pos_cpy, NULL); hubp->funcs->set_cursor_position(hubp, &pos_cpy, ¶m); dpp->funcs->set_cursor_position(dpp, &pos_cpy, ¶m, hubp->curs_attr.width, hubp->curs_attr.height); } @@ -3735,25 +3613,6 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx) { struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes; - struct dc_cursor_mi_param param = { 0 }; - - /** - * If enter PSR without cursor attribute update - * the cursor attribute of dmub_restore_plane - * are initial value. call dmub to exit PSR and - * restore plane then update cursor attribute to - * avoid override with initial value - */ - if (pipe_ctx->plane_state != NULL) { - param.pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_100hz / 10; - param.ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clocks.dchub_ref_clock_inKhz; - param.viewport = pipe_ctx->plane_res.scl_data.viewport; - param.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz; - param.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert; - param.rotation = pipe_ctx->plane_state->rotation; - param.mirror = pipe_ctx->plane_state->horizontal_mirror; - dcn10_dmub_update_cursor_data(pipe_ctx, pipe_ctx->plane_res.hubp, ¶m, NULL, attributes); - } pipe_ctx->plane_res.hubp->funcs->set_cursor_attributes( pipe_ctx->plane_res.hubp, attributes); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index b1ec0e6f7f58..4996d2810edb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -617,6 +617,17 @@ void hubp2_cursor_set_attributes( CURSOR0_DST_Y_OFFSET, 0, /* used to shift the cursor chunk request deadline */ CURSOR0_CHUNK_HDL_ADJUST, 3); + + hubp->att.SURFACE_ADDR_HIGH = attr->address.high_part; + hubp->att.SURFACE_ADDR = attr->address.low_part; + hubp->att.size.bits.width = attr->width; + hubp->att.size.bits.height = attr->height; + hubp->att.cur_ctl.bits.mode = attr->color_format; + hubp->att.cur_ctl.bits.pitch = hw_pitch; + hubp->att.cur_ctl.bits.line_per_chunk = lpc; + hubp->att.cur_ctl.bits.cur_2x_magnify = attr->attribute_flags.bits.ENABLE_MAGNIFICATION; + hubp->att.settings.bits.dst_y_offset = 0; + hubp->att.settings.bits.chunk_hdl_adjust = 3; } void hubp2_dmdata_set_attributes( @@ -1033,6 +1044,25 @@ void hubp2_cursor_set_position( REG_SET(CURSOR_DST_OFFSET, 0, CURSOR_DST_X_OFFSET, dst_x_offset); /* TODO Handle surface pixel formats other than 4:4:4 */ + /* Cursor Position Register Config */ + hubp->pos.cur_ctl.bits.cur_enable = cur_en; + hubp->pos.position.bits.x_pos = pos->x; + hubp->pos.position.bits.y_pos = pos->y; + hubp->pos.hot_spot.bits.x_hot = x_hotspot; + hubp->pos.hot_spot.bits.y_hot = y_hotspot; + hubp->pos.dst_offset.bits.dst_x_offset = dst_x_offset; + /* Cursor Rectangle Cache + * Cursor bitmaps have different hotspot values + * There's a possibility that the above logic returns a negative value, + * so we clamp them to 0 + */ + if (src_x_offset < 0) + src_x_offset = 0; + if (src_y_offset < 0) + src_y_offset = 0; + /* Save necessary cursor info x, y position. w, h is saved in attribute func. */ + hubp->cur_rect.x = src_x_offset + param->viewport.x; + hubp->cur_rect.y = src_y_offset + param->viewport.y; } void hubp2_clk_cntl(struct hubp *hubp, bool enable) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index 4a668d6563df..e5b7ef7422b8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -372,6 +372,10 @@ void dpp3_set_cursor_attributes( REG_UPDATE(CURSOR0_COLOR1, CUR0_COLOR1, 0xFFFFFFFF); } + + dpp_base->att.cur0_ctl.bits.expansion_mode = 0; + dpp_base->att.cur0_ctl.bits.cur0_rom_en = cur_rom_en; + dpp_base->att.cur0_ctl.bits.mode = color_format; } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h b/drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h new file mode 100644 index 000000000000..0e7c5880e867 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h @@ -0,0 +1,98 @@ +/* Copyright © 2022 Advanced Micro Devices, Inc. All rights reserved. */ + +#ifndef __DAL_CURSOR_CACHE_H__ +#define __DAL_CURSOR_CACHE_H__ + +union reg_cursor_control_cfg { + struct { + uint32_t cur_enable: 1; + uint32_t reser0: 3; + uint32_t cur_2x_magnify: 1; + uint32_t reser1: 3; + uint32_t mode: 3; + uint32_t reser2: 5; + uint32_t pitch: 2; + uint32_t reser3: 6; + uint32_t line_per_chunk: 5; + uint32_t reser4: 3; + } bits; + uint32_t raw; +}; +struct cursor_position_cache_hubp { + union reg_cursor_control_cfg cur_ctl; + union reg_position_cfg { + struct { + uint32_t x_pos: 16; + uint32_t y_pos: 16; + } bits; + uint32_t raw; + } position; + union reg_hot_spot_cfg { + struct { + uint32_t x_hot: 16; + uint32_t y_hot: 16; + } bits; + uint32_t raw; + } hot_spot; + union reg_dst_offset_cfg { + struct { + uint32_t dst_x_offset: 13; + uint32_t reserved: 19; + } bits; + uint32_t raw; + } dst_offset; +}; + +struct cursor_attribute_cache_hubp { + uint32_t SURFACE_ADDR_HIGH; + uint32_t SURFACE_ADDR; + union reg_cursor_control_cfg cur_ctl; + union reg_cursor_size_cfg { + struct { + uint32_t width: 16; + uint32_t height: 16; + } bits; + uint32_t raw; + } size; + union reg_cursor_settings_cfg { + struct { + uint32_t dst_y_offset: 8; + uint32_t chunk_hdl_adjust: 2; + uint32_t reserved: 22; + } bits; + uint32_t raw; + } settings; +}; + +struct cursor_rect { + uint32_t x; + uint32_t y; + uint32_t w; + uint32_t h; +}; + +union reg_cur0_control_cfg { + struct { + uint32_t cur0_enable: 1; + uint32_t expansion_mode: 1; + uint32_t reser0: 1; + uint32_t cur0_rom_en: 1; + uint32_t mode: 3; + uint32_t reserved: 25; + } bits; + uint32_t raw; +}; +struct cursor_position_cache_dpp { + union reg_cur0_control_cfg cur0_ctl; +}; + +struct cursor_attribute_cache_dpp { + union reg_cur0_control_cfg cur0_ctl; +}; + +struct cursor_attributes_cfg { + struct cursor_attribute_cache_hubp aHubp; + struct cursor_attribute_cache_dpp aDpp; +}; + +#endif diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h index 3ef7faa92052..dcb80c4747b0 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h @@ -28,6 +28,7 @@ #define __DAL_DPP_H__ #include "transform.h" +#include "cursor_reg_cache.h" union defer_reg_writes { struct { @@ -58,6 +59,9 @@ struct dpp { struct pwl_params shaper_params; bool cm_bypass_mode; + + struct cursor_position_cache_dpp pos; + struct cursor_attribute_cache_dpp att; }; struct dpp_input_csc_matrix { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index 44c4578193a3..d5ea7545583e 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -27,6 +27,7 @@ #define __DAL_HUBP_H__ #include "mem_input.h" +#include "cursor_reg_cache.h" #define OPP_ID_INVALID 0xf #define MAX_TTU 0xffffff @@ -65,6 +66,10 @@ struct hubp { struct dc_cursor_attributes curs_attr; struct dc_cursor_position curs_pos; bool power_gated; + + struct cursor_position_cache_hubp pos; + struct cursor_attribute_cache_hubp att; + struct cursor_rect cur_rect; }; struct surface_flip_registers { diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 5d1aadade8a5..834707dfc189 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -760,11 +760,6 @@ enum dmub_cmd_dpia_type { DMUB_CMD__DPIA_MST_ALLOC_SLOTS = 2, }; -enum dmub_cmd_header_sub_type { - DMUB_CMD__SUB_TYPE_GENERAL = 0, - DMUB_CMD__SUB_TYPE_CURSOR_POSITION = 1 -}; - #pragma pack(push, 1) /** @@ -2089,7 +2084,99 @@ struct dmub_rb_cmd_update_dirty_rect { /** * Data passed from driver to FW in a DMUB_CMD__UPDATE_CURSOR_INFO command. */ -struct dmub_cmd_update_cursor_info_data { +union dmub_reg_cursor_control_cfg { + struct { + uint32_t cur_enable: 1; + uint32_t reser0: 3; + uint32_t cur_2x_magnify: 1; + uint32_t reser1: 3; + uint32_t mode: 3; + uint32_t reser2: 5; + uint32_t pitch: 2; + uint32_t reser3: 6; + uint32_t line_per_chunk: 5; + uint32_t reser4: 3; + } bits; + uint32_t raw; +}; +struct dmub_cursor_position_cache_hubp { + union dmub_reg_cursor_control_cfg cur_ctl; + union dmub_reg_position_cfg { + struct { + uint32_t cur_x_pos: 16; + uint32_t cur_y_pos: 16; + } bits; + uint32_t raw; + } position; + union dmub_reg_hot_spot_cfg { + struct { + uint32_t hot_x: 16; + uint32_t hot_y: 16; + } bits; + uint32_t raw; + } hot_spot; + union dmub_reg_dst_offset_cfg { + struct { + uint32_t dst_x_offset: 13; + uint32_t reserved: 19; + } bits; + uint32_t raw; + } dst_offset; +}; + +union dmub_reg_cur0_control_cfg { + struct { + uint32_t cur0_enable: 1; + uint32_t expansion_mode: 1; + uint32_t reser0: 1; + uint32_t cur0_rom_en: 1; + uint32_t mode: 3; + uint32_t reserved: 25; + } bits; + uint32_t raw; +}; +struct dmub_cursor_position_cache_dpp { + union dmub_reg_cur0_control_cfg cur0_ctl; +}; +struct dmub_cursor_position_cfg { + struct dmub_cursor_position_cache_hubp pHubp; + struct dmub_cursor_position_cache_dpp pDpp; + uint8_t pipe_idx; + /* + * Padding is required. To be 4 Bytes Aligned. + */ + uint8_t padding[3]; +}; + +struct dmub_cursor_attribute_cache_hubp { + uint32_t SURFACE_ADDR_HIGH; + uint32_t SURFACE_ADDR; + union dmub_reg_cursor_control_cfg cur_ctl; + union dmub_reg_cursor_size_cfg { + struct { + uint32_t width: 16; + uint32_t height: 16; + } bits; + uint32_t raw; + } size; + union dmub_reg_cursor_settings_cfg { + struct { + uint32_t dst_y_offset: 8; + uint32_t chunk_hdl_adjust: 2; + uint32_t reserved: 22; + } bits; + uint32_t raw; + } settings; +}; +struct dmub_cursor_attribute_cache_dpp { + union dmub_reg_cur0_control_cfg cur0_ctl; +}; +struct dmub_cursor_attributes_cfg { + struct dmub_cursor_attribute_cache_hubp aHubp; + struct dmub_cursor_attribute_cache_dpp aDpp; +}; + +struct dmub_cmd_update_cursor_payload0 { /** * Cursor dirty rects. */ @@ -2116,6 +2203,20 @@ struct dmub_cmd_update_cursor_info_data { * Currently the support is only for 0 or 1 */ uint8_t panel_inst; + /** + * Cursor Position Register. + * Registers contains Hubp & Dpp modules + */ + struct dmub_cursor_position_cfg position_cfg; +}; + +struct dmub_cmd_update_cursor_payload1 { + struct dmub_cursor_attributes_cfg attribute_cfg; +}; + +union dmub_cmd_update_cursor_info_data { + struct dmub_cmd_update_cursor_payload0 payload0; + struct dmub_cmd_update_cursor_payload1 payload1; }; /** * Definition of a DMUB_CMD__UPDATE_CURSOR_INFO command. @@ -2128,7 +2229,7 @@ struct dmub_rb_cmd_update_cursor_info { /** * Data passed from driver to FW in a DMUB_CMD__UPDATE_CURSOR_INFO command. */ - struct dmub_cmd_update_cursor_info_data update_cursor_info_data; + union dmub_cmd_update_cursor_info_data update_cursor_info_data; }; /** -- cgit From 6f4f8ff567c48823f8279206e236643e8e8f377e Mon Sep 17 00:00:00 2001 From: Meenakshikumar Somasundaram Date: Thu, 29 Sep 2022 23:55:41 -0400 Subject: drm/amd/display: Display does not light up after S4 resume [Why] Dpia hpd interrupt processing is disabled when entering S4/S0i3 and would be reenabled after detection completes during resuming. Because, keeping hpd interrupts enabled during detection leads to multiple detections for the same hpd transition. There is a S4 case where dpia hpd interrupt is missed when driver is in transitioning from hpd interrupt processing disable to enable and the display does not light up. [How] - Added dmub inbox command DMUB_CMD__DPIA_HPD_INT_ENABLE to explicitly control dmub to issue dpia hpd interrupt or not. If dpia hpd interrupt is disabled, dmub will keep the hpd pending and post it once driver reenables dpia hpd interrupt or when querying with DMUB_CMD__QUERY_HPD_STATE. - Added dmub boot option dpia_hpd_int_enable_supported to notify dmub about whether DMUB_CMD__DPIA_HPD_INT_ENABLE command would be used. Tested-by: Daniel Wheeler Reviewed-by: Mustapha Ghaddar Reviewed-by: Jun Lei Acked-by: Qingqing Zhuo Signed-off-by: Meenakshikumar Somasundaram Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 31 +++++++++++++++++++++++ drivers/gpu/drm/amd/display/dc/dc.h | 3 +++ drivers/gpu/drm/amd/display/dmub/dmub_srv.h | 1 + drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 21 ++++++++++++++- drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c | 1 + 5 files changed, 56 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index b5058a2ce7e8..660316a536f7 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -4656,6 +4656,37 @@ enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, return DC_OK; } +/** + ***************************************************************************** + * Function: dc_process_dmub_dpia_hpd_int_enable + * + * @brief + * Submits dpia hpd int enable command to dmub via inbox message + * + * @param + * [in] dc: dc structure + * [in] hpd_int_enable: 1 for hpd int enable, 0 to disable + * + * @return + * None + ***************************************************************************** + */ +void dc_process_dmub_dpia_hpd_int_enable(const struct dc *dc, + uint32_t hpd_int_enable) +{ + union dmub_rb_cmd cmd = {0}; + struct dc_dmub_srv *dmub_srv = dc->ctx->dmub_srv; + + cmd.dpia_hpd_int_enable.header.type = DMUB_CMD__DPIA_HPD_INT_ENABLE; + cmd.dpia_hpd_int_enable.enable = hpd_int_enable; + + dc_dmub_srv_cmd_queue(dmub_srv, &cmd); + dc_dmub_srv_cmd_execute(dmub_srv); + dc_dmub_srv_wait_idle(dmub_srv); + + DC_LOG_DEBUG("%s: hpd_int_enable(%d)\n", __func__, hpd_int_enable); +} + /** * dc_disable_accelerated_mode - disable accelerated mode * @dc: dc structure diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index b0afcff94591..5d0103e20412 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1612,6 +1612,9 @@ enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, uint8_t mst_alloc_slots, uint8_t *mst_slots_in_use); +void dc_process_dmub_dpia_hpd_int_enable(const struct dc *dc, + uint32_t hpd_int_enable); + /******************************************************************************* * DSC Interfaces ******************************************************************************/ diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index f34c45b19fcb..eb5b7eb292ef 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -248,6 +248,7 @@ struct dmub_srv_hw_params { bool disable_dpia; bool usb4_cm_version; bool fw_in_system_memory; + bool dpia_hpd_int_enable_supported; }; /** diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 834707dfc189..1d36f0fceb3e 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -400,8 +400,9 @@ union dmub_fw_boot_options { uint32_t diag_env: 1; /* 1 if diagnostic environment */ uint32_t gpint_scratch8: 1; /* 1 if GPINT is in scratch8*/ uint32_t usb4_cm_version: 1; /**< 1 CM support */ + uint32_t dpia_hpd_int_enable_supported: 1; /* 1 if dpia hpd int enable supported */ - uint32_t reserved : 17; /**< reserved */ + uint32_t reserved : 16; /**< reserved */ } bits; /**< boot bits */ uint32_t all; /**< 32-bit access to bits */ }; @@ -728,6 +729,12 @@ enum dmub_cmd_type { /** * Command type used for all VBIOS interface commands. */ + + /** + * Command type used to set DPIA HPD interrupt state + */ + DMUB_CMD__DPIA_HPD_INT_ENABLE = 86, + DMUB_CMD__VBIOS = 128, }; @@ -1255,6 +1262,14 @@ struct dmub_rb_cmd_set_mst_alloc_slots { struct dmub_cmd_mst_alloc_slots_control_data mst_slots_control; /* mst slots control */ }; +/** + * DMUB command structure for DPIA HPD int enable control. + */ +struct dmub_rb_cmd_dpia_hpd_int_enable { + struct dmub_cmd_header header; /* header */ + uint32_t enable; /* dpia hpd interrupt enable */ +}; + /** * struct dmub_rb_cmd_dpphy_init - DPPHY init. */ @@ -3336,6 +3351,10 @@ union dmub_rb_cmd { * Definition of a DMUB_CMD__QUERY_HPD_STATE command. */ struct dmub_rb_cmd_query_hpd_state query_hpd; + /** + * Definition of a DMUB_CMD__DPIA_HPD_INT_ENABLE command. + */ + struct dmub_rb_cmd_dpia_hpd_int_enable dpia_hpd_int_enable; }; /** diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c index c7bd7e216710..c90b9ee42e12 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c @@ -350,6 +350,7 @@ void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu boot_options.bits.dpia_supported = params->dpia_supported; boot_options.bits.enable_dpia = params->disable_dpia ? 0 : 1; boot_options.bits.usb4_cm_version = params->usb4_cm_version; + boot_options.bits.dpia_hpd_int_enable_supported = params->dpia_hpd_int_enable_supported; boot_options.bits.power_optimization = params->power_optimization; boot_options.bits.sel_mux_phy_c_d_phy_f_g = (dmub->asic == DMUB_ASIC_DCN31B) ? 1 : 0; -- cgit From ba30b223c93ec5af63993b6397cd7316e5acb6c1 Mon Sep 17 00:00:00 2001 From: Dmytro Laktyushkin Date: Tue, 4 Oct 2022 13:30:51 -0400 Subject: drm/amd/display: always allow pstate change when no dpps are active on dcn315 Prevents certain configs blocking s0i3 when streams aren't completely removed Tested-by: Daniel Wheeler Reviewed-by: Charlene Liu Acked-by: Qingqing Zhuo Signed-off-by: Dmytro Laktyushkin Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index 87bfc42bdaaf..7dd0845d1bd9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c @@ -483,7 +483,7 @@ void dcn31_calculate_wm_and_dlg_fp( int pipe_cnt, int vlevel) { - int i, pipe_idx; + int i, pipe_idx, active_dpp_count = 0; double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; dc_assert_fp_enabled(); @@ -528,6 +528,9 @@ void dcn31_calculate_wm_and_dlg_fp( if (!context->res_ctx.pipe_ctx[i].stream) continue; + if (context->res_ctx.pipe_ctx[i].plane_state) + active_dpp_count++; + pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt); pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); @@ -544,9 +547,9 @@ void dcn31_calculate_wm_and_dlg_fp( } dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); - /* For 31x apu pstate change is only supported if possible in vactive */ + /* For 31x apu pstate change is only supported if possible in vactive or if there are no active dpps */ context->bw_ctx.bw.dcn.clk.p_state_change_support = - context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] == dm_dram_clock_change_vactive; + context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] == dm_dram_clock_change_vactive || !active_dpp_count; } void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) -- cgit From 1298d9ab848653fc35431581d6e36662c7b6935a Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 27 Sep 2022 17:59:05 -0400 Subject: drm/amd/display: Add a missing hook to DCN20 The struct timing_generator_funcs provides a hook for setting up the maximum possible vertical dimension of display for OTG, as the panel supports. DCN10 has a standard function named optc1_set_vtotal_min_max which all ASICs can use to set the aforementioned hook. Since we did not set it for DCN20, this commit initializes the set_vtotal_min_max with the DCN10 function. Tested-by: Daniel Wheeler Acked-by: Qingqing Zhuo Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c index 0340fdd3f5fb..a08c335b7383 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c @@ -529,6 +529,7 @@ static struct timing_generator_funcs dcn20_tg_funcs = { .enable_optc_clock = optc1_enable_optc_clock, .set_drr = optc1_set_drr, .get_last_used_drr_vtotal = optc2_get_last_used_drr_vtotal, + .set_vtotal_min_max = optc1_set_vtotal_min_max, .set_static_screen_control = optc1_set_static_screen_control, .program_stereo = optc1_program_stereo, .is_stereo_left_eye = optc1_is_stereo_left_eye, -- cgit From 15e8b368981e1e8420f08b35bb12b794b200f4a0 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Fri, 12 Mar 2021 11:58:57 -0500 Subject: drm/amd/display: Use set_vtotal_min_max to configure OTG VTOTAL In multiple parts of the DCN code, we write directly to the OTG_V_TOTAL_* registers in some OPTC functions. Let's avoid it by using the set_vtotal_min_max. Tested-by: Daniel Wheeler Acked-by: Qingqing Zhuo Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c | 18 ++++-------------- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c | 2 +- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c | 1 - drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 4 ---- 4 files changed, 5 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index 143a900d4d3d..dca8a1446120 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -207,10 +207,7 @@ void optc1_program_timing( /* In case of V_TOTAL_CONTROL is on, make sure OTG_V_TOTAL_MAX and * OTG_V_TOTAL_MIN are equal to V_TOTAL. */ - REG_SET(OTG_V_TOTAL_MAX, 0, - OTG_V_TOTAL_MAX, v_total); - REG_SET(OTG_V_TOTAL_MIN, 0, - OTG_V_TOTAL_MIN, v_total); + optc->funcs->set_vtotal_min_max(optc, v_total, v_total); /* v_sync_start = 0, v_sync_end = v_sync_width */ v_sync_end = patched_crtc_timing.v_sync_width; @@ -931,11 +928,7 @@ void optc1_set_drr( } - REG_SET(OTG_V_TOTAL_MAX, 0, - OTG_V_TOTAL_MAX, params->vertical_total_max - 1); - - REG_SET(OTG_V_TOTAL_MIN, 0, - OTG_V_TOTAL_MIN, params->vertical_total_min - 1); + optc->funcs->set_vtotal_min_max(optc, params->vertical_total_min - 1, params->vertical_total_max - 1); REG_UPDATE_5(OTG_V_TOTAL_CONTROL, OTG_V_TOTAL_MIN_SEL, 1, @@ -954,11 +947,7 @@ void optc1_set_drr( OTG_V_TOTAL_MAX_SEL, 0, OTG_FORCE_LOCK_ON_EVENT, 0); - REG_SET(OTG_V_TOTAL_MIN, 0, - OTG_V_TOTAL_MIN, 0); - - REG_SET(OTG_V_TOTAL_MAX, 0, - OTG_V_TOTAL_MAX, 0); + optc->funcs->set_vtotal_min_max(optc, 0, 0); } } @@ -1577,6 +1566,7 @@ static const struct timing_generator_funcs dcn10_tg_funcs = { .enable_optc_clock = optc1_enable_optc_clock, .set_drr = optc1_set_drr, .get_last_used_drr_vtotal = NULL, + .set_vtotal_min_max = optc1_set_vtotal_min_max, .set_static_screen_control = optc1_set_static_screen_control, .set_test_pattern = optc1_set_test_pattern, .program_stereo = optc1_program_stereo, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c index 02459a64ee21..892d3c4d01a1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_optc.c @@ -325,6 +325,7 @@ static struct timing_generator_funcs dcn30_tg_funcs = { .enable_optc_clock = optc1_enable_optc_clock, .set_drr = optc1_set_drr, .get_last_used_drr_vtotal = optc2_get_last_used_drr_vtotal, + .set_vtotal_min_max = optc3_set_vtotal_min_max, .set_static_screen_control = optc1_set_static_screen_control, .program_stereo = optc1_program_stereo, .is_stereo_left_eye = optc1_is_stereo_left_eye, @@ -365,4 +366,3 @@ void dcn30_timing_generator_init(struct optc *optc1) optc1->min_h_sync_width = 4; optc1->min_v_sync_width = 1; } - diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index d873def1a8f9..63a677c8ee27 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -201,7 +201,6 @@ void optc31_set_drr( // Setup manual flow control for EOF via TRIG_A optc->funcs->setup_manual_trigger(optc); - } else { REG_UPDATE_4(OTG_V_TOTAL_CONTROL, OTG_SET_V_TOTAL_MIN_MASK, 0, diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 1d36f0fceb3e..7a8f61517424 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -2941,11 +2941,7 @@ struct dmub_rb_cmd_get_visual_confirm_color { struct dmub_optc_state { uint32_t v_total_max; uint32_t v_total_min; - uint32_t v_total_mid; - uint32_t v_total_mid_frame_num; uint32_t tg_inst; - uint32_t enable_manual_trigger; - uint32_t clear_force_vsync; }; struct dmub_rb_cmd_drr_update { -- cgit From c8588697aa4ec1f3b7fc09277cf2a5a662d40834 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 27 Sep 2022 18:30:08 -0400 Subject: drm/amd/display: Drop uncessary OTG lock check The OTG_MASTER_UPDATE_LOCK_SEL is used for GSL and OTGs in the same group for selecting the OTG_MASTER_UPDATE_LOCK from the same OTG. At some point, it a check was added to see if OTG is running or not, which is not necessary, and for this reason, this commit dropped that check. Tested-by: Daniel Wheeler Acked-by: Qingqing Zhuo Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c index dca8a1446120..33d780218790 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c @@ -646,13 +646,6 @@ uint32_t optc1_get_vblank_counter(struct timing_generator *optc) void optc1_lock(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - uint32_t regval = 0; - - regval = REG_READ(OTG_CONTROL); - - /* otg is not running, do not need to be locked */ - if ((regval & 0x1) == 0x0) - return; REG_SET(OTG_GLOBAL_CONTROL0, 0, OTG_MASTER_UPDATE_LOCK_SEL, optc->inst); @@ -660,12 +653,10 @@ void optc1_lock(struct timing_generator *optc) OTG_MASTER_UPDATE_LOCK, 1); /* Should be fast, status does not update on maximus */ - if (optc->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS) { - + if (optc->ctx->dce_environment != DCE_ENV_FPGA_MAXIMUS) REG_WAIT(OTG_MASTER_UPDATE_LOCK, UPDATE_LOCK_STATUS, 1, 1, 10); - } } void optc1_unlock(struct timing_generator *optc) -- cgit From 9799702360d51a714e888fef4ab5fb9123dfb41f Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Wed, 29 Jun 2022 12:35:12 -0400 Subject: drm/amd/display: Fix watermark calculation Watermark calculation was incorrect due to missing brackets. Fixes: 85f4bc0c333c ("drm/amd/display: Add SubVP required code") Tested-by: Daniel Wheeler Reviewed-by: Rodrigo Siqueira Acked-by: Qingqing Zhuo Signed-off-by: Alvin Lee Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0 --- drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index bbde635c56fc..0541e87e4f38 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -781,7 +781,7 @@ void dc_dmub_setup_subvp_dmub_command(struct dc *dc, // Store the original watermark value for this SubVP config so we can lower it when the // MCLK switch starts wm_val_refclk = context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns * - dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000 / 1000; + (dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000) / 1000; cmd.fw_assisted_mclk_switch_v2.config_data.watermark_a_cache = wm_val_refclk < 0xFFFF ? wm_val_refclk : 0xFFFF; } -- cgit From e5da651985be20616a9e0662032e0ea2ee4dd468 Mon Sep 17 00:00:00 2001 From: Bokun Zhang Date: Fri, 7 Oct 2022 02:08:38 +0800 Subject: drm/amdgpu: Fix SDMA engine resume issue under SRIOV - Under SRIOV, SDMA engine is shared between VFs. Therefore, we will not stop SDMA during hw_fini. This is not an issue with normal dirver loading and unloading. - However, when we put the SDMA engine to suspend state and resume it, the issue starts to show up. Something could attempt to use that SDMA engine to clear or move memory before the engine is initialized since the DRM entity is still there. - Therefore, we will call sdma_v5_2_enable(false) during hw_fini, and if we are under SRIOV, we will call sdma_v5_2_enable(true) afterwards to allow other VFs to use SDMA. This way, the DRM entity of SDMA engine is emptied and it will follow the flow of resume code path. Tested-by: Bokun Zhang Signed-off-by: Bokun Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index f136fec7b4f4..3eaf1a573e73 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1357,12 +1357,19 @@ static int sdma_v5_2_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (amdgpu_sriov_vf(adev)) - return 0; - + /* + * Under SRIOV, the VF cannot single-mindedly stop SDMA engine + * However, we still need to clean up the DRM entity + * Therefore, we will re-enable SDMA afterwards. + */ sdma_v5_2_ctx_switch_enable(adev, false); sdma_v5_2_enable(adev, false); + if (amdgpu_sriov_vf(adev)) { + sdma_v5_2_enable(adev, true); + sdma_v5_2_ctx_switch_enable(adev, true); + } + return 0; } -- cgit From 571c053658926df3321633b7133f574d3e656c81 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 6 Oct 2022 15:31:40 -0400 Subject: drm/amdgpu: switch sdma buffer function tear down to a helper Switch all of the SDMA implementations to use the helper to tear down the ttm buffer manager. Tested-by: Bokun Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 21 +++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h | 2 ++ drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 6 +----- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 6 +----- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 6 +----- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 24 +++++------------------- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 6 +----- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 10 +--------- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 9 +-------- drivers/gpu/drm/amd/amdgpu/si_dma.c | 5 ++--- 10 files changed, 36 insertions(+), 59 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c index 43cf8632cc1a..ea5278f094c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c @@ -285,3 +285,24 @@ out: } return err; } + +void amdgpu_sdma_unset_buffer_funcs_helper(struct amdgpu_device *adev) +{ + struct amdgpu_ring *sdma; + int i; + + for (i = 0; i < adev->sdma.num_instances; i++) { + if (adev->sdma.has_page_queue) { + sdma = &adev->sdma.instance[i].page; + if (adev->mman.buffer_funcs_ring == sdma) { + amdgpu_ttm_set_buffer_funcs_status(adev, false); + break; + } + } + sdma = &adev->sdma.instance[i].ring; + if (adev->mman.buffer_funcs_ring == sdma) { + amdgpu_ttm_set_buffer_funcs_status(adev, false); + break; + } + } +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h index d2d88279fefb..7d99205c2e01 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h @@ -128,4 +128,6 @@ int amdgpu_sdma_init_microcode(struct amdgpu_device *adev, char *fw_name, u32 instance, bool duplicate); void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev, bool duplicate); +void amdgpu_sdma_unset_buffer_funcs_helper(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index 5647f13b98d4..cbca9866645c 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -309,14 +309,10 @@ static void cik_sdma_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq */ static void cik_sdma_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 6bdffdc1c0b9..c52d246a1d96 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -342,14 +342,10 @@ static void sdma_v2_4_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v2_4_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 2584fa3cb13e..486d9b5c1b9e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -516,14 +516,10 @@ static void sdma_v3_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v3_0_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 7241a9fb0121..7b4195f18a7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -915,18 +915,12 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v4_0_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES]; u32 rb_cntl, ib_cntl; - int i, unset = 0; + int i; - for (i = 0; i < adev->sdma.num_instances; i++) { - sdma[i] = &adev->sdma.instance[i].ring; - - if ((adev->mman.buffer_funcs_ring == sdma[i]) && unset != 1) { - amdgpu_ttm_set_buffer_funcs_status(adev, false); - unset = 1; - } + amdgpu_sdma_unset_buffer_funcs_helper(adev); + for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0); WREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL, rb_cntl); @@ -957,20 +951,12 @@ static void sdma_v4_0_rlc_stop(struct amdgpu_device *adev) */ static void sdma_v4_0_page_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES]; u32 rb_cntl, ib_cntl; int i; - bool unset = false; - for (i = 0; i < adev->sdma.num_instances; i++) { - sdma[i] = &adev->sdma.instance[i].page; - - if ((adev->mman.buffer_funcs_ring == sdma[i]) && - (!unset)) { - amdgpu_ttm_set_buffer_funcs_status(adev, false); - unset = true; - } + amdgpu_sdma_unset_buffer_funcs_helper(adev); + for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SDMA(i, mmSDMA0_PAGE_RB_CNTL); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_PAGE_RB_CNTL, RB_ENABLE, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index c05c3eebde4c..783048e1b0ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -584,14 +584,10 @@ static void sdma_v5_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v5_0_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL)); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 3eaf1a573e73..c2ee53c2dd1b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -414,18 +414,10 @@ static void sdma_v5_2_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v5_2_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; - struct amdgpu_ring *sdma2 = &adev->sdma.instance[2].ring; - struct amdgpu_ring *sdma3 = &adev->sdma.instance[3].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1) || - (adev->mman.buffer_funcs_ring == sdma2) || - (adev->mman.buffer_funcs_ring == sdma3)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL)); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index 0150f66a5ae6..a6483483404e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -398,14 +398,10 @@ static void sdma_v6_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se */ static void sdma_v6_0_gfx_stop(struct amdgpu_device *adev) { - struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring; - struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring; u32 rb_cntl, ib_cntl; int i; - if ((adev->mman.buffer_funcs_ring == sdma0) || - (adev->mman.buffer_funcs_ring == sdma1)) - amdgpu_ttm_set_buffer_funcs_status(adev, false); + amdgpu_sdma_unset_buffer_funcs_helper(adev); for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SOC15_IP(GC, sdma_v6_0_get_reg_offset(adev, i, regSDMA0_QUEUE0_RB_CNTL)); @@ -415,9 +411,6 @@ static void sdma_v6_0_gfx_stop(struct amdgpu_device *adev) ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_QUEUE0_IB_CNTL, IB_ENABLE, 0); WREG32_SOC15_IP(GC, sdma_v6_0_get_reg_offset(adev, i, regSDMA0_QUEUE0_IB_CNTL), ib_cntl); } - - sdma0->sched.ready = false; - sdma1->sched.ready = false; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c index f675111ace20..4d5e718540aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dma.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c @@ -116,15 +116,14 @@ static void si_dma_stop(struct amdgpu_device *adev) u32 rb_cntl; unsigned i; + amdgpu_sdma_unset_buffer_funcs_helper(adev); + for (i = 0; i < adev->sdma.num_instances; i++) { ring = &adev->sdma.instance[i].ring; /* dma0 */ rb_cntl = RREG32(DMA_RB_CNTL + sdma_offsets[i]); rb_cntl &= ~DMA_RB_ENABLE; WREG32(DMA_RB_CNTL + sdma_offsets[i], rb_cntl); - - if (adev->mman.buffer_funcs_ring == ring) - amdgpu_ttm_set_buffer_funcs_status(adev, false); } } -- cgit From a98cec220aa4b2502704aa0196da1bdc9eb455b4 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 6 Oct 2022 15:53:10 -0400 Subject: drm/amdgpu: fix SDMA suspend/resume on SR-IOV Update all SDMA versions that support SR-IOV to properly tear down the ttm buffer functions on suspend. Tested-by: Bokun Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 5 ++++- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 5 ++++- drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 16 ++++++---------- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 5 ++++- 4 files changed, 18 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 7b4195f18a7c..298fa11702e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1940,8 +1940,11 @@ static int sdma_v4_0_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int i; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { + /* disable the scheduler for SDMA */ + amdgpu_sdma_unset_buffer_funcs_helper(adev); return 0; + } for (i = 0; i < adev->sdma.num_instances; i++) { amdgpu_irq_put(adev, &adev->sdma.ecc_irq, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c index 783048e1b0ce..d4d9f196db83 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c @@ -1456,8 +1456,11 @@ static int sdma_v5_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { + /* disable the scheduler for SDMA */ + amdgpu_sdma_unset_buffer_funcs_helper(adev); return 0; + } sdma_v5_0_ctx_switch_enable(adev, false); sdma_v5_0_enable(adev, false); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index c2ee53c2dd1b..809eca54fc61 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1349,19 +1349,15 @@ static int sdma_v5_2_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - /* - * Under SRIOV, the VF cannot single-mindedly stop SDMA engine - * However, we still need to clean up the DRM entity - * Therefore, we will re-enable SDMA afterwards. - */ - sdma_v5_2_ctx_switch_enable(adev, false); - sdma_v5_2_enable(adev, false); - if (amdgpu_sriov_vf(adev)) { - sdma_v5_2_enable(adev, true); - sdma_v5_2_ctx_switch_enable(adev, true); + /* disable the scheduler for SDMA */ + amdgpu_sdma_unset_buffer_funcs_helper(adev); + return 0; } + sdma_v5_2_ctx_switch_enable(adev, false); + sdma_v5_2_enable(adev, false); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index a6483483404e..da3beb0bf2fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1311,8 +1311,11 @@ static int sdma_v6_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { + /* disable the scheduler for SDMA */ + amdgpu_sdma_unset_buffer_funcs_helper(adev); return 0; + } sdma_v6_0_ctx_switch_enable(adev, false); sdma_v6_0_enable(adev, false); -- cgit From 2cc4a5914ce952d6fc83b0f8089a23095ad4f677 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Tue, 4 Oct 2022 11:14:01 +0300 Subject: drm/amd/pm: vega10_hwmgr: fix potential off-by-one overflow in 'performance_levels' Since 'hardwareActivityPerformanceLevels' is set to the size of the 'performance_levels' array in vega10_hwmgr_backend_init(), using the '<=' assertion to check for the next index value is incorrect. Replace it with '<'. Detected using the static analysis tool - Svace. Fixes: f83a9991648b ("drm/amd/powerplay: add Vega10 powerplay support (v5)") Reviewed-by: Evan Quan Signed-off-by: Alexey Kodanev Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 99bfe5efe171..c8c9fb827bda 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -3155,7 +3155,7 @@ static int vega10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, return -1); PP_ASSERT_WITH_CODE( - (vega10_ps->performance_level_count <= + (vega10_ps->performance_level_count < hwmgr->platform_descriptor. hardwareActivityPerformanceLevels), "Performance levels exceeds Driver limit!", -- cgit From d2bd0831b51d1123fc86c019db3452d6a1ce5029 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Tue, 4 Oct 2022 11:14:02 +0300 Subject: drm/amd/pm: smu7_hwmgr: fix potential off-by-one overflow in 'performance_levels' Since 'hardwareActivityPerformanceLevels' is set to the size of the 'performance_levels' array in smu7_hwmgr_backend_init(), using the '<=' assertion to check for the next index value is incorrect. Replace it with '<'. Detected using the static analysis tool - Svace. Fixes: 599a7e9fe1b6 ("drm/amd/powerplay: implement smu7 hwmgr to manager asics with smu ip version 7.") Reviewed-by: Evan Quan Signed-off-by: Alexey Kodanev Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index e4fcbf8a7eb5..7ef7e81525a3 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -3603,7 +3603,7 @@ static int smu7_get_pp_table_entry_callback_func_v1(struct pp_hwmgr *hwmgr, return -EINVAL); PP_ASSERT_WITH_CODE( - (smu7_power_state->performance_level_count <= + (smu7_power_state->performance_level_count < hwmgr->platform_descriptor.hardwareActivityPerformanceLevels), "Performance levels exceeds Driver limit!", return -EINVAL); -- cgit From faf4d8e07f5b67bece91723ad3e8b3f88a3dbf23 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sun, 9 Oct 2022 23:05:12 -0700 Subject: drm/amd/display: fix array-bounds error in dc_stream_remove_writeback() [take 2] Commit 5d8c3e836fc2 ("drm/amd/display: fix array-bounds error in dc_stream_remove_writeback()") tried to fix an array bounds error seen with gcc 12.0. Unfortunately, that results in another array bounds error, seen with older versions of gcc. Building csky:allmodconfig ... failed -------------- Error log: drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_stream.c: In function 'dc_stream_remove_writeback': drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_stream.c:527:83: error: array subscript 1 is above array bounds of 'struct dc_writeback_info[1]' [-Werror=array-bounds] 527 | stream->writeback_info[j] = stream->writeback_info[i]; | ~~~~~~~~~~~~~~~~~~~~~~^~~ In file included from drivers/gpu/drm/amd/amdgpu/../display/dc/dc.h:1269, from drivers/gpu/drm/amd/amdgpu/../display/dc/inc/core_types.h:29, from drivers/gpu/drm/amd/amdgpu/../display/dc/basics/dc_common.h:29, from drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_stream.c:27: drivers/gpu/drm/amd/amdgpu/../display/dc/dc_stream.h:241:34: note: while referencing 'writeback_info' 241 | struct dc_writeback_info writeback_info[MAX_DWB_PIPES]; We could check both i and j for overflow to fix the problem. That would, however, be not make much sense since it is known and provable that j <= i. Also, the check introduced with commit 5d8c3e836fc2 does not really add value since it checks if j < MAX_DWB_PIPES. Since it is known that j <= i, it would make more sense to check if i < MAX_DWB_PIPES. Unfortunately, that does not help to solve the problem observed here: gcc still complains. To solve the problem, replace the subsequent check for 'i != j' with 'j < i'. This is identical to the original check since we know that j <= i, and it makes all versions of gcc happy. Drop the check introduced with commit 5d8c3e836fc2 since it is not really useful and does not solve the problem. Cc: Aurabindo Pillai Cc: Hamza Mahfooz Fixes: 5d8c3e836fc2 ("drm/amd/display: fix array-bounds error in dc_stream_remove_writeback()") Signed-off-by: Guenter Roeck Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 9998f58c14b9..38d71b5c1f2d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -524,9 +524,9 @@ bool dc_stream_remove_writeback(struct dc *dc, } /* remove writeback info for disabled writeback pipes from stream */ - for (i = 0, j = 0; i < stream->num_wb_info && j < MAX_DWB_PIPES; i++) { + for (i = 0, j = 0; i < stream->num_wb_info; i++) { if (stream->writeback_info[i].wb_enabled) { - if (i != j) + if (j < i) /* trim the array */ stream->writeback_info[j] = stream->writeback_info[i]; j++; -- cgit From 096f2a0c6469c8a8e70cfbb83345b7ada2929f13 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 10 Oct 2022 16:47:38 +0200 Subject: clk: Update req_rate on __clk_recalc_rates() Commit cb1b1dd96241 ("clk: Set req_rate on reparenting") introduced a new function, clk_core_update_orphan_child_rates(), that updates the req_rate field on reparenting. It turns out that that function will interfere with the clock notifying done by __clk_recalc_rates(). This ends up reporting the new rate in both the old_rate and new_rate fields of struct clk_notifier_data. Since clk_core_update_orphan_child_rates() is basically __clk_recalc_rates() without the notifiers, and with the req_rate field update, we can drop clk_core_update_orphan_child_rates() entirely, and make __clk_recalc_rates() update req_rate. However, __clk_recalc_rates() is being called in several code paths: when retrieving a rate (most likely through clk_get_rate()), when changing parents (through clk_set_rate() or clk_hw_reparent()), or when updating the orphan status (through clk_core_reparent_orphans_nolock(), called at registration). Updating req_rate on reparenting or initialisation makes sense, but we shouldn't do it on clk_get_rate(). Thus an extra flag has been added to update or not req_rate depending on the context. Fixes: cb1b1dd96241 ("clk: Set req_rate on reparenting") Link: https://lore.kernel.org/linux-clk/0acc7217-762c-7c0d-45a0-55c384824ce4@samsung.com/ Link: https://lore.kernel.org/linux-clk/Y0QNSx+ZgqKSvPOC@sirena.org.uk/ Reported-by: Marek Szyprowski Reported-by: Mark Brown Suggested-by: Stephen Boyd Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20221010-rpi-clk-fixes-again-v1-1-d87ba82ac404@cerno.tech Tested-by: Marek Szyprowski Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 39 +++++++++++---------------------------- 1 file changed, 11 insertions(+), 28 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index ec518dc5d462..47b33c5b28e1 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1760,6 +1760,7 @@ static unsigned long clk_recalc(struct clk_core *core, /** * __clk_recalc_rates * @core: first clk in the subtree + * @update_req: Whether req_rate should be updated with the new rate * @msg: notification type (see include/linux/clk.h) * * Walks the subtree of clks starting with clk and recalculates rates as it @@ -1769,7 +1770,8 @@ static unsigned long clk_recalc(struct clk_core *core, * clk_recalc_rates also propagates the POST_RATE_CHANGE notification, * if necessary. */ -static void __clk_recalc_rates(struct clk_core *core, unsigned long msg) +static void __clk_recalc_rates(struct clk_core *core, bool update_req, + unsigned long msg) { unsigned long old_rate; unsigned long parent_rate = 0; @@ -1783,6 +1785,8 @@ static void __clk_recalc_rates(struct clk_core *core, unsigned long msg) parent_rate = core->parent->rate; core->rate = clk_recalc(core, parent_rate); + if (update_req) + core->req_rate = core->rate; /* * ignore NOTIFY_STOP and NOTIFY_BAD return values for POST_RATE_CHANGE @@ -1792,13 +1796,13 @@ static void __clk_recalc_rates(struct clk_core *core, unsigned long msg) __clk_notify(core, msg, old_rate, core->rate); hlist_for_each_entry(child, &core->children, child_node) - __clk_recalc_rates(child, msg); + __clk_recalc_rates(child, update_req, msg); } static unsigned long clk_core_get_rate_recalc(struct clk_core *core) { if (core && (core->flags & CLK_GET_RATE_NOCACHE)) - __clk_recalc_rates(core, 0); + __clk_recalc_rates(core, false, 0); return clk_core_get_rate_nolock(core); } @@ -1901,23 +1905,6 @@ static void clk_core_update_orphan_status(struct clk_core *core, bool is_orphan) clk_core_update_orphan_status(child, is_orphan); } -/* - * Update the orphan rate and req_rate of @core and all its children. - */ -static void clk_core_update_orphan_child_rates(struct clk_core *core) -{ - struct clk_core *child; - unsigned long parent_rate = 0; - - if (core->parent) - parent_rate = core->parent->rate; - - core->rate = core->req_rate = clk_recalc(core, parent_rate); - - hlist_for_each_entry(child, &core->children, child_node) - clk_core_update_orphan_child_rates(child); -} - static void clk_reparent(struct clk_core *core, struct clk_core *new_parent) { bool was_orphan = core->orphan; @@ -1987,8 +1974,6 @@ static struct clk_core *__clk_set_parent_before(struct clk_core *core, clk_reparent(core, parent); clk_enable_unlock(flags); - clk_core_update_orphan_child_rates(core); - return old_parent; } @@ -2034,7 +2019,6 @@ static int __clk_set_parent(struct clk_core *core, struct clk_core *parent, clk_reparent(core, old_parent); clk_enable_unlock(flags); - clk_core_update_orphan_child_rates(core); __clk_set_parent_after(core, old_parent, parent); return ret; @@ -2658,9 +2642,8 @@ static void clk_core_reparent(struct clk_core *core, struct clk_core *new_parent) { clk_reparent(core, new_parent); - clk_core_update_orphan_child_rates(core); __clk_recalc_accuracies(core); - __clk_recalc_rates(core, POST_RATE_CHANGE); + __clk_recalc_rates(core, true, POST_RATE_CHANGE); } void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent) @@ -2744,9 +2727,9 @@ static int clk_core_set_parent_nolock(struct clk_core *core, /* propagate rate an accuracy recalculation accordingly */ if (ret) { - __clk_recalc_rates(core, ABORT_RATE_CHANGE); + __clk_recalc_rates(core, true, ABORT_RATE_CHANGE); } else { - __clk_recalc_rates(core, POST_RATE_CHANGE); + __clk_recalc_rates(core, true, POST_RATE_CHANGE); __clk_recalc_accuracies(core); } @@ -3643,7 +3626,7 @@ static void clk_core_reparent_orphans_nolock(void) __clk_set_parent_before(orphan, parent); __clk_set_parent_after(orphan, parent, NULL); __clk_recalc_accuracies(orphan); - __clk_recalc_rates(orphan, 0); + __clk_recalc_rates(orphan, true, 0); /* * __clk_init_parent() will set the initial req_rate to -- cgit From 589a2004881f0941ca46146a5de68b3666d1d54a Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Mon, 10 Oct 2022 16:47:39 +0200 Subject: clk: tests: Add tests for notifiers We're recently encountered a regression due to the rates reported through the clk_notifier_data being off when changing parents. Let's add a test suite and a test to make sure that we do get notified and with the proper rates. Suggested-by: Stephen Boyd Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20221010-rpi-clk-fixes-again-v1-2-d87ba82ac404@cerno.tech Tested-by: Marek Szyprowski Signed-off-by: Stephen Boyd --- drivers/clk/clk_test.c | 156 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 156 insertions(+) diff --git a/drivers/clk/clk_test.c b/drivers/clk/clk_test.c index 509256c5567a..f9a5c2964c65 100644 --- a/drivers/clk/clk_test.c +++ b/drivers/clk/clk_test.c @@ -2239,10 +2239,166 @@ static struct kunit_suite clk_leaf_mux_set_rate_parent_test_suite = { .test_cases = clk_leaf_mux_set_rate_parent_test_cases, }; +struct clk_mux_notifier_rate_change { + bool done; + unsigned long old_rate; + unsigned long new_rate; + wait_queue_head_t wq; +}; + +struct clk_mux_notifier_ctx { + struct clk_multiple_parent_ctx mux_ctx; + struct clk *clk; + struct notifier_block clk_nb; + struct clk_mux_notifier_rate_change pre_rate_change; + struct clk_mux_notifier_rate_change post_rate_change; +}; + +#define NOTIFIER_TIMEOUT_MS 100 + +static int clk_mux_notifier_callback(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct clk_notifier_data *clk_data = data; + struct clk_mux_notifier_ctx *ctx = container_of(nb, + struct clk_mux_notifier_ctx, + clk_nb); + + if (action & PRE_RATE_CHANGE) { + ctx->pre_rate_change.old_rate = clk_data->old_rate; + ctx->pre_rate_change.new_rate = clk_data->new_rate; + ctx->pre_rate_change.done = true; + wake_up_interruptible(&ctx->pre_rate_change.wq); + } + + if (action & POST_RATE_CHANGE) { + ctx->post_rate_change.old_rate = clk_data->old_rate; + ctx->post_rate_change.new_rate = clk_data->new_rate; + ctx->post_rate_change.done = true; + wake_up_interruptible(&ctx->post_rate_change.wq); + } + + return 0; +} + +static int clk_mux_notifier_test_init(struct kunit *test) +{ + struct clk_mux_notifier_ctx *ctx; + const char *top_parents[2] = { "parent-0", "parent-1" }; + int ret; + + ctx = kunit_kzalloc(test, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + test->priv = ctx; + ctx->clk_nb.notifier_call = clk_mux_notifier_callback; + init_waitqueue_head(&ctx->pre_rate_change.wq); + init_waitqueue_head(&ctx->post_rate_change.wq); + + ctx->mux_ctx.parents_ctx[0].hw.init = CLK_HW_INIT_NO_PARENT("parent-0", + &clk_dummy_rate_ops, + 0); + ctx->mux_ctx.parents_ctx[0].rate = DUMMY_CLOCK_RATE_1; + ret = clk_hw_register(NULL, &ctx->mux_ctx.parents_ctx[0].hw); + if (ret) + return ret; + + ctx->mux_ctx.parents_ctx[1].hw.init = CLK_HW_INIT_NO_PARENT("parent-1", + &clk_dummy_rate_ops, + 0); + ctx->mux_ctx.parents_ctx[1].rate = DUMMY_CLOCK_RATE_2; + ret = clk_hw_register(NULL, &ctx->mux_ctx.parents_ctx[1].hw); + if (ret) + return ret; + + ctx->mux_ctx.current_parent = 0; + ctx->mux_ctx.hw.init = CLK_HW_INIT_PARENTS("test-mux", top_parents, + &clk_multiple_parents_mux_ops, + 0); + ret = clk_hw_register(NULL, &ctx->mux_ctx.hw); + if (ret) + return ret; + + ctx->clk = clk_hw_get_clk(&ctx->mux_ctx.hw, NULL); + ret = clk_notifier_register(ctx->clk, &ctx->clk_nb); + if (ret) + return ret; + + return 0; +} + +static void clk_mux_notifier_test_exit(struct kunit *test) +{ + struct clk_mux_notifier_ctx *ctx = test->priv; + struct clk *clk = ctx->clk; + + clk_notifier_unregister(clk, &ctx->clk_nb); + clk_put(clk); + + clk_hw_unregister(&ctx->mux_ctx.hw); + clk_hw_unregister(&ctx->mux_ctx.parents_ctx[0].hw); + clk_hw_unregister(&ctx->mux_ctx.parents_ctx[1].hw); +} + +/* + * Test that if the we have a notifier registered on a mux, the core + * will notify us when we switch to another parent, and with the proper + * old and new rates. + */ +static void clk_mux_notifier_set_parent_test(struct kunit *test) +{ + struct clk_mux_notifier_ctx *ctx = test->priv; + struct clk_hw *hw = &ctx->mux_ctx.hw; + struct clk *clk = clk_hw_get_clk(hw, NULL); + struct clk *new_parent = clk_hw_get_clk(&ctx->mux_ctx.parents_ctx[1].hw, NULL); + int ret; + + ret = clk_set_parent(clk, new_parent); + KUNIT_ASSERT_EQ(test, ret, 0); + + ret = wait_event_interruptible_timeout(ctx->pre_rate_change.wq, + ctx->pre_rate_change.done, + msecs_to_jiffies(NOTIFIER_TIMEOUT_MS)); + KUNIT_ASSERT_GT(test, ret, 0); + + KUNIT_EXPECT_EQ(test, ctx->pre_rate_change.old_rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_EQ(test, ctx->pre_rate_change.new_rate, DUMMY_CLOCK_RATE_2); + + ret = wait_event_interruptible_timeout(ctx->post_rate_change.wq, + ctx->post_rate_change.done, + msecs_to_jiffies(NOTIFIER_TIMEOUT_MS)); + KUNIT_ASSERT_GT(test, ret, 0); + + KUNIT_EXPECT_EQ(test, ctx->post_rate_change.old_rate, DUMMY_CLOCK_RATE_1); + KUNIT_EXPECT_EQ(test, ctx->post_rate_change.new_rate, DUMMY_CLOCK_RATE_2); + + clk_put(new_parent); + clk_put(clk); +} + +static struct kunit_case clk_mux_notifier_test_cases[] = { + KUNIT_CASE(clk_mux_notifier_set_parent_test), + {} +}; + +/* + * Test suite for a mux with multiple parents, and a notifier registered + * on the mux. + * + * These tests exercise the behaviour of notifiers. + */ +static struct kunit_suite clk_mux_notifier_test_suite = { + .name = "clk-mux-notifier", + .init = clk_mux_notifier_test_init, + .exit = clk_mux_notifier_test_exit, + .test_cases = clk_mux_notifier_test_cases, +}; + kunit_test_suites( &clk_leaf_mux_set_rate_parent_test_suite, &clk_test_suite, &clk_multiple_parents_mux_test_suite, + &clk_mux_notifier_test_suite, &clk_orphan_transparent_multiple_parent_mux_test_suite, &clk_orphan_transparent_single_parent_test_suite, &clk_orphan_two_level_root_last_test_suite, -- cgit From 4f2e56a59b9947b3e698d3cabcb858765c12b1e8 Mon Sep 17 00:00:00 2001 From: Saranya Gopal Date: Tue, 11 Oct 2022 10:19:16 +0530 Subject: ALSA: hda/realtek: Add Intel Reference SSID to support headset keys This patch fixes the issue with 3.5mm headset keys on RPL-P platform. [ Rearranged the entry in SSID order by tiwai ] Signed-off-by: Saranya Gopal Signed-off-by: Ninad Naik Cc: Link: https://lore.kernel.org/r/20221011044916.2278867-1-saranya.gopal@intel.com 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 54a0f6b4ffc7..4b076912bbf4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9445,6 +9445,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE), SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), + SND_PCI_QUIRK(0x10ec, 0x124c, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1252, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), -- cgit From a70aef7982b012e86dfd39fbb235e76a21ae778a Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 11 Oct 2022 09:01:46 +0200 Subject: ALSA: rawmidi: Drop register_mutex in snd_rawmidi_free() The register_mutex taken around the dev_unregister callback call in snd_rawmidi_free() may potentially lead to a mutex deadlock, when OSS emulation and a hot unplug are involved. Since the mutex doesn't protect the actual race (as the registration itself is already protected by another means), let's drop it. Link: https://lore.kernel.org/r/CAB7eexJP7w1B0mVgDF0dQ+gWor7UdkiwPczmL7pn91xx8xpzOA@mail.gmail.com Cc: Link: https://lore.kernel.org/r/20221011070147.7611-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/core/rawmidi.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 6963d5a487b3..d8edb6055072 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -1899,10 +1899,8 @@ static int snd_rawmidi_free(struct snd_rawmidi *rmidi) snd_info_free_entry(rmidi->proc_entry); rmidi->proc_entry = NULL; - mutex_lock(®ister_mutex); if (rmidi->ops && rmidi->ops->dev_unregister) rmidi->ops->dev_unregister(rmidi); - mutex_unlock(®ister_mutex); snd_rawmidi_free_substreams(&rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT]); snd_rawmidi_free_substreams(&rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT]); -- cgit From 97d917879d7f92df09c3f21fd54609a8bcd654b2 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 11 Oct 2022 09:01:47 +0200 Subject: ALSA: oss: Fix potential deadlock at unregistration We took sound_oss_mutex around the calls of unregister_sound_special() at unregistering OSS devices. This may, however, lead to a deadlock, because we manage the card release via the card's device object, and the release may happen at unregister_sound_special() call -- which will take sound_oss_mutex again in turn. Although the deadlock might be fixed by relaxing the rawmidi mutex in the previous commit, it's safer to move unregister_sound_special() calls themselves out of the sound_oss_mutex, too. The call is race-safe as the function has a spinlock protection by itself. Link: https://lore.kernel.org/r/CAB7eexJP7w1B0mVgDF0dQ+gWor7UdkiwPczmL7pn91xx8xpzOA@mail.gmail.com Cc: Link: https://lore.kernel.org/r/20221011070147.7611-2-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/core/sound_oss.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/sound/core/sound_oss.c b/sound/core/sound_oss.c index 7ed0a2a91035..2751bf2ff61b 100644 --- a/sound/core/sound_oss.c +++ b/sound/core/sound_oss.c @@ -162,7 +162,6 @@ int snd_unregister_oss_device(int type, struct snd_card *card, int dev) mutex_unlock(&sound_oss_mutex); return -ENOENT; } - unregister_sound_special(minor); switch (SNDRV_MINOR_OSS_DEVICE(minor)) { case SNDRV_MINOR_OSS_PCM: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_AUDIO); @@ -174,12 +173,18 @@ int snd_unregister_oss_device(int type, struct snd_card *card, int dev) track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_DMMIDI1); break; } - if (track2 >= 0) { - unregister_sound_special(track2); + if (track2 >= 0) snd_oss_minors[track2] = NULL; - } snd_oss_minors[minor] = NULL; mutex_unlock(&sound_oss_mutex); + + /* call unregister_sound_special() outside sound_oss_mutex; + * otherwise may deadlock, as it can trigger the release of a card + */ + unregister_sound_special(minor); + if (track2 >= 0) + unregister_sound_special(track2); + kfree(mptr); return 0; } -- cgit From b148766e2b8b7b61c9aef53aefedae33f637a1e7 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 28 Sep 2022 23:31:20 +0200 Subject: parisc: Reduce kernel size by packing alternative tables The values stored in the length and condition fields of the alternative tables fit into 16 bits, so we can save 4 bytes per alternative table entry. Since a typical 32-bit kernel has more than 3000 entries this saves > 12k of storage on disc. bloat-o-meter shows a reduction of -0.01% by this change: Total: Before=10196505, After=10195529, chg -0.01% $ ls -la vmlinux vmlinux.before -rwxr-xr-x 14437324 vmlinux -rwxr-xr-x 14449512 vmlinux.before Signed-off-by: Helge Deller --- arch/parisc/include/asm/alternative.h | 21 ++++++++++++--------- arch/parisc/kernel/alternative.c | 7 ++++--- 2 files changed, 16 insertions(+), 12 deletions(-) diff --git a/arch/parisc/include/asm/alternative.h b/arch/parisc/include/asm/alternative.h index 0ec54f43d6d2..1ed45fd085d3 100644 --- a/arch/parisc/include/asm/alternative.h +++ b/arch/parisc/include/asm/alternative.h @@ -22,10 +22,10 @@ struct alt_instr { s32 orig_offset; /* offset to original instructions */ - s32 len; /* end of original instructions */ - u32 cond; /* see ALT_COND_XXX */ + s16 len; /* end of original instructions */ + u16 cond; /* see ALT_COND_XXX */ u32 replacement; /* replacement instruction or code */ -}; +} __packed; void set_kernel_text_rw(int enable_read_write); void apply_alternatives_all(void); @@ -35,8 +35,9 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* Alternative SMP implementation. */ #define ALTERNATIVE(cond, replacement) "!0:" \ ".section .altinstructions, \"aw\" !" \ - ".word (0b-4-.), 1, " __stringify(cond) "," \ - __stringify(replacement) " !" \ + ".word (0b-4-.) !" \ + ".hword 1, " __stringify(cond) " !" \ + ".word " __stringify(replacement) " !" \ ".previous" #else @@ -44,15 +45,17 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* to replace one single instructions by a new instruction */ #define ALTERNATIVE(from, to, cond, replacement)\ .section .altinstructions, "aw" ! \ - .word (from - .), (to - from)/4 ! \ - .word cond, replacement ! \ + .word (from - .) ! \ + .hword (to - from)/4, cond ! \ + .word replacement ! \ .previous /* to replace multiple instructions by new code */ #define ALTERNATIVE_CODE(from, num_instructions, cond, new_instr_ptr)\ .section .altinstructions, "aw" ! \ - .word (from - .), -num_instructions ! \ - .word cond, (new_instr_ptr - .) ! \ + .word (from - .) ! \ + .hword -num_instructions, cond ! \ + .word (new_instr_ptr - .) ! \ .previous #endif /* __ASSEMBLY__ */ diff --git a/arch/parisc/kernel/alternative.c b/arch/parisc/kernel/alternative.c index daa1e9047275..66f5672c70bd 100644 --- a/arch/parisc/kernel/alternative.c +++ b/arch/parisc/kernel/alternative.c @@ -26,7 +26,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start, struct alt_instr *entry; int index = 0, applied = 0; int num_cpus = num_online_cpus(); - u32 cond_check; + u16 cond_check; cond_check = ALT_COND_ALWAYS | ((num_cpus == 1) ? ALT_COND_NO_SMP : 0) | @@ -45,8 +45,9 @@ void __init_or_module apply_alternatives(struct alt_instr *start, for (entry = start; entry < end; entry++, index++) { - u32 *from, cond, replacement; - s32 len; + u32 *from, replacement; + u16 cond; + s16 len; from = (u32 *)((ulong)&entry->orig_offset + entry->orig_offset); len = entry->len; -- cgit From 027c3d345e2a1ea61d6e4506a250eb392e6e7b18 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 1 Oct 2022 00:32:07 +0200 Subject: parisc: Convert PDC console to an early console Rewrite the PDC console to become an early console. Beside the fact that now boot information is visible until another (text- or graphics) console takes over, this benefits as well machines with a yet-unsupported STI console and kgdb. Signed-off-by: Helge Deller --- arch/parisc/include/asm/pdc.h | 3 - arch/parisc/kernel/pdc_cons.c | 240 +++++------------------------------------- arch/parisc/kernel/setup.c | 6 +- arch/parisc/kernel/traps.c | 15 +-- drivers/tty/serial/Kconfig | 15 --- lib/Kconfig.kgdb | 2 +- 6 files changed, 32 insertions(+), 249 deletions(-) diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h index b643092d4b98..fcbcf9a96c11 100644 --- a/arch/parisc/include/asm/pdc.h +++ b/arch/parisc/include/asm/pdc.h @@ -19,9 +19,6 @@ extern unsigned long parisc_pat_pdc_cap; /* PDC capabilities (PAT) */ #define PDC_TYPE_SYSTEM_MAP 1 /* 32-bit, but supports PDC_SYSTEM_MAP */ #define PDC_TYPE_SNAKE 2 /* Doesn't support SYSTEM_MAP */ -void pdc_console_init(void); /* in pdc_console.c */ -void pdc_console_restart(void); - void setup_pdc(void); /* in inventory.c */ /* wrapper-functions from pdc.c */ diff --git a/arch/parisc/kernel/pdc_cons.c b/arch/parisc/kernel/pdc_cons.c index 2661cdd256ae..7d0989f523d0 100644 --- a/arch/parisc/kernel/pdc_cons.c +++ b/arch/parisc/kernel/pdc_cons.c @@ -1,46 +1,18 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * PDC Console support - ie use firmware to dump text via boot console + * PDC early console support - use PDC firmware to dump text via boot console * - * Copyright (C) 1999-2003 Matthew Wilcox - * Copyright (C) 2000 Martin K Petersen - * Copyright (C) 2000 John Marvin - * Copyright (C) 2000-2003 Paul Bame - * Copyright (C) 2000 Philipp Rumpf - * Copyright (C) 2000 Michael Ang - * Copyright (C) 2000 Grant Grundler - * Copyright (C) 2001-2002 Ryan Bradetich - * Copyright (C) 2001 Helge Deller - * Copyright (C) 2001 Thomas Bogendoerfer - * Copyright (C) 2002 Randolph Chung - * Copyright (C) 2010 Guy Martin + * Copyright (C) 2001-2022 Helge Deller */ -/* - * The PDC console is a simple console, which can be used for debugging - * boot related problems on HP PA-RISC machines. It is also useful when no - * other console works. - * - * This code uses the ROM (=PDC) based functions to read and write characters - * from and to PDC's boot path. - */ - -/* Define EARLY_BOOTUP_DEBUG to debug kernel related boot problems. - * On production kernels EARLY_BOOTUP_DEBUG should be undefined. */ -#define EARLY_BOOTUP_DEBUG - - -#include #include -#include #include -#include -#include +#include +#include #include /* for PAGE0 */ #include /* for iodc_call() proto and friends */ static DEFINE_SPINLOCK(pdc_console_lock); -static struct console pdc_cons; static void pdc_console_write(struct console *co, const char *s, unsigned count) { @@ -54,7 +26,8 @@ static void pdc_console_write(struct console *co, const char *s, unsigned count) spin_unlock_irqrestore(&pdc_console_lock, flags); } -int pdc_console_poll_key(struct console *co) +#ifdef CONFIG_KGDB +static int kgdb_pdc_read_char(void) { int c; unsigned long flags; @@ -63,201 +36,40 @@ int pdc_console_poll_key(struct console *co) c = pdc_iodc_getc(); spin_unlock_irqrestore(&pdc_console_lock, flags); - return c; -} - -static int pdc_console_setup(struct console *co, char *options) -{ - return 0; -} - -#if defined(CONFIG_PDC_CONSOLE) -#include -#include - -#define PDC_CONS_POLL_DELAY (30 * HZ / 1000) - -static void pdc_console_poll(struct timer_list *unused); -static DEFINE_TIMER(pdc_console_timer, pdc_console_poll); -static struct tty_port tty_port; - -static int pdc_console_tty_open(struct tty_struct *tty, struct file *filp) -{ - tty_port_tty_set(&tty_port, tty); - mod_timer(&pdc_console_timer, jiffies + PDC_CONS_POLL_DELAY); - - return 0; + return (c <= 0) ? NO_POLL_CHAR : c; } -static void pdc_console_tty_close(struct tty_struct *tty, struct file *filp) +static void kgdb_pdc_write_char(u8 chr) { - if (tty->count == 1) { - del_timer_sync(&pdc_console_timer); - tty_port_tty_set(&tty_port, NULL); - } + if (PAGE0->mem_cons.cl_class != CL_DUPLEX) + pdc_console_write(NULL, &chr, 1); } -static int pdc_console_tty_write(struct tty_struct *tty, const unsigned char *buf, int count) -{ - pdc_console_write(NULL, buf, count); - return count; -} - -static unsigned int pdc_console_tty_write_room(struct tty_struct *tty) -{ - return 32768; /* no limit, no buffer used */ -} - -static const struct tty_operations pdc_console_tty_ops = { - .open = pdc_console_tty_open, - .close = pdc_console_tty_close, - .write = pdc_console_tty_write, - .write_room = pdc_console_tty_write_room, +static struct kgdb_io kgdb_pdc_io_ops = { + .name = "kgdb_pdc", + .read_char = kgdb_pdc_read_char, + .write_char = kgdb_pdc_write_char, }; - -static void pdc_console_poll(struct timer_list *unused) -{ - int data, count = 0; - - while (1) { - data = pdc_console_poll_key(NULL); - if (data == -1) - break; - tty_insert_flip_char(&tty_port, data & 0xFF, TTY_NORMAL); - count ++; - } - - if (count) - tty_flip_buffer_push(&tty_port); - - if (pdc_cons.flags & CON_ENABLED) - mod_timer(&pdc_console_timer, jiffies + PDC_CONS_POLL_DELAY); -} - -static struct tty_driver *pdc_console_tty_driver; - -static int __init pdc_console_tty_driver_init(void) -{ - struct tty_driver *driver; - int err; - - /* Check if the console driver is still registered. - * It is unregistered if the pdc console was not selected as the - * primary console. */ - - struct console *tmp; - - console_lock(); - for_each_console(tmp) - if (tmp == &pdc_cons) - break; - console_unlock(); - - if (!tmp) { - printk(KERN_INFO "PDC console driver not registered anymore, not creating %s\n", pdc_cons.name); - return -ENODEV; - } - - printk(KERN_INFO "The PDC console driver is still registered, removing CON_BOOT flag\n"); - pdc_cons.flags &= ~CON_BOOT; - - driver = tty_alloc_driver(1, TTY_DRIVER_REAL_RAW | - TTY_DRIVER_RESET_TERMIOS); - if (IS_ERR(driver)) - return PTR_ERR(driver); - - tty_port_init(&tty_port); - - driver->driver_name = "pdc_cons"; - driver->name = "ttyB"; - driver->major = MUX_MAJOR; - driver->minor_start = 0; - driver->type = TTY_DRIVER_TYPE_SYSTEM; - driver->init_termios = tty_std_termios; - tty_set_operations(driver, &pdc_console_tty_ops); - tty_port_link_device(&tty_port, driver, 0); - - err = tty_register_driver(driver); - if (err) { - printk(KERN_ERR "Unable to register the PDC console TTY driver\n"); - tty_port_destroy(&tty_port); - tty_driver_kref_put(driver); - return err; - } - - pdc_console_tty_driver = driver; - - return 0; -} -device_initcall(pdc_console_tty_driver_init); - -static struct tty_driver * pdc_console_device (struct console *c, int *index) -{ - *index = c->index; - return pdc_console_tty_driver; -} -#else -#define pdc_console_device NULL #endif -static struct console pdc_cons = { - .name = "ttyB", - .write = pdc_console_write, - .device = pdc_console_device, - .setup = pdc_console_setup, - .flags = CON_BOOT | CON_PRINTBUFFER, - .index = -1, -}; - -static int pdc_console_initialized; - -static void pdc_console_init_force(void) +static int __init pdc_earlycon_setup(struct earlycon_device *device, + const char *opt) { - if (pdc_console_initialized) - return; - ++pdc_console_initialized; - + struct console *earlycon_console; + /* If the console is duplex then copy the COUT parameters to CIN. */ if (PAGE0->mem_cons.cl_class == CL_DUPLEX) memcpy(&PAGE0->mem_kbd, &PAGE0->mem_cons, sizeof(PAGE0->mem_cons)); - /* register the pdc console */ - register_console(&pdc_cons); -} + earlycon_console = device->con; + earlycon_console->write = pdc_console_write; + device->port.iotype = UPIO_MEM32BE; -void __init pdc_console_init(void) -{ -#if defined(EARLY_BOOTUP_DEBUG) || defined(CONFIG_PDC_CONSOLE) - pdc_console_init_force(); +#ifdef CONFIG_KGDB + kgdb_register_io_module(&kgdb_pdc_io_ops); #endif -#ifdef EARLY_BOOTUP_DEBUG - printk(KERN_INFO "Initialized PDC Console for debugging.\n"); -#endif -} - - -/* - * Used for emergencies. Currently only used if an HPMC occurs. If an - * HPMC occurs, it is possible that the current console may not be - * properly initialised after the PDC IO reset. This routine unregisters - * all of the current consoles, reinitializes the pdc console and - * registers it. - */ - -void pdc_console_restart(void) -{ - struct console *console; - - if (pdc_console_initialized) - return; - /* If we've already seen the output, don't bother to print it again */ - if (console_drivers != NULL) - pdc_cons.flags &= ~CON_PRINTBUFFER; - - while ((console = console_drivers) != NULL) - unregister_console(console_drivers); - - /* force registering the pdc console */ - pdc_console_init_force(); + return 0; } + +EARLYCON_DECLARE(pdc, pdc_earlycon_setup); diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index f005ddedb50e..375f38d6e1a4 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -70,6 +70,10 @@ void __init setup_cmdline(char **cmdline_p) strlcat(p, "tty0", COMMAND_LINE_SIZE); } + /* default to use early console */ + if (!strstr(p, "earlycon")) + strlcat(p, " earlycon=pdc", COMMAND_LINE_SIZE); + #ifdef CONFIG_BLK_DEV_INITRD if (boot_args[2] != 0) /* did palo pass us a ramdisk? */ { @@ -139,8 +143,6 @@ void __init setup_arch(char **cmdline_p) if (__pa((unsigned long) &_end) >= KERNEL_INITIAL_SIZE) panic("KERNEL_INITIAL_ORDER too small!"); - pdc_console_init(); - #ifdef CONFIG_64BIT if(parisc_narrow_firmware) { printk(KERN_INFO "Kernel is using PDC in 32-bit mode.\n"); diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index b78f1b9d45c1..f9696fbf646c 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -239,13 +239,6 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) /* unlock the pdc lock if necessary */ pdc_emergency_unlock(); - /* maybe the kernel hasn't booted very far yet and hasn't been able - * to initialize the serial or STI console. In that case we should - * re-enable the pdc console, so that the user will be able to - * identify the problem. */ - if (!console_drivers) - pdc_console_restart(); - if (err) printk(KERN_CRIT "%s (pid %d): %s (code %ld)\n", current->comm, task_pid_nr(current), str, err); @@ -429,10 +422,6 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o /* unlock the pdc lock if necessary */ pdc_emergency_unlock(); - /* restart pdc console if necessary */ - if (!console_drivers) - pdc_console_restart(); - /* Not all paths will gutter the processor... */ switch(code){ @@ -482,9 +471,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) unsigned long fault_space = 0; int si_code; - if (code == 1) - pdc_console_restart(); /* switch back to pdc if HPMC */ - else if (!irqs_disabled_flags(regs->gr[0])) + if (!irqs_disabled_flags(regs->gr[0])) local_irq_enable(); /* Security check: diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 877173907c53..898728ab2c18 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -602,21 +602,6 @@ config SERIAL_MUX_CONSOLE select SERIAL_CORE_CONSOLE default y -config PDC_CONSOLE - bool "PDC software console support" - depends on PARISC && !SERIAL_MUX && VT - help - Saying Y here will enable the software based PDC console to be - used as the system console. This is useful for machines in - which the hardware based console has not been written yet. The - following steps must be completed to use the PDC console: - - 1. create the device entry (mknod /dev/ttyB0 c 11 0) - 2. Edit the /etc/inittab to start a getty listening on /dev/ttyB0 - 3. Add device ttyB0 to /etc/securetty (if you want to log on as - root on this console.) - 4. Change the kernel command console parameter to: console=ttyB0 - config SERIAL_SUNSAB tristate "Sun Siemens SAB82532 serial support" depends on SPARC && PCI diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index 05dae05b6cc9..3b9a44008433 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -121,7 +121,7 @@ config KDB_DEFAULT_ENABLE config KDB_KEYBOARD bool "KGDB_KDB: keyboard as input device" - depends on VT && KGDB_KDB + depends on VT && KGDB_KDB && !PARISC default n help KDB can use a PS/2 type keyboard for an input device -- cgit From 9971a741c5f44fd72e664c35be9bc6fedb8a3498 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Tue, 27 Sep 2022 09:30:39 -0700 Subject: btrfs: send: allow protocol version 3 with CONFIG_BTRFS_DEBUG We haven't finalized send stream v3 yet, so gate the send stream version behind CONFIG_BTRFS_DEBUG as we want some way to test it. The original verity send did not check the protocol version, so add that actual protection as well. Reviewed-by: Anand Jain Signed-off-by: Boris Burkov Signed-off-by: David Sterba --- fs/btrfs/send.c | 2 +- fs/btrfs/send.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4ef4167072b8..178347666235 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6469,7 +6469,7 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (ret < 0) goto out; } - if (sctx->cur_inode_needs_verity) { + if (sctx->proto >= 3 && sctx->cur_inode_needs_verity) { ret = process_verity(sctx); if (ret < 0) goto out; diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h index 0a4537775e0c..f7585cfa7e52 100644 --- a/fs/btrfs/send.h +++ b/fs/btrfs/send.h @@ -10,7 +10,12 @@ #include #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream" +/* Conditional support for the upcoming protocol version. */ +#ifdef CONFIG_BTRFS_DEBUG +#define BTRFS_SEND_STREAM_VERSION 3 +#else #define BTRFS_SEND_STREAM_VERSION 2 +#endif /* * In send stream v1, no command is larger than 64K. In send stream v2, no limit -- cgit From c86eab81a23f368d08efd3df96a95f3d0b471f85 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 7 Oct 2022 17:10:02 +0200 Subject: btrfs: send: update command for protocol version check For a protocol and command compatibility we have a helper that hasn't been updated for v3 yet. We use it for verity so update where necessary. Fixes: 38622010a6de ("btrfs: send: add support for fs-verity") Signed-off-by: David Sterba --- fs/btrfs/send.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 178347666235..ec6e1752af2c 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -348,6 +348,7 @@ static bool proto_cmd_ok(const struct send_ctx *sctx, int cmd) switch (sctx->proto) { case 1: return cmd <= BTRFS_SEND_C_MAX_V1; case 2: return cmd <= BTRFS_SEND_C_MAX_V2; + case 3: return cmd <= BTRFS_SEND_C_MAX_V3; default: return false; } } @@ -6469,7 +6470,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (ret < 0) goto out; } - if (sctx->proto >= 3 && sctx->cur_inode_needs_verity) { + + if (proto_cmd_ok(sctx, BTRFS_SEND_C_ENABLE_VERITY) + && sctx->cur_inode_needs_verity) { ret = process_verity(sctx); if (ret < 0) goto out; -- cgit From 9e769bd7e5db5e3bd76e7c67004c261f7fcaa8f1 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 30 Sep 2022 16:45:08 -0400 Subject: btrfs: unlock locked extent area if we have contention In production we hit the following deadlock task 1 task 2 task 3 ------ ------ ------ fiemap(file) falloc(file) fsync(file) write(0, 1MiB) btrfs_commit_transaction() wait_on(!pending_ordered) lock(512MiB, 1GiB) start_transaction wait_on_transaction lock(0, 1GiB) wait_extent_bit(512MiB) task 4 ------ finish_ordered_extent(0, 1MiB) lock(0, 1MiB) **DEADLOCK** This occurs because when task 1 does it's lock, it locks everything from 0-512MiB, and then waits for the 512MiB chunk to unlock. task 2 will never unlock because it's waiting on the transaction commit to happen, the transaction commit is waiting for the outstanding ordered extents, and then the ordered extent thread is blocked waiting on the 0-1MiB range to unlock. To fix this we have to clear anything we've locked so far, wait for the extent_state that we contended on, and then try to re-lock the entire range again. CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Filipe Manana Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/extent-io-tree.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c index 618275af19c4..83cb0378096f 100644 --- a/fs/btrfs/extent-io-tree.c +++ b/fs/btrfs/extent-io-tree.c @@ -1641,16 +1641,17 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, int err; u64 failed_start; - while (1) { + err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start, + cached_state, NULL, GFP_NOFS); + while (err == -EEXIST) { + if (failed_start != start) + clear_extent_bit(tree, start, failed_start - 1, + EXTENT_LOCKED, cached_state); + + wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED); err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start, cached_state, NULL, GFP_NOFS); - if (err == -EEXIST) { - wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED); - start = failed_start; - } else - break; - WARN_ON(start > end); } return err; } -- cgit From 295a53ccc4ca8383f6d107534b466b91aa013f79 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 11 Oct 2022 11:25:33 +0200 Subject: btrfs: delete stale comments after merge conflict resolution There are two comments in btrfs_cache_block_group that I left when resolving conflict between commits ced8ecf026fd8 "btrfs: fix space cache corruption and potential double allocations" and 527c490f44f6f "btrfs: delete btrfs_wait_space_cache_v1_finished". The former reworked the caching logic to wait until the caching ends in btrfs_cache_block_group while the latter only open coded the waiting. Both removed btrfs_wait_space_cache_v1_finished, the correct code is with the waiting and returning error. Thus the conflict resolution was OK. Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 32c415cfbdfe..deebc8ddbd93 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -774,10 +774,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work); out: - /* REVIEW */ if (wait && caching_ctl) ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); - /* wait_event(caching_ctl->wait, space_cache_v1_done(cache)); */ if (caching_ctl) btrfs_put_caching_control(caching_ctl); -- cgit From 4fc7b57228243d09c0d878873bf24fa64a90fa01 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 11 Oct 2022 13:16:51 +0100 Subject: btrfs: fix processing of delayed data refs during backref walking When processing delayed data references during backref walking and we are using a share context (we are being called through fiemap), whenever we find a delayed data reference for an inode different from the one we are interested in, then we immediately exit and consider the data extent as shared. This is wrong, because: 1) This might be a DROP reference that will cancel out a reference in the extent tree; 2) Even if it's an ADD reference, it may be followed by a DROP reference that cancels it out. In either case we should not exit immediately. Fix this by never exiting when we find a delayed data reference for another inode - instead add the reference and if it does not cancel out other delayed reference, we will exit early when we call extent_is_shared() after processing all delayed references. If we find a drop reference, then signal the code that processes references from the extent tree (add_inline_refs() and add_keyed_refs()) to not exit immediately if it finds there a reference for another inode, since we have delayed drop references that may cancel it out. In this later case we exit once we don't have references in the rb trees that cancel out each other and have two references for different inodes. Example reproducer for case 1): $ cat test-1.sh #!/bin/bash DEV=/dev/sdj MNT=/mnt/sdj mkfs.btrfs -f $DEV mount $DEV $MNT xfs_io -f -c "pwrite 0 64K" $MNT/foo cp --reflink=always $MNT/foo $MNT/bar echo echo "fiemap after cloning:" xfs_io -c "fiemap -v" $MNT/foo rm -f $MNT/bar echo echo "fiemap after removing file bar:" xfs_io -c "fiemap -v" $MNT/foo umount $MNT Running it before this patch, the extent is still listed as shared, it has the flag 0x2000 (FIEMAP_EXTENT_SHARED) set: $ ./test-1.sh fiemap after cloning: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 fiemap after removing file bar: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 Example reproducer for case 2): $ cat test-2.sh #!/bin/bash DEV=/dev/sdj MNT=/mnt/sdj mkfs.btrfs -f $DEV mount $DEV $MNT xfs_io -f -c "pwrite 0 64K" $MNT/foo cp --reflink=always $MNT/foo $MNT/bar # Flush delayed references to the extent tree and commit current # transaction. sync echo echo "fiemap after cloning:" xfs_io -c "fiemap -v" $MNT/foo rm -f $MNT/bar echo echo "fiemap after removing file bar:" xfs_io -c "fiemap -v" $MNT/foo umount $MNT Running it before this patch, the extent is still listed as shared, it has the flag 0x2000 (FIEMAP_EXTENT_SHARED) set: $ ./test-2.sh fiemap after cloning: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 fiemap after removing file bar: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 After this patch, after deleting bar in both tests, the extent is not reported with the 0x2000 flag anymore, it gets only the flag 0x1 (which is FIEMAP_EXTENT_LAST): $ ./test-1.sh fiemap after cloning: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 fiemap after removing file bar: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x1 $ ./test-2.sh fiemap after cloning: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x2001 fiemap after removing file bar: /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [0..127]: 26624..26751 128 0x1 These tests will later be converted to a test case for fstests. Fixes: dc046b10c8b7d4 ("Btrfs: make fiemap not blow when you have lots of snapshots") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/backref.c | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 3c0c1f626c75..cf47dabb786f 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -138,6 +138,7 @@ struct share_check { u64 root_objectid; u64 inum; int share_count; + bool have_delayed_delete_refs; }; static inline int extent_is_shared(struct share_check *sc) @@ -884,13 +885,22 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, key.offset = ref->offset; /* - * Found a inum that doesn't match our known inum, we - * know it's shared. + * If we have a share check context and a reference for + * another inode, we can't exit immediately. This is + * because even if this is a BTRFS_ADD_DELAYED_REF + * reference we may find next a BTRFS_DROP_DELAYED_REF + * which cancels out this ADD reference. + * + * If this is a DROP reference and there was no previous + * ADD reference, then we need to signal that when we + * process references from the extent tree (through + * add_inline_refs() and add_keyed_refs()), we should + * not exit early if we find a reference for another + * inode, because one of the delayed DROP references + * may cancel that reference in the extent tree. */ - if (sc && sc->inum && ref->objectid != sc->inum) { - ret = BACKREF_FOUND_SHARED; - goto out; - } + if (sc && count < 0) + sc->have_delayed_delete_refs = true; ret = add_indirect_ref(fs_info, preftrees, ref->root, &key, 0, node->bytenr, count, sc, @@ -920,7 +930,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, } if (!ret) ret = extent_is_shared(sc); -out: + spin_unlock(&head->lock); return ret; } @@ -1023,7 +1033,8 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -1033,6 +1044,7 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, ret = add_indirect_ref(fs_info, preftrees, root, &key, 0, bytenr, count, sc, GFP_NOFS); + break; } default: @@ -1122,7 +1134,8 @@ static int add_keyed_refs(struct btrfs_root *extent_root, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -1661,6 +1674,7 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr, .root_objectid = root->root_key.objectid, .inum = inum, .share_count = 0, + .have_delayed_delete_refs = false, }; int level; @@ -1726,6 +1740,7 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr, break; } shared.share_count = 0; + shared.have_delayed_delete_refs = false; cond_resched(); } -- cgit From 943553ef9b51db303ab2b955c1025261abfdf6fb Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 11 Oct 2022 13:16:52 +0100 Subject: btrfs: fix processing of delayed tree block refs during backref walking During backref walking, when processing a delayed reference with a type of BTRFS_TREE_BLOCK_REF_KEY, we have two bugs there: 1) We are accessing the delayed references extent_op, and its key, without the protection of the delayed ref head's lock; 2) If there's no extent op for the delayed ref head, we end up with an uninitialized key in the stack, variable 'tmp_op_key', and then pass it to add_indirect_ref(), which adds the reference to the indirect refs rb tree. This is wrong, because indirect references should have a NULL key when we don't have access to the key, and in that case they should be added to the indirect_missing_keys rb tree and not to the indirect rb tree. This means that if have BTRFS_TREE_BLOCK_REF_KEY delayed ref resulting from freeing an extent buffer, therefore with a count of -1, it will not cancel out the corresponding reference we have in the extent tree (with a count of 1), since both references end up in different rb trees. When using fiemap, where we often need to check if extents are shared through shared subtrees resulting from snapshots, it means we can incorrectly report an extent as shared when it's no longer shared. However this is temporary because after the transaction is committed the extent is no longer reported as shared, as running the delayed reference results in deleting the tree block reference from the extent tree. Outside the fiemap context, the result is unpredictable, as the key was not initialized but it's used when navigating the rb trees to insert and search for references (prelim_ref_compare()), and we expect all references in the indirect rb tree to have valid keys. The following reproducer triggers the second bug: $ cat test.sh #!/bin/bash DEV=/dev/sdj MNT=/mnt/sdj mkfs.btrfs -f $DEV mount -o compress $DEV $MNT # With a compressed 128M file we get a tree height of 2 (level 1 root). xfs_io -f -c "pwrite -b 1M 0 128M" $MNT/foo btrfs subvolume snapshot $MNT $MNT/snap # Fiemap should output 0x2008 in the flags column. # 0x2000 means shared extent # 0x8 means encoded extent (because it's compressed) echo echo "fiemap after snapshot, range [120M, 120M + 128K):" xfs_io -c "fiemap -v 120M 128K" $MNT/foo echo # Overwrite one extent and fsync to flush delalloc and COW a new path # in the snapshot's tree. # # After this we have a BTRFS_DROP_DELAYED_REF delayed ref of type # BTRFS_TREE_BLOCK_REF_KEY with a count of -1 for every COWed extent # buffer in the path. # # In the extent tree we have inline references of type # BTRFS_TREE_BLOCK_REF_KEY, with a count of 1, for the same extent # buffers, so they should cancel each other, and the extent buffers in # the fs tree should no longer be considered as shared. # echo "Overwriting file range [120M, 120M + 128K)..." xfs_io -c "pwrite -b 128K 120M 128K" $MNT/snap/foo xfs_io -c "fsync" $MNT/snap/foo # Fiemap should output 0x8 in the flags column. The extent in the range # [120M, 120M + 128K) is no longer shared, it's now exclusive to the fs # tree. echo echo "fiemap after overwrite range [120M, 120M + 128K):" xfs_io -c "fiemap -v 120M 128K" $MNT/foo echo umount $MNT Running it before this patch: $ ./test.sh (...) wrote 134217728/134217728 bytes at offset 0 128 MiB, 128 ops; 0.1152 sec (1.085 GiB/sec and 1110.5809 ops/sec) Create a snapshot of '/mnt/sdj' in '/mnt/sdj/snap' fiemap after snapshot, range [120M, 120M + 128K): /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [245760..246015]: 34304..34559 256 0x2008 Overwriting file range [120M, 120M + 128K)... wrote 131072/131072 bytes at offset 125829120 128 KiB, 1 ops; 0.0001 sec (683.060 MiB/sec and 5464.4809 ops/sec) fiemap after overwrite range [120M, 120M + 128K): /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [245760..246015]: 34304..34559 256 0x2008 The extent in the range [120M, 120M + 128K) is still reported as shared (0x2000 bit set) after overwriting that range and flushing delalloc, which is not correct - an entire path was COWed in the snapshot's tree and the extent is now only referenced by the original fs tree. Running it after this patch: $ ./test.sh (...) wrote 134217728/134217728 bytes at offset 0 128 MiB, 128 ops; 0.1198 sec (1.043 GiB/sec and 1068.2067 ops/sec) Create a snapshot of '/mnt/sdj' in '/mnt/sdj/snap' fiemap after snapshot, range [120M, 120M + 128K): /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [245760..246015]: 34304..34559 256 0x2008 Overwriting file range [120M, 120M + 128K)... wrote 131072/131072 bytes at offset 125829120 128 KiB, 1 ops; 0.0001 sec (694.444 MiB/sec and 5555.5556 ops/sec) fiemap after overwrite range [120M, 120M + 128K): /mnt/sdj/foo: EXT: FILE-OFFSET BLOCK-RANGE TOTAL FLAGS 0: [245760..246015]: 34304..34559 256 0x8 Now the extent is not reported as shared anymore. So fix this by passing a NULL key pointer to add_indirect_ref() when processing a delayed reference for a tree block if there's no extent op for our delayed ref head with a defined key. Also access the extent op only after locking the delayed ref head's lock. The reproducer will be converted later to a test case for fstests. Fixes: 86d5f994425252 ("btrfs: convert prelimary reference tracking to use rbtrees") Fixes: a6dbceafb915e8 ("btrfs: Remove unused op_key var from add_delayed_refs") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/backref.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index cf47dabb786f..4e29ccb234c0 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -821,16 +821,11 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, struct preftrees *preftrees, struct share_check *sc) { struct btrfs_delayed_ref_node *node; - struct btrfs_delayed_extent_op *extent_op = head->extent_op; struct btrfs_key key; - struct btrfs_key tmp_op_key; struct rb_node *n; int count; int ret = 0; - if (extent_op && extent_op->update_key) - btrfs_disk_key_to_cpu(&tmp_op_key, &extent_op->key); - spin_lock(&head->lock); for (n = rb_first_cached(&head->ref_tree); n; n = rb_next(n)) { node = rb_entry(n, struct btrfs_delayed_ref_node, @@ -856,10 +851,16 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, case BTRFS_TREE_BLOCK_REF_KEY: { /* NORMAL INDIRECT METADATA backref */ struct btrfs_delayed_tree_ref *ref; + struct btrfs_key *key_ptr = NULL; + + if (head->extent_op && head->extent_op->update_key) { + btrfs_disk_key_to_cpu(&key, &head->extent_op->key); + key_ptr = &key; + } ref = btrfs_delayed_node_to_tree_ref(node); ret = add_indirect_ref(fs_info, preftrees, ref->root, - &tmp_op_key, ref->level + 1, + key_ptr, ref->level + 1, node->bytenr, count, sc, GFP_ATOMIC); break; -- cgit From 63c84b46b3b75798f1ad63527b6250de00331907 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 11 Oct 2022 13:16:53 +0100 Subject: btrfs: ignore fiemap path cache if we have multiple leaves for a data extent The path cache used during fiemap used to determine the sharedness of extent buffers in a path from a leaf containing a file extent item pointing to our data extent up to the root node of the tree, is meant to be used for a single path. Having a single path is by far the most common case, and therefore worth to optimize for, but it's possible to actually have multiple paths because we have 2 or more leaves. If we have multiple leaves, the 'level' variable keeps getting incremented in each iteration of the while loop at btrfs_is_data_extent_shared(), which means we will treat the second leaf in the 'tmp' ulist as a level 1 node, and so forth. In the worst case this can lead to getting a level greater than or equals to BTRFS_MAX_LEVEL (8), which will trigger a WARN_ON_ONCE() in the functions to lookup from or store in the path cache (lookup_backref_shared_cache() and store_backref_shared_cache()). If the current level never goes beyond 8, due to shared nodes in the paths and a fs tree height smaller than 8, it can still result in incorrectly marking one leaf as shared because some other leaf is shared and is stored one level below that other leaf, as when storing a true sharedness value in the cache results in updating the sharedness to true of all entries in the cache below the current level. Having multiple leaves happens in a case like the following: - We have a file extent item point to data extent at bytenr X, for a file range [0, 1M[ for example; - At this moment we have an extent data ref for the extent, with an offset of 0 and a count of 1; - A write into the middle of the extent happens, file range [64K, 128K) so the file extent item is split into two (at btrfs_drop_extents()): 1) One for file range [0, 64K), with a length (num_bytes field) of 64K and an extent offset of 0; 2) Another one for file range [128K, 1M), with a length of 896K (1M - 128K) and an extent offset of 128K. - At this moment the two file extent items are located in the same leaf; - A new file extent item for the range [64K, 128K), pointing to a new data extent, is inserted in the leaf. This results in a leaf split and now those two file extent items pointing to data extent X end up located in different leaves; - Once delayed refs are run, we still have a single extent data ref item for our data extent at bytenr X, for offset 0, but now with a count of 2 instead of 1; - So during fiemap, at btrfs_is_data_extent_shared(), after we call find_parent_nodes() for the data extent, we get two leaves, since we have two file extent items point to data extent at bytenr X that are located in two different leaves. So skip the use of the path cache when we get more than one leaf. Fixes: 12a824dc67a61e ("btrfs: speedup checking for extent sharedness during fiemap") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/backref.c | 25 +++++++++++++++++++++++++ fs/btrfs/backref.h | 1 + 2 files changed, 26 insertions(+) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 4e29ccb234c0..4ec18ceb2f21 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1536,6 +1536,9 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_shared_cache *cache { struct btrfs_backref_shared_cache_entry *entry; + if (!cache->use_cache) + return false; + if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL)) return false; @@ -1600,6 +1603,9 @@ static void store_backref_shared_cache(struct btrfs_backref_shared_cache *cache, struct btrfs_backref_shared_cache_entry *entry; u64 gen; + if (!cache->use_cache) + return; + if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL)) return; @@ -1697,6 +1703,7 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr, /* -1 means we are in the bytenr of the data extent. */ level = -1; ULIST_ITER_INIT(&uiter); + cache->use_cache = true; while (1) { bool is_shared; bool cached; @@ -1726,6 +1733,24 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr, extent_gen > btrfs_root_last_snapshot(&root->root_item)) break; + /* + * If our data extent was not directly shared (without multiple + * reference items), than it might have a single reference item + * with a count > 1 for the same offset, which means there are 2 + * (or more) file extent items that point to the data extent - + * this happens when a file extent item needs to be split and + * then one item gets moved to another leaf due to a b+tree leaf + * split when inserting some item. In this case the file extent + * items may be located in different leaves and therefore some + * of the leaves may be referenced through shared subtrees while + * others are not. Since our extent buffer cache only works for + * a single path (by far the most common case and simpler to + * deal with), we can not use it if we have multiple leaves + * (which implies multiple paths). + */ + if (level == -1 && tmp->nnodes > 1) + cache->use_cache = false; + if (level >= 0) store_backref_shared_cache(cache, root, bytenr, level, false); diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index 52ae6957b414..8e69584d538d 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -29,6 +29,7 @@ struct btrfs_backref_shared_cache { * a given data extent should never exceed the maximum b+tree height. */ struct btrfs_backref_shared_cache_entry entries[BTRFS_MAX_LEVEL]; + bool use_cache; }; typedef int (iterate_extent_inodes_t)(u64 inum, u64 offset, u64 root, -- cgit From 6e141772e6465f937458b35ddcfd0a981b6f5280 Mon Sep 17 00:00:00 2001 From: Wenchao Chen Date: Tue, 11 Oct 2022 18:49:35 +0800 Subject: mmc: sdhci-sprd: Fix minimum clock limit The Spreadtrum controller supports 100KHz minimal clock rate, which means that the current value 400KHz is wrong. Unfortunately this has also lead to fail to initialize some cards, which are allowed to require 100KHz to work. So, let's fix the problem by changing the minimal supported clock rate to 100KHz. Signed-off-by: Wenchao Chen Acked-by: Adrian Hunter Fixes: fb8bd90f83c4 ("mmc: sdhci-sprd: Add Spreadtrum's initial host controller") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221011104935.10980-1-wenchao.chen666@gmail.com [Ulf: Clarified to commit-message] Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-sprd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 46c55ab4884c..b92a408f138d 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -309,7 +309,7 @@ static unsigned int sdhci_sprd_get_max_clock(struct sdhci_host *host) static unsigned int sdhci_sprd_get_min_clock(struct sdhci_host *host) { - return 400000; + return 100000; } static void sdhci_sprd_set_uhs_signaling(struct sdhci_host *host, -- cgit From 6c482c62a635aa4f534d2439fbf8afa37452b986 Mon Sep 17 00:00:00 2001 From: Thomas Hellström Date: Wed, 5 Oct 2022 14:11:59 +0200 Subject: drm/i915: Fix display problems after resume MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 39a2bd34c933 ("drm/i915: Use the vma resource as argument for gtt binding / unbinding") introduced a regression that due to the vma resource tracking of the binding state, dpt ptes were not correctly repopulated. Fix this by clearing the vma resource state before repopulating. The state will subsequently be restored by the bind_vma operation. Fixes: 39a2bd34c933 ("drm/i915: Use the vma resource as argument for gtt binding / unbinding") Signed-off-by: Thomas Hellström Link: https://patchwork.freedesktop.org/patch/msgid/20220912121957.31310-1-thomas.hellstrom@linux.intel.com Cc: Matthew Auld Cc: intel-gfx@lists.freedesktop.org Cc: # v5.18+ Reported-and-tested-by: Kevin Boulain Tested-by: David de Sousa Reviewed-by: Matthew Auld Reviewed-by: Andrzej Hajda Signed-off-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20221005121159.340245-1-thomas.hellstrom@linux.intel.com (cherry picked from commit bc2472538c0d1cce334ffc9e97df0614cd2b1469) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/gt/intel_ggtt.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 30cf5c3369d9..2049a00417af 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -1275,10 +1275,16 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm) atomic_read(&vma->flags) & I915_VMA_BIND_MASK; GEM_BUG_ON(!was_bound); - if (!retained_ptes) + if (!retained_ptes) { + /* + * Clear the bound flags of the vma resource to allow + * ptes to be repopulated. + */ + vma->resource->bound_flags = 0; vma->ops->bind_vma(vm, NULL, vma->resource, obj ? obj->cache_level : 0, was_bound); + } if (obj) { /* only used during resume => exclusive access */ write_domain_objs |= fetch_and_zero(&obj->write_domain); obj->read_domains |= I915_GEM_DOMAIN_GTT; -- cgit From cdbb816b5bfeb69ad925805d99b2ec312b241f1c Mon Sep 17 00:00:00 2001 From: Tao Zhou Date: Mon, 26 Sep 2022 17:01:33 +0800 Subject: drm/amdgpu: remove check for CE in RAS error address query Only RAS UE error address is queried currently, no need to check CE status. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/umc_v6_1.c | 10 ++--- drivers/gpu/drm/amd/amdgpu/umc_v6_7.c | 67 ++++++++++++++-------------------- drivers/gpu/drm/amd/amdgpu/umc_v8_10.c | 52 +++++++++++--------------- drivers/gpu/drm/amd/amdgpu/umc_v8_7.c | 20 +++------- 4 files changed, 59 insertions(+), 90 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c index 939cb203f7ad..f17d297b594b 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c @@ -327,10 +327,9 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev, return; } - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); /* the lowest lsb bits should be ignored */ @@ -343,10 +342,7 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev, ADDR_OF_256B_BLOCK(channel_index) | OFFSET_IN_256B_BLOCK(err_addr); - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1) - amdgpu_umc_fill_error_record(err_data, err_addr, + amdgpu_umc_fill_error_record(err_data, err_addr, retired_page, channel_index, umc_inst); } diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c index a0d19b768346..64d760eb92a3 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c @@ -209,10 +209,9 @@ static void umc_v6_7_ecc_info_query_error_address(struct amdgpu_device *adev, if (!err_data->err_addr) return; - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { err_addr = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_addr; err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); @@ -228,22 +227,18 @@ static void umc_v6_7_ecc_info_query_error_address(struct amdgpu_device *adev, /* clear [C4 C3 C2] in soc physical address */ soc_pa &= ~(0x7ULL << UMC_V6_7_PA_C2_BIT); - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1) { - /* loop for all possibilities of [C4 C3 C2] */ - for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { - retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - - /* shift R14 bit */ - retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - } + /* loop for all possibilities of [C4 C3 C2] */ + for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { + retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); + + /* shift R14 bit */ + retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); } } } @@ -481,10 +476,9 @@ static void umc_v6_7_query_error_address(struct amdgpu_device *adev, channel_index = adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) || + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) || mca_addr != UMC_INVALID_ADDR) { if (mca_addr == UMC_INVALID_ADDR) { err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); @@ -505,23 +499,18 @@ static void umc_v6_7_query_error_address(struct amdgpu_device *adev, /* clear [C4 C3 C2] in soc physical address */ soc_pa &= ~(0x7ULL << UMC_V6_7_PA_C2_BIT); - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1 || - mca_addr != UMC_INVALID_ADDR) { - /* loop for all possibilities of [C4 C3 C2] */ - for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { - retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - - /* shift R14 bit */ - retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - } + /* loop for all possibilities of [C4 C3 C2] */ + for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { + retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); + + /* shift R14 bit */ + retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); } } diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c index a8cbda81828d..38f9e29990cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c @@ -208,7 +208,10 @@ static void umc_v8_10_query_error_address(struct amdgpu_device *adev, { uint64_t mc_umc_status_addr; uint64_t mc_umc_status, err_addr; - uint32_t channel_index; + uint64_t mc_umc_addrt0, na_err_addr_base; + uint64_t na_err_addr, retired_page_addr; + uint32_t channel_index, addr_lsb, col = 0; + int ret = 0; mc_umc_status_addr = SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); @@ -229,13 +232,10 @@ static void umc_v8_10_query_error_address(struct amdgpu_device *adev, umc_inst * adev->umc.channel_inst_num + ch_inst]; - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, AddrV) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { - uint32_t addr_lsb; - uint64_t mc_umc_addrt0; + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { mc_umc_addrt0 = SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_ADDRT0); err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); @@ -243,32 +243,24 @@ static void umc_v8_10_query_error_address(struct amdgpu_device *adev, /* the lowest lsb bits should be ignored */ addr_lsb = REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, AddrLsb); - err_addr &= ~((0x1ULL << addr_lsb) - 1); - - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { - uint64_t na_err_addr_base = err_addr & ~(0x3ULL << UMC_V8_10_NA_C5_BIT); - uint64_t na_err_addr, retired_page_addr; - uint32_t col = 0; - int ret = 0; - - /* loop for all possibilities of [C6 C5] in normal address. */ - for (col = 0; col < UMC_V8_10_NA_COL_2BITS_POWER_OF_2_NUM; col++) { - na_err_addr = na_err_addr_base | (col << UMC_V8_10_NA_C5_BIT); - - /* Mapping normal error address to retired soc physical address. */ - ret = umc_v8_10_swizzle_mode_na_to_pa(adev, channel_index, - na_err_addr, &retired_page_addr); - if (ret) { - dev_err(adev->dev, "Failed to map pa from umc na.\n"); - break; - } - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", - retired_page_addr); - amdgpu_umc_fill_error_record(err_data, na_err_addr, - retired_page_addr, channel_index, umc_inst); + na_err_addr_base = err_addr & ~(0x3ULL << UMC_V8_10_NA_C5_BIT); + + /* loop for all possibilities of [C6 C5] in normal address. */ + for (col = 0; col < UMC_V8_10_NA_COL_2BITS_POWER_OF_2_NUM; col++) { + na_err_addr = na_err_addr_base | (col << UMC_V8_10_NA_C5_BIT); + + /* Mapping normal error address to retired soc physical address. */ + ret = umc_v8_10_swizzle_mode_na_to_pa(adev, channel_index, + na_err_addr, &retired_page_addr); + if (ret) { + dev_err(adev->dev, "Failed to map pa from umc na.\n"); + break; } + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", + retired_page_addr); + amdgpu_umc_fill_error_record(err_data, na_err_addr, + retired_page_addr, channel_index, umc_inst); } } diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c index f35253e0eaa6..e2623685cb44 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c @@ -130,10 +130,9 @@ static void umc_v8_7_ecc_info_query_error_address(struct amdgpu_device *adev, if (!err_data->err_addr) return; - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { err_addr = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_addr; err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); @@ -143,10 +142,7 @@ static void umc_v8_7_ecc_info_query_error_address(struct amdgpu_device *adev, ADDR_OF_256B_BLOCK(channel_index) | OFFSET_IN_256B_BLOCK(err_addr); - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1) - amdgpu_umc_fill_error_record(err_data, err_addr, + amdgpu_umc_fill_error_record(err_data, err_addr, retired_page, channel_index, umc_inst); } } @@ -343,10 +339,9 @@ static void umc_v8_7_query_error_address(struct amdgpu_device *adev, return; } - /* calculate error address if ue/ce error is detected */ + /* calculate error address if ue error is detected */ if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) { + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); /* the lowest lsb bits should be ignored */ @@ -359,10 +354,7 @@ static void umc_v8_7_query_error_address(struct amdgpu_device *adev, ADDR_OF_256B_BLOCK(channel_index) | OFFSET_IN_256B_BLOCK(err_addr); - /* we only save ue error information currently, ce is skipped */ - if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) - == 1) - amdgpu_umc_fill_error_record(err_data, err_addr, + amdgpu_umc_fill_error_record(err_data, err_addr, retired_page, channel_index, umc_inst); } -- cgit From 44420ac5f855f5704d8f939926ed145f99e49e55 Mon Sep 17 00:00:00 2001 From: Tao Zhou Date: Tue, 27 Sep 2022 11:36:46 +0800 Subject: drm/amdgpu: define RAS convert_error_address API Make the code reusable and remove redundant code. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h | 7 +- drivers/gpu/drm/amd/amdgpu/umc_v6_7.c | 148 +++++++++++++------------------- 3 files changed, 64 insertions(+), 93 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index ccebd8e2a2d8..c2f9970e851c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2889,7 +2889,7 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb, if (adev->umc.ras && adev->umc.ras->convert_ras_error_address) adev->umc.ras->convert_ras_error_address(adev, - &err_data, 0, ch_inst, umc_inst, m->addr); + &err_data, m->addr, ch_inst, umc_inst); if (amdgpu_bad_page_threshold != 0) { amdgpu_ras_add_bad_pages(adev, err_data.err_addr, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h index 2fb4951a6433..e46439274f3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h @@ -22,8 +22,6 @@ #define __AMDGPU_UMC_H__ #include "amdgpu_ras.h" -#define UMC_INVALID_ADDR 0x1ULL - /* * (addr / 256) * 4096, the higher 26 bits in ErrorAddr * is the index of 4KB block @@ -54,9 +52,8 @@ struct amdgpu_umc_ras { void (*err_cnt_init)(struct amdgpu_device *adev); bool (*query_ras_poison_mode)(struct amdgpu_device *adev); void (*convert_ras_error_address)(struct amdgpu_device *adev, - struct ras_err_data *err_data, - uint32_t umc_reg_offset, uint32_t ch_inst, - uint32_t umc_inst, uint64_t mca_addr); + struct ras_err_data *err_data, uint64_t err_addr, + uint32_t ch_inst, uint32_t umc_inst); void (*ecc_info_query_ras_error_count)(struct amdgpu_device *adev, void *ras_error_status); void (*ecc_info_query_ras_error_address)(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c index 64d760eb92a3..5d5d031c9e7d 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_7.c @@ -187,20 +187,51 @@ static void umc_v6_7_ecc_info_query_ras_error_count(struct amdgpu_device *adev, } } +static void umc_v6_7_convert_error_address(struct amdgpu_device *adev, + struct ras_err_data *err_data, uint64_t err_addr, + uint32_t ch_inst, uint32_t umc_inst) +{ + uint32_t channel_index; + uint64_t soc_pa, retired_page, column; + + channel_index = + adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; + /* translate umc channel address to soc pa, 3 parts are included */ + soc_pa = ADDR_OF_8KB_BLOCK(err_addr) | + ADDR_OF_256B_BLOCK(channel_index) | + OFFSET_IN_256B_BLOCK(err_addr); + + /* The umc channel bits are not original values, they are hashed */ + SET_CHANNEL_HASH(channel_index, soc_pa); + + /* clear [C4 C3 C2] in soc physical address */ + soc_pa &= ~(0x7ULL << UMC_V6_7_PA_C2_BIT); + + /* loop for all possibilities of [C4 C3 C2] */ + for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { + retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); + + /* shift R14 bit */ + retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); + dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); + } +} + static void umc_v6_7_ecc_info_query_error_address(struct amdgpu_device *adev, struct ras_err_data *err_data, uint32_t ch_inst, uint32_t umc_inst) { - uint64_t mc_umc_status, err_addr, soc_pa, retired_page, column; - uint32_t channel_index; + uint64_t mc_umc_status, err_addr; uint32_t eccinfo_table_idx; struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); eccinfo_table_idx = umc_inst * adev->umc.channel_inst_num + ch_inst; - channel_index = - adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; - mc_umc_status = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_status; if (mc_umc_status == 0) @@ -216,30 +247,8 @@ static void umc_v6_7_ecc_info_query_error_address(struct amdgpu_device *adev, err_addr = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_addr; err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); - /* translate umc channel address to soc pa, 3 parts are included */ - soc_pa = ADDR_OF_8KB_BLOCK(err_addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(err_addr); - - /* The umc channel bits are not original values, they are hashed */ - SET_CHANNEL_HASH(channel_index, soc_pa); - - /* clear [C4 C3 C2] in soc physical address */ - soc_pa &= ~(0x7ULL << UMC_V6_7_PA_C2_BIT); - - /* loop for all possibilities of [C4 C3 C2] */ - for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { - retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - - /* shift R14 bit */ - retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - } + umc_v6_7_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst); } } @@ -448,75 +457,40 @@ static void umc_v6_7_query_ras_error_count(struct amdgpu_device *adev, static void umc_v6_7_query_error_address(struct amdgpu_device *adev, struct ras_err_data *err_data, uint32_t umc_reg_offset, uint32_t ch_inst, - uint32_t umc_inst, uint64_t mca_addr) + uint32_t umc_inst) { uint32_t mc_umc_status_addr; - uint32_t channel_index; - uint64_t mc_umc_status = 0, mc_umc_addrt0; - uint64_t err_addr, soc_pa, retired_page, column; + uint64_t mc_umc_status = 0, mc_umc_addrt0, err_addr; - if (mca_addr == UMC_INVALID_ADDR) { - mc_umc_status_addr = - SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); - mc_umc_addrt0 = - SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_ADDRT0); + mc_umc_status_addr = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_STATUST0); + mc_umc_addrt0 = + SOC15_REG_OFFSET(UMC, 0, regMCA_UMC_UMC0_MCUMC_ADDRT0); - mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4); + mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4); - if (mc_umc_status == 0) - return; + if (mc_umc_status == 0) + return; - if (!err_data->err_addr) { - /* clear umc status */ - WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL); - return; - } + if (!err_data->err_addr) { + /* clear umc status */ + WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL); + return; } - channel_index = - adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; - /* calculate error address if ue error is detected */ - if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) || - mca_addr != UMC_INVALID_ADDR) { - if (mca_addr == UMC_INVALID_ADDR) { - err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); - err_addr = - REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); - } else { - err_addr = mca_addr; - } + if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 && + REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1) { + err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4); + err_addr = + REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); - /* translate umc channel address to soc pa, 3 parts are included */ - soc_pa = ADDR_OF_8KB_BLOCK(err_addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(err_addr); - - /* The umc channel bits are not original values, they are hashed */ - SET_CHANNEL_HASH(channel_index, soc_pa); - - /* clear [C4 C3 C2] in soc physical address */ - soc_pa &= ~(0x7ULL << UMC_V6_7_PA_C2_BIT); - - /* loop for all possibilities of [C4 C3 C2] */ - for (column = 0; column < UMC_V6_7_NA_MAP_PA_NUM; column++) { - retired_page = soc_pa | (column << UMC_V6_7_PA_C2_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - - /* shift R14 bit */ - retired_page ^= (0x1ULL << UMC_V6_7_PA_R14_BIT); - dev_info(adev->dev, "Error Address(PA): 0x%llx\n", retired_page); - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); - } + umc_v6_7_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst); } /* clear umc status */ - if (mca_addr == UMC_INVALID_ADDR) - WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL); + WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL); } static void umc_v6_7_query_ras_error_address(struct amdgpu_device *adev, @@ -538,7 +512,7 @@ static void umc_v6_7_query_ras_error_address(struct amdgpu_device *adev, umc_v6_7_query_error_address(adev, err_data, umc_reg_offset, ch_inst, - umc_inst, UMC_INVALID_ADDR); + umc_inst); } } @@ -579,5 +553,5 @@ struct amdgpu_umc_ras umc_v6_7_ras = { .query_ras_poison_mode = umc_v6_7_query_ras_poison_mode, .ecc_info_query_ras_error_count = umc_v6_7_ecc_info_query_ras_error_count, .ecc_info_query_ras_error_address = umc_v6_7_ecc_info_query_ras_error_address, - .convert_ras_error_address = umc_v6_7_query_error_address, + .convert_ras_error_address = umc_v6_7_convert_error_address, }; -- cgit From fb4d5891cee6d1c14b8d8f1b65c9d061ed3a495c Mon Sep 17 00:00:00 2001 From: Tao Zhou Date: Tue, 27 Sep 2022 11:42:45 +0800 Subject: drm/amdgpu: define convert_error_address for umc v8.7 So the code can be simplified. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/umc_v8_7.c | 47 +++++++++++++++++++---------------- 1 file changed, 25 insertions(+), 22 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c index e2623685cb44..b717fdaa46e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c @@ -108,20 +108,35 @@ static void umc_v8_7_ecc_info_query_ras_error_count(struct amdgpu_device *adev, } } +static void umc_v8_7_convert_error_address(struct amdgpu_device *adev, + struct ras_err_data *err_data, uint64_t err_addr, + uint32_t ch_inst, uint32_t umc_inst) +{ + uint64_t retired_page; + uint32_t channel_index; + + channel_index = + adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; + + /* translate umc channel address to soc pa, 3 parts are included */ + retired_page = ADDR_OF_4KB_BLOCK(err_addr) | + ADDR_OF_256B_BLOCK(channel_index) | + OFFSET_IN_256B_BLOCK(err_addr); + + amdgpu_umc_fill_error_record(err_data, err_addr, + retired_page, channel_index, umc_inst); +} + static void umc_v8_7_ecc_info_query_error_address(struct amdgpu_device *adev, struct ras_err_data *err_data, uint32_t ch_inst, uint32_t umc_inst) { - uint64_t mc_umc_status, err_addr, retired_page; - uint32_t channel_index; + uint64_t mc_umc_status, err_addr; uint32_t eccinfo_table_idx; struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); eccinfo_table_idx = umc_inst * adev->umc.channel_inst_num + ch_inst; - channel_index = - adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; - mc_umc_status = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_status; if (mc_umc_status == 0) @@ -137,13 +152,8 @@ static void umc_v8_7_ecc_info_query_error_address(struct amdgpu_device *adev, err_addr = ras->umc_ecc.ecc[eccinfo_table_idx].mca_umc_addr; err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); - /* translate umc channel address to soc pa, 3 parts are included */ - retired_page = ADDR_OF_4KB_BLOCK(err_addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(err_addr); - - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); + umc_v8_7_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst); } } @@ -320,14 +330,12 @@ static void umc_v8_7_query_error_address(struct amdgpu_device *adev, uint32_t umc_inst) { uint32_t lsb, mc_umc_status_addr; - uint64_t mc_umc_status, err_addr, retired_page, mc_umc_addrt0; - uint32_t channel_index = adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst]; + uint64_t mc_umc_status, err_addr, mc_umc_addrt0; mc_umc_status_addr = SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0); mc_umc_addrt0 = SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_ADDRT0); - mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4); if (mc_umc_status == 0) @@ -349,13 +357,8 @@ static void umc_v8_7_query_error_address(struct amdgpu_device *adev, err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr); err_addr &= ~((0x1ULL << lsb) - 1); - /* translate umc channel address to soc pa, 3 parts are included */ - retired_page = ADDR_OF_4KB_BLOCK(err_addr) | - ADDR_OF_256B_BLOCK(channel_index) | - OFFSET_IN_256B_BLOCK(err_addr); - - amdgpu_umc_fill_error_record(err_data, err_addr, - retired_page, channel_index, umc_inst); + umc_v8_7_convert_error_address(adev, err_data, err_addr, + ch_inst, umc_inst); } /* clear umc status */ -- cgit From 38dbbfa57c08b29ef8cf1d3fb3ad639ae819754e Mon Sep 17 00:00:00 2001 From: Tao Zhou Date: Thu, 29 Sep 2022 14:59:11 +0800 Subject: drm/amdgpu: fix coding style issue for mca notifier Fix some issues found by checkpatch script. Signed-off-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index c2f9970e851c..2dad7aa9a03b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -2877,9 +2877,9 @@ static int amdgpu_bad_page_notifier(struct notifier_block *nb, err_data.err_addr = kcalloc(adev->umc.max_ras_err_cnt_per_query, sizeof(struct eeprom_table_record), GFP_KERNEL); - if(!err_data.err_addr) { - dev_warn(adev->dev, "Failed to alloc memory for " - "umc error address record in mca notifier!\n"); + if (!err_data.err_addr) { + dev_warn(adev->dev, + "Failed to alloc memory for umc error record in mca notifier!\n"); return NOTIFY_DONE; } -- cgit From 6dddc1eb9632b0eb6098d1dc849e8acb2408c1b6 Mon Sep 17 00:00:00 2001 From: Candice Li Date: Mon, 26 Sep 2022 16:18:56 +0800 Subject: drm/amdgpu: Update umc v8_10_0 headers Add GeccCtrl offset and mask to umc v8_10_0 headers. Signed-off-by: Candice Li Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_offset.h | 2 ++ drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_sh_mask.h | 3 +++ 2 files changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_offset.h index b798cf5a2c39..38adde3cae5a 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_offset.h @@ -29,5 +29,7 @@ #define regMCA_UMC_UMC0_MCUMC_STATUST0_BASE_IDX 2 #define regMCA_UMC_UMC0_MCUMC_ADDRT0 0x03c4 #define regMCA_UMC_UMC0_MCUMC_ADDRT0_BASE_IDX 2 +#define regUMCCH0_0_GeccCtrl 0x0053 +#define regUMCCH0_0_GeccCtrl_BASE_IDX 2 #endif diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_sh_mask.h index bd99b431247f..4dbec524f943 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_8_10_0_sh_mask.h @@ -90,5 +90,8 @@ #define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr__SHIFT 0x0 #define MCA_UMC_UMC0_MCUMC_ADDRT0__Reserved__SHIFT 0x38 #define MCA_UMC_UMC0_MCUMC_ADDRT0__ErrorAddr_MASK 0x00FFFFFFFFFFFFFFL +//UMCCH0_0_GeccCtrl +#define UMCCH0_0_GeccCtrl__UCFatalEn__SHIFT 0xd +#define UMCCH0_0_GeccCtrl__UCFatalEn_MASK 0x00002000L #endif -- cgit From 832e72dd0d705bfcb4236bb2d561d82afe253e63 Mon Sep 17 00:00:00 2001 From: Candice Li Date: Mon, 26 Sep 2022 16:21:05 +0800 Subject: drm/amdgpu: Add poison mode query for umc v8_10_0 Add poison mode query support on umc v8_10_0. Signed-off-by: Candice Li Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/umc_v8_10.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c index 38f9e29990cc..91235df54e22 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_10.c @@ -330,6 +330,31 @@ static void umc_v8_10_err_cnt_init(struct amdgpu_device *adev) } } +static uint32_t umc_v8_10_query_ras_poison_mode_per_channel( + struct amdgpu_device *adev, + uint32_t umc_reg_offset) +{ + uint32_t ecc_ctrl_addr, ecc_ctrl; + + ecc_ctrl_addr = + SOC15_REG_OFFSET(UMC, 0, regUMCCH0_0_GeccCtrl); + ecc_ctrl = RREG32_PCIE((ecc_ctrl_addr + + umc_reg_offset) * 4); + + return REG_GET_FIELD(ecc_ctrl, UMCCH0_0_GeccCtrl, UCFatalEn); +} + +static bool umc_v8_10_query_ras_poison_mode(struct amdgpu_device *adev) +{ + uint32_t umc_reg_offset = 0; + + /* Enabling fatal error in umc node0 instance0 channel0 will be + * considered as fatal error mode + */ + umc_reg_offset = get_umc_v8_10_reg_offset(adev, 0, 0, 0); + return !umc_v8_10_query_ras_poison_mode_per_channel(adev, umc_reg_offset); +} + const struct amdgpu_ras_block_hw_ops umc_v8_10_ras_hw_ops = { .query_ras_error_count = umc_v8_10_query_ras_error_count, .query_ras_error_address = umc_v8_10_query_ras_error_address, @@ -340,4 +365,5 @@ struct amdgpu_umc_ras umc_v8_10_ras = { .hw_ops = &umc_v8_10_ras_hw_ops, }, .err_cnt_init = umc_v8_10_err_cnt_init, + .query_ras_poison_mode = umc_v8_10_query_ras_poison_mode, }; -- cgit From 09f1ef99ce900dbc3659d478f006081c96cc977f Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 27 Sep 2022 17:59:21 -0400 Subject: drm/amd/display: Clean some DCN32 macros Some unused macros might mislead developers during the debug, which can be removed without any issue. This commit drops some unused references to SE_COMMON_MASK_SH_LIST_DCN32. Tested-by: Daniel Wheeler Acked-by: Qingqing Zhuo Signed-off-by: Rodrigo Siqueira Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h index 20e5f016a45a..ecd041a446d2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dio_stream_encoder.h @@ -95,7 +95,7 @@ SRI(DIG_FIFO_CTRL0, DIG, id) -#define SE_COMMON_MASK_SH_LIST_DCN32_BASE(mask_sh)\ +#define SE_COMMON_MASK_SH_LIST_DCN32(mask_sh)\ SE_SF(DP0_DP_PIXEL_FORMAT, DP_PIXEL_ENCODING, mask_sh),\ SE_SF(DP0_DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH, mask_sh),\ SE_SF(DP0_DP_PIXEL_FORMAT, DP_PIXEL_PER_CYCLE_PROCESSING_MODE, mask_sh),\ @@ -247,15 +247,6 @@ SE_SF(DIG0_DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, mask_sh),\ SE_SF(DIG0_DIG_FIFO_CTRL0, DIG_FIFO_OUTPUT_PIXEL_MODE, mask_sh) -#if defined(CONFIG_DRM_AMD_DC_HDCP) -#define SE_COMMON_MASK_SH_LIST_DCN32(mask_sh)\ - SE_COMMON_MASK_SH_LIST_DCN32_BASE(mask_sh),\ - SE_SF(DIG0_HDMI_VBI_PACKET_CONTROL, HDMI_ACP_SEND, mask_sh) -#else -#define SE_COMMON_MASK_SH_LIST_DCN32(mask_sh)\ - SE_COMMON_MASK_SH_LIST_DCN32_BASE(mask_sh) -#endif - void dcn32_dio_stream_encoder_construct( struct dcn10_stream_encoder *enc1, struct dc_context *ctx, -- cgit From 1ba25b6ff24303fac890d657ffdebf3e8db3bc25 Mon Sep 17 00:00:00 2001 From: Aric Cyr Date: Sun, 2 Oct 2022 11:59:13 -0400 Subject: drm/amd/display: 3.2.207 DC version 3.2.207 brings along the following: - PMFW z-state interface update - Cursor update refactor - Fixes to DSC validation, DCFCLK during Freesync, etc. - Code cleanup Tested-by: Daniel Wheeler Acked-by: Qingqing Zhuo Signed-off-by: Aric Cyr Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 5d0103e20412..bfc5474c0f4c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -47,7 +47,7 @@ struct aux_payload; struct set_config_cmd_payload; struct dmub_notification; -#define DC_VER "3.2.206" +#define DC_VER "3.2.207" #define MAX_SURFACES 3 #define MAX_PLANES 6 -- cgit From eff4ccd11313ecc8ec94c0f39961ffbf227a406d Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 11 Oct 2022 20:41:03 +0800 Subject: drm/amd/display: fix build error on arm64 dcn20_build_mapped_resource() and dcn20_acquire_dsc() is not defined, if CONFIG_DRM_AMD_DC_DCN is disabled. Fix the following build error on arm64: ERROR: modpost: "dcn20_build_mapped_resource" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined! ERROR: modpost: "dcn20_acquire_dsc" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined! Fixes: 20dad3813b3c ("drm/amd/display: Add a helper to map ODM/MPC/Multi-Plane resources") Signed-off-by: Yang Yingliang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 4a6e867369b8..fd8db482e56f 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -3721,12 +3721,16 @@ bool dc_resource_acquire_secondary_pipe_for_mpc_odm( else sec_pipe->stream_res.opp = sec_pipe->top_pipe->stream_res.opp; if (sec_pipe->stream->timing.flags.DSC == 1) { +#if defined(CONFIG_DRM_AMD_DC_DCN) dcn20_acquire_dsc(dc, &state->res_ctx, &sec_pipe->stream_res.dsc, pipe_idx); +#endif ASSERT(sec_pipe->stream_res.dsc); if (sec_pipe->stream_res.dsc == NULL) return false; } +#if defined(CONFIG_DRM_AMD_DC_DCN) dcn20_build_mapped_resource(dc, state, sec_pipe->stream); +#endif } return true; -- cgit From 9f30bf9917612b3a85cc28dc8ef98667ad5c07f8 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 11 Oct 2022 09:27:29 -0400 Subject: drm/amd/display: make dcn32_split_stream_for_mpc_or_odm static It's not used outside of dcn32_fpu.c. Fixes: 20dad3813b3c15 ("drm/amd/display: Add a helper to map ODM/MPC/Multi-Plane resources") Reviewed-by: Harry Wentland Reported-by: kernel test robot Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 2a3f5a485b2b..819de0f11012 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1372,7 +1372,7 @@ static struct pipe_ctx *dcn32_find_split_pipe( return pipe; } -bool dcn32_split_stream_for_mpc_or_odm( +static bool dcn32_split_stream_for_mpc_or_odm( const struct dc *dc, struct resource_context *res_ctx, struct pipe_ctx *pri_pipe, -- cgit From e1e6889fc7b3e5152218db7d9f03c2f81569d54c Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 6 Oct 2022 11:31:25 -0400 Subject: drm/amd/display: fix indentation in dc.c Fixes a warning in dc.c. Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/core/dc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 660316a536f7..997ab031f816 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3526,9 +3526,9 @@ static void commit_planes_for_stream(struct dc *dc, if (update_type != UPDATE_TYPE_FAST) dc->hwss.post_unlock_program_front_end(dc, context); - if (update_type != UPDATE_TYPE_FAST) - if (dc->hwss.commit_subvp_config) - dc->hwss.commit_subvp_config(dc, context); + if (update_type != UPDATE_TYPE_FAST) + if (dc->hwss.commit_subvp_config) + dc->hwss.commit_subvp_config(dc, context); if (update_type != UPDATE_TYPE_FAST) if (dc->hwss.commit_subvp_config) -- cgit From b1d1666276cce28743e2cf90be07182ceac14f1e Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 10 Oct 2022 10:37:43 -0400 Subject: drm/amd/display: make virtual_disable_link_output static It's not used outside of virtual_link_hwss.c. Fixes a -Wmissing-prototypes warning. Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/virtual/virtual_link_hwss.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_hwss.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_hwss.c index 9522fe0b36c9..4f7f99156897 100644 --- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_link_hwss.c @@ -37,7 +37,7 @@ void virtual_reset_stream_encoder(struct pipe_ctx *pipe_ctx) { } -void virtual_disable_link_output(struct dc_link *link, +static void virtual_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal) { -- cgit From f00844daa5212aac609d9cb97ce5e0a74c67890a Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 10 Oct 2022 17:30:08 -0400 Subject: drm/amd/display: add a license to cursor_reg_cache.h It's MIT. Fixes: b73353f7f3d434 ("drm/amd/display: Use the same cursor info across features") Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h b/drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h index 0e7c5880e867..45645f9fd86c 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/cursor_reg_cache.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: MIT */ /* Copyright © 2022 Advanced Micro Devices, Inc. All rights reserved. */ #ifndef __DAL_CURSOR_CACHE_H__ -- cgit From a895014853ea6df2778533e2a0bb7a0d53f02ec2 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 19 Sep 2022 12:36:29 -0400 Subject: drm/amd/display: fix transfer function passed to build_coefficients() The default argument should be enum TRANSFER_FUNCTION_SRGB rather than the current boolean value which improperly maps to TRANSFER_FUNCTION_BT709. Commit 9b3d76527f6e ("drm/amd/display: Revert adding degamma coefficients") looks to have improperly reverted commit d02097095916 ("drm/amd/display: Add regamma/degamma coefficients and set sRGB when TF is BT709") replacing the enum value with a boolean value. Cc: Krunoslav Kovac Cc: Jaehyun Chung Cc: Zeng Heng Fixes: 9b3d76527f6e ("drm/amd/display: Revert adding degamma coefficients") Reviewed-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/modules/color/color_gamma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c index 04f7656906ca..447a0ec9cbe2 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c @@ -1692,7 +1692,7 @@ static void apply_degamma_for_user_regamma(struct pwl_float_data_ex *rgb_regamma struct pwl_float_data_ex *rgb = rgb_regamma; const struct hw_x_point *coord_x = coordinates_x; - build_coefficients(&coeff, true); + build_coefficients(&coeff, TRANSFER_FUNCTION_SRGB); i = 0; while (i != hw_points_num + 1) { -- cgit From 1f768ba469002d2dcad5c3d667151977417df7d9 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Mon, 10 Oct 2022 15:38:03 +0800 Subject: drm/amd/display: Simplify bool conversion The result of 'pwr_status == 0' is Boolean, and the question mark expression is redundant. Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=2354 Reported-by: Abaci Robot Reviewed-by: Harry Wentland Signed-off-by: Yang Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 426b07edb426..cf5bd9713f54 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -1400,7 +1400,7 @@ bool dcn32_dsc_pg_status( break; } - return pwr_status == 0 ? true : false; + return pwr_status == 0; } void dcn32_update_dsc_pg(struct dc *dc, -- cgit From 695ddc9318ad45b6a32f902b7c6998c65d575f26 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 4 Oct 2022 14:19:14 +0100 Subject: drm/i915: allow control over the flags when migrating MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the next patch we want to move the object (if the current resource is not compatible), to the mappable part of lmem for some display buffers. Currently that requires being able to unset the I915_BO_ALLOC_GPU_ONLY hint. Signed-off-by: Matthew Auld Cc: Jianshui Yu Cc: Ville Syrjälä Cc: Nirmoy Das Reviewed-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20221004131916.233474-3-matthew.auld@intel.com (cherry picked from commit 999f4562077208b683f0519e5f1aa1e5c2fd2191) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/gem/i915_gem_object.c | 37 +++++++++++++++++++++++- drivers/gpu/drm/i915/gem/i915_gem_object.h | 4 +++ drivers/gpu/drm/i915/gem/i915_gem_object_types.h | 3 +- drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 5 ++-- 4 files changed, 45 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 7ff9c7877bec..369006c5317f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -652,6 +652,41 @@ bool i915_gem_object_can_migrate(struct drm_i915_gem_object *obj, int i915_gem_object_migrate(struct drm_i915_gem_object *obj, struct i915_gem_ww_ctx *ww, enum intel_region_id id) +{ + return __i915_gem_object_migrate(obj, ww, id, obj->flags); +} + +/** + * __i915_gem_object_migrate - Migrate an object to the desired region id, with + * control of the extra flags + * @obj: The object to migrate. + * @ww: An optional struct i915_gem_ww_ctx. If NULL, the backend may + * not be successful in evicting other objects to make room for this object. + * @id: The region id to migrate to. + * @flags: The object flags. Normally just obj->flags. + * + * Attempt to migrate the object to the desired memory region. The + * object backend must support migration and the object may not be + * pinned, (explicitly pinned pages or pinned vmas). The object must + * be locked. + * On successful completion, the object will have pages pointing to + * memory in the new region, but an async migration task may not have + * completed yet, and to accomplish that, i915_gem_object_wait_migration() + * must be called. + * + * Note: the @ww parameter is not used yet, but included to make sure + * callers put some effort into obtaining a valid ww ctx if one is + * available. + * + * Return: 0 on success. Negative error code on failure. In particular may + * return -ENXIO on lack of region space, -EDEADLK for deadlock avoidance + * if @ww is set, -EINTR or -ERESTARTSYS if signal pending, and + * -EBUSY if the object is pinned. + */ +int __i915_gem_object_migrate(struct drm_i915_gem_object *obj, + struct i915_gem_ww_ctx *ww, + enum intel_region_id id, + unsigned int flags) { struct drm_i915_private *i915 = to_i915(obj->base.dev); struct intel_memory_region *mr; @@ -672,7 +707,7 @@ int i915_gem_object_migrate(struct drm_i915_gem_object *obj, return 0; } - return obj->ops->migrate(obj, mr); + return obj->ops->migrate(obj, mr, flags); } /** diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 7317d4102955..1723af9b0f6a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -608,6 +608,10 @@ bool i915_gem_object_migratable(struct drm_i915_gem_object *obj); int i915_gem_object_migrate(struct drm_i915_gem_object *obj, struct i915_gem_ww_ctx *ww, enum intel_region_id id); +int __i915_gem_object_migrate(struct drm_i915_gem_object *obj, + struct i915_gem_ww_ctx *ww, + enum intel_region_id id, + unsigned int flags); bool i915_gem_object_can_migrate(struct drm_i915_gem_object *obj, enum intel_region_id id); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 40305e2bcd49..d0d6772e6f36 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -107,7 +107,8 @@ struct drm_i915_gem_object_ops { * pinning or for as long as the object lock is held. */ int (*migrate)(struct drm_i915_gem_object *obj, - struct intel_memory_region *mr); + struct intel_memory_region *mr, + unsigned int flags); void (*release)(struct drm_i915_gem_object *obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index e3fc38dd5db0..4f861782c3e8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -848,9 +848,10 @@ static int __i915_ttm_migrate(struct drm_i915_gem_object *obj, } static int i915_ttm_migrate(struct drm_i915_gem_object *obj, - struct intel_memory_region *mr) + struct intel_memory_region *mr, + unsigned int flags) { - return __i915_ttm_migrate(obj, mr, obj->flags); + return __i915_ttm_migrate(obj, mr, flags); } static void i915_ttm_put_pages(struct drm_i915_gem_object *obj, -- cgit From ea19684afb545605bbcb690c49a91ce2c8e596dd Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Tue, 4 Oct 2022 14:19:15 +0100 Subject: drm/i915/display: consider DG2_RC_CCS_CC when migrating buffers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For these types of display buffers, we need to able to CPU access some part of the backing memory in prepare_plane_clear_colors(). As a result we need to ensure we always place in the mappable part of lmem, which becomes necessary on small-bar systems. v2(Nirmoy & Ville): - Add some commentary for why we need to CPU access the buffer. - Split out the other changes, so we just consider the display change here. v3: - Handle this in the dpt path. v4(Ville): - Drop the intel_fb_rc_ccs_cc_plane() sanity check in pin_and_fence_fb_obj(), since we can also trigger this on DG1 it seems. Fixes: eb1c535f0d69 ("drm/i915: turn on small BAR support") Reported-by: Jianshui Yu Signed-off-by: Matthew Auld Cc: Ville Syrjälä Cc: Nirmoy Das Reviewed-by: Ville Syrjälä Acked-by: Nirmoy Das Link: https://patchwork.freedesktop.org/patch/msgid/20221004131916.233474-4-matthew.auld@intel.com (cherry picked from commit e3afc690188be8e4385d13d1b0e7f0ba01caea40) Signed-off-by: Tvrtko Ursulin --- drivers/gpu/drm/i915/display/intel_fb_pin.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c index 733972fab07f..1dddd6abd77b 100644 --- a/drivers/gpu/drm/i915/display/intel_fb_pin.c +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c @@ -50,7 +50,18 @@ intel_pin_fb_obj_dpt(struct drm_framebuffer *fb, continue; if (HAS_LMEM(dev_priv)) { - ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0); + unsigned int flags = obj->flags; + + /* + * For this type of buffer we need to able to read from the CPU + * the clear color value found in the buffer, hence we need to + * ensure it is always in the mappable part of lmem, if this is + * a small-bar device. + */ + if (intel_fb_rc_ccs_cc_plane(fb) >= 0) + flags &= ~I915_BO_ALLOC_GPU_ONLY; + ret = __i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0, + flags); if (ret) continue; } -- cgit From a6d1ce5951185ee91bbe6909fe2758f3625561b0 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Tue, 11 Oct 2022 00:33:58 +0000 Subject: cgroup: add cgroup_v1v2_get_from_[fd/file]() Add cgroup_v1v2_get_from_fd() and cgroup_v1v2_get_from_file() that support both cgroup1 and cgroup2. Signed-off-by: Yosry Ahmed Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 1 + kernel/cgroup/cgroup.c | 50 ++++++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 45 insertions(+), 6 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 398f0bce7c21..a88de5bdeaa9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -106,6 +106,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); +struct cgroup *cgroup_v1v2_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 6d8a5a40c24d..6349a9fe9ec1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6224,16 +6224,36 @@ void cgroup_fork(struct task_struct *child) INIT_LIST_HEAD(&child->cg_list); } -static struct cgroup *cgroup_get_from_file(struct file *f) +/** + * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer + * @f: file corresponding to cgroup_dir + * + * Find the cgroup from a file pointer associated with a cgroup directory. + * Returns a pointer to the cgroup on success. ERR_PTR is returned if the + * cgroup cannot be found. + */ +static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) { struct cgroup_subsys_state *css; - struct cgroup *cgrp; css = css_tryget_online_from_dir(f->f_path.dentry, NULL); if (IS_ERR(css)) return ERR_CAST(css); - cgrp = css->cgroup; + return css->cgroup; +} + +/** + * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports + * cgroup2. + */ +static struct cgroup *cgroup_get_from_file(struct file *f) +{ + struct cgroup *cgrp = cgroup_v1v2_get_from_file(f); + + if (IS_ERR(cgrp)) + return ERR_CAST(cgrp); + if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); @@ -6734,14 +6754,14 @@ EXPORT_SYMBOL_GPL(cgroup_get_from_path); /** * cgroup_get_from_fd - get a cgroup pointer from a fd - * @fd: fd obtained by open(cgroup2_dir) + * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */ -struct cgroup *cgroup_get_from_fd(int fd) +struct cgroup *cgroup_v1v2_get_from_fd(int fd) { struct cgroup *cgrp; struct file *f; @@ -6750,10 +6770,28 @@ struct cgroup *cgroup_get_from_fd(int fd) if (!f) return ERR_PTR(-EBADF); - cgrp = cgroup_get_from_file(f); + cgrp = cgroup_v1v2_get_from_file(f); fput(f); return cgrp; } + +/** + * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports + * cgroup2. + */ +struct cgroup *cgroup_get_from_fd(int fd) +{ + struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd); + + if (IS_ERR(cgrp)) + return ERR_CAST(cgrp); + + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + return cgrp; +} EXPORT_SYMBOL_GPL(cgroup_get_from_fd); static u64 power_of_ten(int power) -- cgit From 35256d673a9cf723d9e2edb5d51e1b1b6b197ba3 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Tue, 11 Oct 2022 00:33:59 +0000 Subject: bpf: cgroup_iter: support cgroup1 using cgroup fd Use cgroup_v1v2_get_from_fd() in cgroup_iter to support attaching to both cgroup v1 and v2 using fds. Signed-off-by: Yosry Ahmed Acked-by: Martin KaFai Lau Signed-off-by: Tejun Heo --- kernel/bpf/cgroup_iter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c index 0d200a993489..9fcf09f2ef00 100644 --- a/kernel/bpf/cgroup_iter.c +++ b/kernel/bpf/cgroup_iter.c @@ -196,7 +196,7 @@ static int bpf_iter_attach_cgroup(struct bpf_prog *prog, return -EINVAL; if (fd) - cgrp = cgroup_get_from_fd(fd); + cgrp = cgroup_v1v2_get_from_fd(fd); else if (id) cgrp = cgroup_get_from_id(id); else /* walk the entire hierarchy by default. */ -- cgit From 8248fe413216732f98563e8882b6c6ae617c327b Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 10 Oct 2022 22:28:08 -0700 Subject: perf stat: Support old kernels for bperf cgroup counting The recent change in the cgroup will break the backward compatiblity in the BPF program. It should support both old and new kernels using BPF CO-RE technique. Like the task_struct->__state handling in the offcpu analysis, we can check the field name in the cgroup struct. Acked-by: Jiri Olsa Acked-by: Andrii Nakryiko Signed-off-by: Namhyung Kim Signed-off-by: Tejun Heo --- tools/perf/util/bpf_skel/bperf_cgroup.bpf.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c index 435a87556688..6a438e0102c5 100644 --- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c @@ -43,6 +43,18 @@ struct { __uint(value_size, sizeof(struct bpf_perf_event_value)); } cgrp_readings SEC(".maps"); +/* new kernel cgroup definition */ +struct cgroup___new { + int level; + struct cgroup *ancestors[]; +} __attribute__((preserve_access_index)); + +/* old kernel cgroup definition */ +struct cgroup___old { + int level; + u64 ancestor_ids[]; +} __attribute__((preserve_access_index)); + const volatile __u32 num_events = 1; const volatile __u32 num_cpus = 1; @@ -50,6 +62,21 @@ int enabled = 0; int use_cgroup_v2 = 0; int perf_subsys_id = -1; +static inline __u64 get_cgroup_v1_ancestor_id(struct cgroup *cgrp, int level) +{ + /* recast pointer to capture new type for compiler */ + struct cgroup___new *cgrp_new = (void *)cgrp; + + if (bpf_core_field_exists(cgrp_new->ancestors)) { + return BPF_CORE_READ(cgrp_new, ancestors[level], kn, id); + } else { + /* recast pointer to capture old type for compiler */ + struct cgroup___old *cgrp_old = (void *)cgrp; + + return BPF_CORE_READ(cgrp_old, ancestor_ids[level]); + } +} + static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) { struct task_struct *p = (void *)bpf_get_current_task(); @@ -77,7 +104,7 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) break; // convert cgroup-id to a map index - cgrp_id = BPF_CORE_READ(cgrp, ancestors[i], kn, id); + cgrp_id = get_cgroup_v1_ancestor_id(cgrp, i); elem = bpf_map_lookup_elem(&cgrp_idx, &cgrp_id); if (!elem) continue; -- cgit From 10f43fda55404cd6b5e1d422d9ecb570ce49d5de Mon Sep 17 00:00:00 2001 From: Wu XiangCheng Date: Tue, 11 Oct 2022 14:00:45 +0800 Subject: docs/zh_CN: promote the title of zh_CN/process/index.rst update to commit 9d0f5cd16744 ("docs: promote the title of process/index.rst") Signed-off-by: Wu XiangCheng Reviewed-by: Yanteng Si Link: https://lore.kernel.org/r/2741340f3b5f131a32d0f295224edd569aab0d98.1665467392.git.bobwxc@email.cn Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/process/index.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/translations/zh_CN/process/index.rst b/Documentation/translations/zh_CN/process/index.rst index a683dbea0c83..a1a35f88f4ae 100644 --- a/Documentation/translations/zh_CN/process/index.rst +++ b/Documentation/translations/zh_CN/process/index.rst @@ -10,6 +10,7 @@ .. _cn_process_index: +======================== 与Linux 内核社区一起工作 ======================== -- cgit From da2e928b2ddbcca793207ca670c6213f925a95f5 Mon Sep 17 00:00:00 2001 From: Wu XiangCheng Date: Tue, 11 Oct 2022 14:01:28 +0800 Subject: docs/zh_CN: add zh_CN/arch.rst Add an entry for all zh arch documents. Signed-off-by: Wu XiangCheng Reviewed-by: Yanteng Si Link: https://lore.kernel.org/r/4e9675ac83a06f2597d069f44a94c4e2cbd7ab2b.1665467392.git.bobwxc@email.cn Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/arch.rst | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 Documentation/translations/zh_CN/arch.rst diff --git a/Documentation/translations/zh_CN/arch.rst b/Documentation/translations/zh_CN/arch.rst new file mode 100644 index 000000000000..690e173d8b2a --- /dev/null +++ b/Documentation/translations/zh_CN/arch.rst @@ -0,0 +1,29 @@ +.. SPDX-License-Identifier: GPL-2.0 + +处理器体系结构 +============== + +以下文档提供了具体架构实现的编程细节。 + +.. toctree:: + :maxdepth: 2 + + mips/index + arm64/index + riscv/index + openrisc/index + parisc/index + loongarch/index + +TODOList: + +* arm/index +* ia64/index +* m68k/index +* nios2/index +* powerpc/index +* s390/index +* sh/index +* sparc/index +* x86/index +* xtensa/index -- cgit From eef24f7054a63058d6400a4386ee8bb2164fec44 Mon Sep 17 00:00:00 2001 From: Wu XiangCheng Date: Tue, 11 Oct 2022 14:02:23 +0800 Subject: docs/zh_CN: Rewrite the Chinese translation front page update to commit 0c7b4366f1ab ("docs: Rewrite the front page") Signed-off-by: Wu XiangCheng Reviewed-by: Yanteng Si Link: https://lore.kernel.org/r/440d7cb3c9f1526ed7c2996aa88ba2bc7fdc018c.1665467392.git.bobwxc@email.cn Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/index.rst | 169 +++++++++-------------------- 1 file changed, 51 insertions(+), 118 deletions(-) diff --git a/Documentation/translations/zh_CN/index.rst b/Documentation/translations/zh_CN/index.rst index 2fc60e60feb4..7be728bed46d 100644 --- a/Documentation/translations/zh_CN/index.rst +++ b/Documentation/translations/zh_CN/index.rst @@ -26,165 +26,98 @@ 顺便说下，中文文档也需要遵守内核编码风格，风格中中文和英文的主要不同就是中文 的字符标点占用两个英文字符宽度， 所以，当英文要求不要超过每行100个字符时， 中文就不要超过50个字符。另外，也要注意'-'，'=' 等符号与相关标题的对齐。在将 -补丁提交到社区之前，一定要进行必要的checkpatch.pl检查和编译测试。 +补丁提交到社区之前，一定要进行必要的 ``checkpatch.pl`` 检查和编译测试。 -许可证文档 ----------- - -下面的文档介绍了Linux内核源代码的许可证（GPLv2）、如何在源代码树中正确标记 -单个文件的许可证、以及指向完整许可证文本的链接。 +与Linux 内核社区一起工作 +------------------------ -* Documentation/translations/zh_CN/process/license-rules.rst - -用户文档 --------- - -下面的手册是为内核用户编写的——即那些试图让它在给定系统上以最佳方式工作的 -用户。 +与内核开发社区进行协作并将工作推向上游的基本指南。 .. toctree:: - :maxdepth: 2 + :maxdepth: 1 - admin-guide/index - -TODOList: - -* kbuild/index + process/development-process + process/submitting-patches + 行为准则 + maintainer/index + 完整开发流程文档 -固件相关文档 ------------- +内部API文档 +----------- -下列文档描述了内核需要的平台固件相关信息。 +开发人员使用的内核内部交互接口手册。 .. toctree:: - :maxdepth: 2 + :maxdepth: 1 - devicetree/index + core-api/index + driver-api/index + 内核中的锁 TODOList: -* firmware-guide/index - -应用程序开发人员文档 --------------------- - -用户空间API手册涵盖了描述应用程序开发人员可见内核接口方面的文档。 - -TODOlist: - -* userspace-api/index +* subsystem-apis -内核开发简介 ------------- +开发工具和流程 +-------------- -这些手册包含有关如何开发内核的整体信息。内核社区非常庞大，一年下来有数千名 -开发人员做出贡献。与任何大型社区一样，知道如何完成任务将使得更改合并的过程 -变得更加容易。 +为所有内核开发人员提供有用信息的各种其他手册。 .. toctree:: - :maxdepth: 2 + :maxdepth: 1 - process/index - dev-tools/index + process/license-rules doc-guide/index + dev-tools/index + dev-tools/testing-overview kernel-hacking/index - maintainer/index TODOList: * trace/index * fault-injection/index * livepatch/index -* rust/index -内核API文档 ------------ +面向用户的文档 +-------------- -以下手册从内核开发人员的角度详细介绍了特定的内核子系统是如何工作的。这里的 -大部分信息都是直接从内核源代码获取的，并根据需要添加补充材料（或者至少是在 -我们设法添加的时候——可能不是所有的都是有需要的）。 +下列手册针对 +希望内核在给定系统上以最佳方式工作的*用户*， +和查找内核用户空间API信息的程序开发人员。 .. toctree:: - :maxdepth: 2 + :maxdepth: 1 - core-api/index - driver-api/index - locking/index - accounting/index - cpu-freq/index - iio/index - infiniband/index - power/index - virt/index - sound/index - filesystems/index - scheduler/index - mm/index - peci/index - PCI/index + admin-guide/index + admin-guide/reporting-issues.rst TODOList: -* block/index -* cdrom/index -* ide/index -* fb/index -* fpga/index -* hid/index -* i2c/index -* isdn/index -* leds/index -* netlabel/index -* networking/index -* pcmcia/index -* target/index -* timers/index -* spi/index -* w1/index -* watchdog/index -* input/index -* hwmon/index -* gpu/index -* security/index -* crypto/index -* bpf/index -* usb/index -* scsi/index -* misc-devices/index -* mhi/index - -体系结构无关文档 ----------------- - -TODOList: +* 内核构建系统 +* 用户空间工具 +* userspace-api/index -* asm-annotations +固件相关文档 +------------ -特定体系结构文档 ----------------- +下列文档描述了内核需要的平台固件相关信息。 .. toctree:: :maxdepth: 2 - mips/index - arm64/index - riscv/index - openrisc/index - parisc/index - loongarch/index + devicetree/index TODOList: -* arm/index -* ia64/index -* m68k/index -* nios2/index -* powerpc/index -* s390/index -* sh/index -* sparc/index -* x86/index -* xtensa/index +* firmware-guide/index + +体系结构文档 +------------ + +.. toctree:: + :maxdepth: 2 + + arch 其他文档 -------- @@ -195,9 +128,9 @@ TODOList: TODOList: * staging/index -* watch_queue -目录和表格 + +索引和表格 ---------- * :ref:`genindex` -- cgit From ff2be4420863cc93bd4e0bea333ac9cb090a3415 Mon Sep 17 00:00:00 2001 From: Wu XiangCheng Date: Tue, 11 Oct 2022 14:03:00 +0800 Subject: docs/zh_CN: add a man-pages link to zh_CN/index.rst update to commit 489876063fb1 ("docs: add a man-pages link to the front page") Signed-off-by: Wu XiangCheng Reviewed-by: Yanteng Si Link: https://lore.kernel.org/r/6e289528ed1b40c1fcc03ea5e854e7c8ba264e67.1665467392.git.bobwxc@email.cn Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/index.rst | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/translations/zh_CN/index.rst b/Documentation/translations/zh_CN/index.rst index 7be728bed46d..ec99ef5fe990 100644 --- a/Documentation/translations/zh_CN/index.rst +++ b/Documentation/translations/zh_CN/index.rst @@ -97,6 +97,8 @@ TODOList: * 用户空间工具 * userspace-api/index +也可参考独立于内核文档的 `Linux 手册页 `_ 。 + 固件相关文档 ------------ -- cgit From 71c8517e004b950a148581ea2d2abe10aa46e02d Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Mon, 10 Oct 2022 23:17:04 +0100 Subject: MAINTAINERS: update polarfire soc clock binding The clock binding has been renamed and a new binding added for the clock controllers in the FPGA fabric. Generalise the pattern to cover both. Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20221010221704.2161221-2-conor@kernel.org/ Signed-off-by: Palmer Dabbelt --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 0dc4a769216b..94cf47ea5f80 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17645,7 +17645,7 @@ M: Conor Dooley M: Daire McNamara L: linux-riscv@lists.infradead.org S: Supported -F: Documentation/devicetree/bindings/clock/microchip,mpfs.yaml +F: Documentation/devicetree/bindings/clock/microchip,mpfs*.yaml F: Documentation/devicetree/bindings/gpio/microchip,mpfs-gpio.yaml F: Documentation/devicetree/bindings/i2c/microchip,corei2c.yaml F: Documentation/devicetree/bindings/mailbox/microchip,mpfs-mailbox.yaml -- cgit From abbb388d335f8c400d1baecb15d360fa0062de77 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Mon, 10 Oct 2022 23:17:05 +0100 Subject: dt-bindings: riscv: update microchip.yaml's maintainership Daire and I are the platform maintainers for Microchip's RISC-V FPGAs. Update the maintainers in microchip.yaml to reflect this and explicitly add the binding to the SoC's MAINTAINERS entry. Acked-by: Krzysztof Kozlowski Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20221010221704.2161221-3-conor@kernel.org/ Signed-off-by: Palmer Dabbelt --- Documentation/devicetree/bindings/riscv/microchip.yaml | 4 ++-- MAINTAINERS | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/riscv/microchip.yaml b/Documentation/devicetree/bindings/riscv/microchip.yaml index 1aa7336a9672..9faf8447332b 100644 --- a/Documentation/devicetree/bindings/riscv/microchip.yaml +++ b/Documentation/devicetree/bindings/riscv/microchip.yaml @@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip PolarFire SoC-based boards device tree bindings maintainers: - - Cyril Jean - - Lewis Hanly + - Conor Dooley + - Daire McNamara description: Microchip PolarFire SoC-based boards diff --git a/MAINTAINERS b/MAINTAINERS index 94cf47ea5f80..b3415857a812 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17651,6 +17651,7 @@ F: Documentation/devicetree/bindings/i2c/microchip,corei2c.yaml F: Documentation/devicetree/bindings/mailbox/microchip,mpfs-mailbox.yaml F: Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml F: Documentation/devicetree/bindings/pwm/microchip,corepwm.yaml +F: Documentation/devicetree/bindings/riscv/microchip.yaml F: Documentation/devicetree/bindings/soc/microchip/microchip,mpfs-sys-controller.yaml F: Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml F: Documentation/devicetree/bindings/usb/microchip,mpfs-musb.yaml -- cgit From 780614ce1988f9d8ab05a58b49d5506bca60b935 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Wed, 12 Oct 2022 08:07:29 +1000 Subject: cifs: fix skipping to incorrect offset in emit_cached_dirents When application has done lseek() to a different offset on a directory fd we skipped one entry too many before we start emitting directory entries from the cache. We need to also make sure that when we are starting to emit directory entries from the cache, the ->pos sequence might have holes and skip some indices. Signed-off-by: Ronnie Sahlberg Reviewed-by: Tom Talpey Signed-off-by: Steve French --- fs/cifs/readdir.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 8e060c00c969..1bb4624e768b 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -844,17 +844,34 @@ static bool emit_cached_dirents(struct cached_dirents *cde, struct dir_context *ctx) { struct cached_dirent *dirent; - int rc; + bool rc; list_for_each_entry(dirent, &cde->entries, entry) { - if (ctx->pos >= dirent->pos) + /* + * Skip all early entries prior to the current lseek() + * position. + */ + if (ctx->pos > dirent->pos) continue; + /* + * We recorded the current ->pos value for the dirent + * when we stored it in the cache. + * However, this sequence of ->pos values may have holes + * in it, for example dot-dirs returned from the server + * are suppressed. + * Handle this bu forcing ctx->pos to be the same as the + * ->pos of the current dirent we emit from the cache. + * This means that when we emit these entries from the cache + * we now emit them with the same ->pos value as in the + * initial scan. + */ ctx->pos = dirent->pos; rc = dir_emit(ctx, dirent->name, dirent->namelen, dirent->fattr.cf_uniqueid, dirent->fattr.cf_dtype); if (!rc) return rc; + ctx->pos++; } return true; } @@ -1202,10 +1219,10 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) ctx->pos, tmp_buf); cifs_save_resume_key(current_entry, cifsFile); break; - } else - current_entry = - nxt_dir_entry(current_entry, end_of_smb, - cifsFile->srch_inf.info_level); + } + current_entry = + nxt_dir_entry(current_entry, end_of_smb, + cifsFile->srch_inf.info_level); } kfree(tmp_buf); -- cgit From 81895a65ec63ee1daec3255dc1a06675d2fbe915 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 16:43:38 +0200 Subject: treewide: use prandom_u32_max() when possible, part 1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rather than incurring a division or requesting too many random bytes for the given range, use the prandom_u32_max() function, which only takes the minimum required bytes from the RNG and avoids divisions. This was done mechanically with this coccinelle script: @basic@ expression E; type T; identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; typedef u64; @@ ( - ((T)get_random_u32() % (E)) + prandom_u32_max(E) | - ((T)get_random_u32() & ((E) - 1)) + prandom_u32_max(E * XXX_MAKE_SURE_E_IS_POW2) | - ((u64)(E) * get_random_u32() >> 32) + prandom_u32_max(E) | - ((T)get_random_u32() & ~PAGE_MASK) + prandom_u32_max(PAGE_SIZE) ) @multi_line@ identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; identifier RAND; expression E; @@ - RAND = get_random_u32(); ... when != RAND - RAND %= (E); + RAND = prandom_u32_max(E); // Find a potential literal @literal_mask@ expression LITERAL; type T; identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; position p; @@ ((T)get_random_u32()@p & (LITERAL)) // Add one to the literal. @script:python add_one@ literal << literal_mask.LITERAL; RESULT; @@ value = None if literal.startswith('0x'): value = int(literal, 16) elif literal[0] in '123456789': value = int(literal, 10) if value is None: print("I don't know how to handle %s" % (literal)) cocci.include_match(False) elif value == 2**32 - 1 or value == 2**31 - 1 or value == 2**24 - 1 or value == 2**16 - 1 or value == 2**8 - 1: print("Skipping 0x%x for cleanup elsewhere" % (value)) cocci.include_match(False) elif value & (value + 1) != 0: print("Skipping 0x%x because it's not a power of two minus one" % (value)) cocci.include_match(False) elif literal.startswith('0x'): coccinelle.RESULT = cocci.make_expr("0x%x" % (value + 1)) else: coccinelle.RESULT = cocci.make_expr("%d" % (value + 1)) // Replace the literal mask with the calculated result. @plus_one@ expression literal_mask.LITERAL; position literal_mask.p; expression add_one.RESULT; identifier FUNC; @@ - (FUNC()@p & (LITERAL)) + prandom_u32_max(RESULT) @collapse_ret@ type T; identifier VAR; expression E; @@ { - T VAR; - VAR = (E); - return VAR; + return E; } @drop_var@ type T; identifier VAR; @@ { - T VAR; ... when != VAR } Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Reviewed-by: KP Singh Reviewed-by: Jan Kara # for ext4 and sbitmap Reviewed-by: Christoph Böhmwalder # for drbd Acked-by: Jakub Kicinski Acked-by: Heiko Carstens # for s390 Acked-by: Ulf Hansson # for mmc Acked-by: Darrick J. Wong # for xfs Signed-off-by: Jason A. Donenfeld --- arch/arm/kernel/process.c | 2 +- arch/arm64/kernel/process.c | 2 +- arch/loongarch/kernel/process.c | 2 +- arch/loongarch/kernel/vdso.c | 2 +- arch/mips/kernel/process.c | 2 +- arch/mips/kernel/vdso.c | 2 +- arch/parisc/kernel/vdso.c | 2 +- arch/powerpc/kernel/process.c | 2 +- arch/s390/kernel/process.c | 2 +- arch/s390/kernel/vdso.c | 2 +- arch/sparc/vdso/vma.c | 2 +- arch/um/kernel/process.c | 2 +- arch/x86/entry/vdso/vma.c | 2 +- arch/x86/kernel/module.c | 2 +- arch/x86/kernel/process.c | 2 +- arch/x86/mm/pat/cpa-test.c | 4 +- crypto/testmgr.c | 86 +++++++++++----------- drivers/block/drbd/drbd_receiver.c | 4 +- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 2 +- drivers/infiniband/core/cma.c | 2 +- drivers/infiniband/hw/cxgb4/id_table.c | 4 +- drivers/infiniband/hw/hns/hns_roce_ah.c | 5 +- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 3 +- drivers/md/bcache/request.c | 2 +- drivers/media/test-drivers/vivid/vivid-touch-cap.c | 2 +- drivers/mmc/core/core.c | 4 +- drivers/mmc/host/dw_mmc.c | 2 +- drivers/mtd/nand/raw/nandsim.c | 4 +- drivers/mtd/tests/mtd_nandecctest.c | 10 +-- drivers/mtd/tests/stresstest.c | 17 +---- drivers/mtd/ubi/debug.c | 2 +- drivers/mtd/ubi/debug.h | 6 +- drivers/net/ethernet/broadcom/cnic.c | 3 +- .../chelsio/inline_crypto/chtls/chtls_io.c | 4 +- drivers/net/hamradio/baycom_epp.c | 2 +- drivers/net/hamradio/hdlcdrv.c | 2 +- drivers/net/hamradio/yam.c | 2 +- drivers/net/phy/at803x.c | 2 +- .../net/wireless/broadcom/brcm80211/brcmfmac/p2p.c | 2 +- drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 2 +- drivers/scsi/fcoe/fcoe_ctlr.c | 4 +- drivers/scsi/qedi/qedi_main.c | 2 +- fs/ceph/inode.c | 2 +- fs/ceph/mdsmap.c | 2 +- fs/ext4/super.c | 7 +- fs/f2fs/gc.c | 2 +- fs/f2fs/segment.c | 8 +- fs/ubifs/debug.c | 8 +- fs/ubifs/lpt_commit.c | 14 ++-- fs/ubifs/tnc_commit.c | 2 +- fs/xfs/libxfs/xfs_alloc.c | 2 +- fs/xfs/libxfs/xfs_ialloc.c | 2 +- fs/xfs/xfs_error.c | 2 +- include/linux/nodemask.h | 2 +- kernel/bpf/core.c | 4 +- kernel/locking/test-ww_mutex.c | 4 +- kernel/time/clocksource.c | 2 +- lib/fault-inject.c | 2 +- lib/find_bit_benchmark.c | 4 +- lib/kobject.c | 2 +- lib/reed_solomon/test_rslib.c | 6 +- lib/sbitmap.c | 2 +- lib/test-string_helpers.c | 2 +- lib/test_hexdump.c | 10 +-- lib/test_list_sort.c | 2 +- mm/kasan/kasan_test.c | 6 +- mm/slub.c | 2 +- net/802/garp.c | 2 +- net/802/mrp.c | 2 +- net/ceph/mon_client.c | 2 +- net/ceph/osd_client.c | 2 +- net/core/neighbour.c | 2 +- net/core/pktgen.c | 43 ++++++----- net/core/stream.c | 2 +- net/ipv4/igmp.c | 6 +- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/inet_hashtables.c | 2 +- net/ipv6/addrconf.c | 8 +- net/ipv6/mcast.c | 10 +-- net/netfilter/ipvs/ip_vs_twos.c | 4 +- net/packet/af_packet.c | 2 +- net/sched/act_gact.c | 2 +- net/sched/act_sample.c | 2 +- net/sched/sch_netem.c | 4 +- net/sctp/socket.c | 2 +- net/sunrpc/cache.c | 2 +- net/sunrpc/xprtsock.c | 2 +- net/tipc/socket.c | 2 +- net/xfrm/xfrm_state.c | 2 +- 89 files changed, 204 insertions(+), 218 deletions(-) diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 96f3fbd51764..129279b33b1d 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -375,7 +375,7 @@ static unsigned long sigpage_addr(const struct mm_struct *mm, slots = ((last - first) >> PAGE_SHIFT) + 1; - offset = get_random_int() % slots; + offset = prandom_u32_max(slots); addr = first + (offset << PAGE_SHIFT); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 92bcc1768f0b..87203429f802 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -595,7 +595,7 @@ unsigned long __get_wchan(struct task_struct *p) unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() & ~PAGE_MASK; + sp -= prandom_u32_max(PAGE_SIZE); return sp & ~0xf; } diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 660492f064e7..1256e3582475 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -293,7 +293,7 @@ unsigned long stack_top(void) unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() & ~PAGE_MASK; + sp -= prandom_u32_max(PAGE_SIZE); return sp & STACK_ALIGN; } diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c index f32c38abd791..8c9826062652 100644 --- a/arch/loongarch/kernel/vdso.c +++ b/arch/loongarch/kernel/vdso.c @@ -78,7 +78,7 @@ static unsigned long vdso_base(void) unsigned long base = STACK_TOP; if (current->flags & PF_RANDOMIZE) { - base += get_random_int() & (VDSO_RANDOMIZE_SIZE - 1); + base += prandom_u32_max(VDSO_RANDOMIZE_SIZE); base = PAGE_ALIGN(base); } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 35b912bce429..bbe9ce471791 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -711,7 +711,7 @@ unsigned long mips_stack_top(void) unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() & ~PAGE_MASK; + sp -= prandom_u32_max(PAGE_SIZE); return sp & ALMASK; } diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index b2cc2c2dd4bf..5fd9bf1d596c 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -79,7 +79,7 @@ static unsigned long vdso_base(void) } if (current->flags & PF_RANDOMIZE) { - base += get_random_int() & (VDSO_RANDOMIZE_SIZE - 1); + base += prandom_u32_max(VDSO_RANDOMIZE_SIZE); base = PAGE_ALIGN(base); } diff --git a/arch/parisc/kernel/vdso.c b/arch/parisc/kernel/vdso.c index 63dc44c4c246..47e5960a2f96 100644 --- a/arch/parisc/kernel/vdso.c +++ b/arch/parisc/kernel/vdso.c @@ -75,7 +75,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, map_base = mm->mmap_base; if (current->flags & PF_RANDOMIZE) - map_base -= (get_random_int() & 0x1f) * PAGE_SIZE; + map_base -= prandom_u32_max(0x20) * PAGE_SIZE; vdso_text_start = get_unmapped_area(NULL, map_base, vdso_text_len, 0, 0); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 37df0428e4fb..599391c23573 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -2308,6 +2308,6 @@ void notrace __ppc64_runlatch_off(void) unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() & ~PAGE_MASK; + sp -= prandom_u32_max(PAGE_SIZE); return sp & ~0xf; } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index d5119e039d85..5ec78555dd2e 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -224,7 +224,7 @@ unsigned long __get_wchan(struct task_struct *p) unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() & ~PAGE_MASK; + sp -= prandom_u32_max(PAGE_SIZE); return sp & ~0xf; } diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 535099f2736d..3105ca5bd470 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -227,7 +227,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned long len) end -= len; if (end > start) { - offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + offset = prandom_u32_max(((end - start) >> PAGE_SHIFT) + 1); addr = start + (offset << PAGE_SHIFT); } else { addr = start; diff --git a/arch/sparc/vdso/vma.c b/arch/sparc/vdso/vma.c index cc19e09b0fa1..ae9a86cb6f3d 100644 --- a/arch/sparc/vdso/vma.c +++ b/arch/sparc/vdso/vma.c @@ -354,7 +354,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned int len) unsigned int offset; /* This loses some more bits than a modulo, but is cheaper */ - offset = get_random_int() & (PTRS_PER_PTE - 1); + offset = prandom_u32_max(PTRS_PER_PTE); return start + (offset << PAGE_SHIFT); } diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 80b90b1276a1..010bc422a09d 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -356,7 +356,7 @@ int singlestepping(void * t) unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() % 8192; + sp -= prandom_u32_max(8192); return sp & ~0xf; } #endif diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 6292b960037b..311eae30e089 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -327,7 +327,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) end -= len; if (end > start) { - offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + offset = prandom_u32_max(((end - start) >> PAGE_SHIFT) + 1); addr = start + (offset << PAGE_SHIFT); } else { addr = start; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index b1abf663417c..c032edcd3d95 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -53,7 +53,7 @@ static unsigned long int get_module_load_offset(void) */ if (module_load_offset == 0) module_load_offset = - (get_random_int() % 1024 + 1) * PAGE_SIZE; + (prandom_u32_max(1024) + 1) * PAGE_SIZE; mutex_unlock(&module_kaslr_mutex); } return module_load_offset; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 58a6ea472db9..c21b7347a26d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -965,7 +965,7 @@ early_param("idle", idle_setup); unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= get_random_int() % 8192; + sp -= prandom_u32_max(8192); return sp & ~0xf; } diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c index 0612a73638a8..423b21e80929 100644 --- a/arch/x86/mm/pat/cpa-test.c +++ b/arch/x86/mm/pat/cpa-test.c @@ -136,10 +136,10 @@ static int pageattr_test(void) failed += print_split(&sa); for (i = 0; i < NTEST; i++) { - unsigned long pfn = prandom_u32() % max_pfn_mapped; + unsigned long pfn = prandom_u32_max(max_pfn_mapped); addr[i] = (unsigned long)__va(pfn << PAGE_SHIFT); - len[i] = prandom_u32() % NPAGES; + len[i] = prandom_u32_max(NPAGES); len[i] = min_t(unsigned long, len[i], max_pfn_mapped - pfn - 1); if (len[i] == 0) diff --git a/crypto/testmgr.c b/crypto/testmgr.c index e4bb03b8b924..bff4833dbe7c 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -855,9 +855,9 @@ static int prepare_keybuf(const u8 *key, unsigned int ksize, /* Generate a random length in range [0, max_len], but prefer smaller values */ static unsigned int generate_random_length(unsigned int max_len) { - unsigned int len = prandom_u32() % (max_len + 1); + unsigned int len = prandom_u32_max(max_len + 1); - switch (prandom_u32() % 4) { + switch (prandom_u32_max(4)) { case 0: return len % 64; case 1: @@ -874,14 +874,14 @@ static void flip_random_bit(u8 *buf, size_t size) { size_t bitpos; - bitpos = prandom_u32() % (size * 8); + bitpos = prandom_u32_max(size * 8); buf[bitpos / 8] ^= 1 << (bitpos % 8); } /* Flip a random byte in the given nonempty data buffer */ static void flip_random_byte(u8 *buf, size_t size) { - buf[prandom_u32() % size] ^= 0xff; + buf[prandom_u32_max(size)] ^= 0xff; } /* Sometimes make some random changes to the given nonempty data buffer */ @@ -891,15 +891,15 @@ static void mutate_buffer(u8 *buf, size_t size) size_t i; /* Sometimes flip some bits */ - if (prandom_u32() % 4 == 0) { - num_flips = min_t(size_t, 1 << (prandom_u32() % 8), size * 8); + if (prandom_u32_max(4) == 0) { + num_flips = min_t(size_t, 1 << prandom_u32_max(8), size * 8); for (i = 0; i < num_flips; i++) flip_random_bit(buf, size); } /* Sometimes flip some bytes */ - if (prandom_u32() % 4 == 0) { - num_flips = min_t(size_t, 1 << (prandom_u32() % 8), size); + if (prandom_u32_max(4) == 0) { + num_flips = min_t(size_t, 1 << prandom_u32_max(8), size); for (i = 0; i < num_flips; i++) flip_random_byte(buf, size); } @@ -915,11 +915,11 @@ static void generate_random_bytes(u8 *buf, size_t count) if (count == 0) return; - switch (prandom_u32() % 8) { /* Choose a generation strategy */ + switch (prandom_u32_max(8)) { /* Choose a generation strategy */ case 0: case 1: /* All the same byte, plus optional mutations */ - switch (prandom_u32() % 4) { + switch (prandom_u32_max(4)) { case 0: b = 0x00; break; @@ -959,24 +959,24 @@ static char *generate_random_sgl_divisions(struct test_sg_division *divs, unsigned int this_len; const char *flushtype_str; - if (div == &divs[max_divs - 1] || prandom_u32() % 2 == 0) + if (div == &divs[max_divs - 1] || prandom_u32_max(2) == 0) this_len = remaining; else - this_len = 1 + (prandom_u32() % remaining); + this_len = 1 + prandom_u32_max(remaining); div->proportion_of_total = this_len; - if (prandom_u32() % 4 == 0) - div->offset = (PAGE_SIZE - 128) + (prandom_u32() % 128); - else if (prandom_u32() % 2 == 0) - div->offset = prandom_u32() % 32; + if (prandom_u32_max(4) == 0) + div->offset = (PAGE_SIZE - 128) + prandom_u32_max(128); + else if (prandom_u32_max(2) == 0) + div->offset = prandom_u32_max(32); else - div->offset = prandom_u32() % PAGE_SIZE; - if (prandom_u32() % 8 == 0) + div->offset = prandom_u32_max(PAGE_SIZE); + if (prandom_u32_max(8) == 0) div->offset_relative_to_alignmask = true; div->flush_type = FLUSH_TYPE_NONE; if (gen_flushes) { - switch (prandom_u32() % 4) { + switch (prandom_u32_max(4)) { case 0: div->flush_type = FLUSH_TYPE_REIMPORT; break; @@ -988,7 +988,7 @@ static char *generate_random_sgl_divisions(struct test_sg_division *divs, if (div->flush_type != FLUSH_TYPE_NONE && !(req_flags & CRYPTO_TFM_REQ_MAY_SLEEP) && - prandom_u32() % 2 == 0) + prandom_u32_max(2) == 0) div->nosimd = true; switch (div->flush_type) { @@ -1035,7 +1035,7 @@ static void generate_random_testvec_config(struct testvec_config *cfg, p += scnprintf(p, end - p, "random:"); - switch (prandom_u32() % 4) { + switch (prandom_u32_max(4)) { case 0: case 1: cfg->inplace_mode = OUT_OF_PLACE; @@ -1050,12 +1050,12 @@ static void generate_random_testvec_config(struct testvec_config *cfg, break; } - if (prandom_u32() % 2 == 0) { + if (prandom_u32_max(2) == 0) { cfg->req_flags |= CRYPTO_TFM_REQ_MAY_SLEEP; p += scnprintf(p, end - p, " may_sleep"); } - switch (prandom_u32() % 4) { + switch (prandom_u32_max(4)) { case 0: cfg->finalization_type = FINALIZATION_TYPE_FINAL; p += scnprintf(p, end - p, " use_final"); @@ -1071,7 +1071,7 @@ static void generate_random_testvec_config(struct testvec_config *cfg, } if (!(cfg->req_flags & CRYPTO_TFM_REQ_MAY_SLEEP) && - prandom_u32() % 2 == 0) { + prandom_u32_max(2) == 0) { cfg->nosimd = true; p += scnprintf(p, end - p, " nosimd"); } @@ -1084,7 +1084,7 @@ static void generate_random_testvec_config(struct testvec_config *cfg, cfg->req_flags); p += scnprintf(p, end - p, "]"); - if (cfg->inplace_mode == OUT_OF_PLACE && prandom_u32() % 2 == 0) { + if (cfg->inplace_mode == OUT_OF_PLACE && prandom_u32_max(2) == 0) { p += scnprintf(p, end - p, " dst_divs=["); p = generate_random_sgl_divisions(cfg->dst_divs, ARRAY_SIZE(cfg->dst_divs), @@ -1093,13 +1093,13 @@ static void generate_random_testvec_config(struct testvec_config *cfg, p += scnprintf(p, end - p, "]"); } - if (prandom_u32() % 2 == 0) { - cfg->iv_offset = 1 + (prandom_u32() % MAX_ALGAPI_ALIGNMASK); + if (prandom_u32_max(2) == 0) { + cfg->iv_offset = 1 + prandom_u32_max(MAX_ALGAPI_ALIGNMASK); p += scnprintf(p, end - p, " iv_offset=%u", cfg->iv_offset); } - if (prandom_u32() % 2 == 0) { - cfg->key_offset = 1 + (prandom_u32() % MAX_ALGAPI_ALIGNMASK); + if (prandom_u32_max(2) == 0) { + cfg->key_offset = 1 + prandom_u32_max(MAX_ALGAPI_ALIGNMASK); p += scnprintf(p, end - p, " key_offset=%u", cfg->key_offset); } @@ -1652,8 +1652,8 @@ static void generate_random_hash_testvec(struct shash_desc *desc, vec->ksize = 0; if (maxkeysize) { vec->ksize = maxkeysize; - if (prandom_u32() % 4 == 0) - vec->ksize = 1 + (prandom_u32() % maxkeysize); + if (prandom_u32_max(4) == 0) + vec->ksize = 1 + prandom_u32_max(maxkeysize); generate_random_bytes((u8 *)vec->key, vec->ksize); vec->setkey_error = crypto_shash_setkey(desc->tfm, vec->key, @@ -2218,13 +2218,13 @@ static void mutate_aead_message(struct aead_testvec *vec, bool aad_iv, const unsigned int aad_tail_size = aad_iv ? ivsize : 0; const unsigned int authsize = vec->clen - vec->plen; - if (prandom_u32() % 2 == 0 && vec->alen > aad_tail_size) { + if (prandom_u32_max(2) == 0 && vec->alen > aad_tail_size) { /* Mutate the AAD */ flip_random_bit((u8 *)vec->assoc, vec->alen - aad_tail_size); - if (prandom_u32() % 2 == 0) + if (prandom_u32_max(2) == 0) return; } - if (prandom_u32() % 2 == 0) { + if (prandom_u32_max(2) == 0) { /* Mutate auth tag (assuming it's at the end of ciphertext) */ flip_random_bit((u8 *)vec->ctext + vec->plen, authsize); } else { @@ -2249,7 +2249,7 @@ static void generate_aead_message(struct aead_request *req, const unsigned int ivsize = crypto_aead_ivsize(tfm); const unsigned int authsize = vec->clen - vec->plen; const bool inauthentic = (authsize >= MIN_COLLISION_FREE_AUTHSIZE) && - (prefer_inauthentic || prandom_u32() % 4 == 0); + (prefer_inauthentic || prandom_u32_max(4) == 0); /* Generate the AAD. */ generate_random_bytes((u8 *)vec->assoc, vec->alen); @@ -2257,7 +2257,7 @@ static void generate_aead_message(struct aead_request *req, /* Avoid implementation-defined behavior. */ memcpy((u8 *)vec->assoc + vec->alen - ivsize, vec->iv, ivsize); - if (inauthentic && prandom_u32() % 2 == 0) { + if (inauthentic && prandom_u32_max(2) == 0) { /* Generate a random ciphertext. */ generate_random_bytes((u8 *)vec->ctext, vec->clen); } else { @@ -2321,8 +2321,8 @@ static void generate_random_aead_testvec(struct aead_request *req, /* Key: length in [0, maxkeysize], but usually choose maxkeysize */ vec->klen = maxkeysize; - if (prandom_u32() % 4 == 0) - vec->klen = prandom_u32() % (maxkeysize + 1); + if (prandom_u32_max(4) == 0) + vec->klen = prandom_u32_max(maxkeysize + 1); generate_random_bytes((u8 *)vec->key, vec->klen); vec->setkey_error = crypto_aead_setkey(tfm, vec->key, vec->klen); @@ -2331,8 +2331,8 @@ static void generate_random_aead_testvec(struct aead_request *req, /* Tag length: in [0, maxauthsize], but usually choose maxauthsize */ authsize = maxauthsize; - if (prandom_u32() % 4 == 0) - authsize = prandom_u32() % (maxauthsize + 1); + if (prandom_u32_max(4) == 0) + authsize = prandom_u32_max(maxauthsize + 1); if (prefer_inauthentic && authsize < MIN_COLLISION_FREE_AUTHSIZE) authsize = MIN_COLLISION_FREE_AUTHSIZE; if (WARN_ON(authsize > maxdatasize)) @@ -2342,7 +2342,7 @@ static void generate_random_aead_testvec(struct aead_request *req, /* AAD, plaintext, and ciphertext lengths */ total_len = generate_random_length(maxdatasize); - if (prandom_u32() % 4 == 0) + if (prandom_u32_max(4) == 0) vec->alen = 0; else vec->alen = generate_random_length(total_len); @@ -2958,8 +2958,8 @@ static void generate_random_cipher_testvec(struct skcipher_request *req, /* Key: length in [0, maxkeysize], but usually choose maxkeysize */ vec->klen = maxkeysize; - if (prandom_u32() % 4 == 0) - vec->klen = prandom_u32() % (maxkeysize + 1); + if (prandom_u32_max(4) == 0) + vec->klen = prandom_u32_max(maxkeysize + 1); generate_random_bytes((u8 *)vec->key, vec->klen); vec->setkey_error = crypto_skcipher_setkey(tfm, vec->key, vec->klen); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index c897c4572036..ee69d50ba4fd 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -781,7 +781,7 @@ static struct socket *drbd_wait_for_connect(struct drbd_connection *connection, timeo = connect_int * HZ; /* 28.5% random jitter */ - timeo += (prandom_u32() & 1) ? timeo / 7 : -timeo / 7; + timeo += prandom_u32_max(2) ? timeo / 7 : -timeo / 7; err = wait_for_completion_interruptible_timeout(&ad->door_bell, timeo); if (err <= 0) @@ -1004,7 +1004,7 @@ retry: drbd_warn(connection, "Error receiving initial packet\n"); sock_release(s); randomize: - if (prandom_u32() & 1) + if (prandom_u32_max(2)) goto retry; } } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index cd75b0ca2555..845023c14eb3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2424,7 +2424,7 @@ gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv, /* Check whether the file_priv has already selected one ring. */ if ((int)file_priv->bsd_engine < 0) file_priv->bsd_engine = - get_random_int() % num_vcs_engines(dev_priv); + prandom_u32_max(num_vcs_engines(dev_priv)); return file_priv->bsd_engine; } diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 70da57ef2eeb..cc2222b85c88 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3807,7 +3807,7 @@ static int cma_alloc_any_port(enum rdma_ucm_port_space ps, inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - rover = prandom_u32() % remaining + low; + rover = prandom_u32_max(remaining) + low; retry: if (last_used_port != rover) { struct rdma_bind_list *bind_list; diff --git a/drivers/infiniband/hw/cxgb4/id_table.c b/drivers/infiniband/hw/cxgb4/id_table.c index f64e7e02b129..280d61466855 100644 --- a/drivers/infiniband/hw/cxgb4/id_table.c +++ b/drivers/infiniband/hw/cxgb4/id_table.c @@ -54,7 +54,7 @@ u32 c4iw_id_alloc(struct c4iw_id_table *alloc) if (obj < alloc->max) { if (alloc->flags & C4IW_ID_TABLE_F_RANDOM) - alloc->last += prandom_u32() % RANDOM_SKIP; + alloc->last += prandom_u32_max(RANDOM_SKIP); else alloc->last = obj + 1; if (alloc->last >= alloc->max) @@ -85,7 +85,7 @@ int c4iw_id_table_alloc(struct c4iw_id_table *alloc, u32 start, u32 num, alloc->start = start; alloc->flags = flags; if (flags & C4IW_ID_TABLE_F_RANDOM) - alloc->last = prandom_u32() % RANDOM_SKIP; + alloc->last = prandom_u32_max(RANDOM_SKIP); else alloc->last = 0; alloc->max = num; diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c index 492b122d0521..480c062dd04f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_ah.c +++ b/drivers/infiniband/hw/hns/hns_roce_ah.c @@ -41,9 +41,8 @@ static inline u16 get_ah_udp_sport(const struct rdma_ah_attr *ah_attr) u16 sport; if (!fl) - sport = get_random_u32() % - (IB_ROCE_UDP_ENCAP_VALID_PORT_MAX + 1 - - IB_ROCE_UDP_ENCAP_VALID_PORT_MIN) + + sport = prandom_u32_max(IB_ROCE_UDP_ENCAP_VALID_PORT_MAX + 1 - + IB_ROCE_UDP_ENCAP_VALID_PORT_MIN) + IB_ROCE_UDP_ENCAP_VALID_PORT_MIN; else sport = rdma_flow_label_to_udp_sport(fl); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 758e1d7ebc36..8546b8816524 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -1517,8 +1517,7 @@ static void rtrs_clt_err_recovery_work(struct work_struct *work) rtrs_clt_stop_and_destroy_conns(clt_path); queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork, msecs_to_jiffies(delay_ms + - prandom_u32() % - RTRS_RECONNECT_SEED)); + prandom_u32_max(RTRS_RECONNECT_SEED))); } static struct rtrs_clt_path *alloc_path(struct rtrs_clt_sess *clt, diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index f2c5a7e06fa9..3427555b0cca 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -401,7 +401,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) } if (bypass_torture_test(dc)) { - if ((get_random_int() & 3) == 3) + if (prandom_u32_max(4) == 3) goto skip; else goto rescale; diff --git a/drivers/media/test-drivers/vivid/vivid-touch-cap.c b/drivers/media/test-drivers/vivid/vivid-touch-cap.c index 64e3e4cb30c2..792660a85bc1 100644 --- a/drivers/media/test-drivers/vivid/vivid-touch-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-touch-cap.c @@ -221,7 +221,7 @@ static void vivid_fill_buff_noise(__s16 *tch_buf, int size) static inline int get_random_pressure(void) { - return get_random_int() % VIVID_PRESSURE_LIMIT; + return prandom_u32_max(VIVID_PRESSURE_LIMIT); } static void vivid_tch_buf_set(struct v4l2_pix_format *f, diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index ef53a2578824..95fa8fb1d45f 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -97,8 +97,8 @@ static void mmc_should_fail_request(struct mmc_host *host, !should_fail(&host->fail_mmc_request, data->blksz * data->blocks)) return; - data->error = data_errors[prandom_u32() % ARRAY_SIZE(data_errors)]; - data->bytes_xfered = (prandom_u32() % (data->bytes_xfered >> 9)) << 9; + data->error = data_errors[prandom_u32_max(ARRAY_SIZE(data_errors))]; + data->bytes_xfered = prandom_u32_max(data->bytes_xfered >> 9) << 9; } #else /* CONFIG_FAIL_MMC_REQUEST */ diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 581614196a84..c78bbc22e0d1 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -1858,7 +1858,7 @@ static void dw_mci_start_fault_timer(struct dw_mci *host) * Try to inject the error at random points during the data transfer. */ hrtimer_start(&host->fault_timer, - ms_to_ktime(prandom_u32() % 25), + ms_to_ktime(prandom_u32_max(25)), HRTIMER_MODE_REL); } diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c index 24beade95c7f..50bcf745e816 100644 --- a/drivers/mtd/nand/raw/nandsim.c +++ b/drivers/mtd/nand/raw/nandsim.c @@ -1405,9 +1405,9 @@ static void ns_do_bit_flips(struct nandsim *ns, int num) if (bitflips && prandom_u32() < (1 << 22)) { int flips = 1; if (bitflips > 1) - flips = (prandom_u32() % (int) bitflips) + 1; + flips = prandom_u32_max(bitflips) + 1; while (flips--) { - int pos = prandom_u32() % (num * 8); + int pos = prandom_u32_max(num * 8); ns->buf.byte[pos / 8] ^= (1 << (pos % 8)); NS_WARN("read_page: flipping bit %d in page %d " "reading from %d ecc: corrected=%u failed=%u\n", diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c index c4f271314f52..1c7201b0f372 100644 --- a/drivers/mtd/tests/mtd_nandecctest.c +++ b/drivers/mtd/tests/mtd_nandecctest.c @@ -47,7 +47,7 @@ struct nand_ecc_test { static void single_bit_error_data(void *error_data, void *correct_data, size_t size) { - unsigned int offset = prandom_u32() % (size * BITS_PER_BYTE); + unsigned int offset = prandom_u32_max(size * BITS_PER_BYTE); memcpy(error_data, correct_data, size); __change_bit_le(offset, error_data); @@ -58,9 +58,9 @@ static void double_bit_error_data(void *error_data, void *correct_data, { unsigned int offset[2]; - offset[0] = prandom_u32() % (size * BITS_PER_BYTE); + offset[0] = prandom_u32_max(size * BITS_PER_BYTE); do { - offset[1] = prandom_u32() % (size * BITS_PER_BYTE); + offset[1] = prandom_u32_max(size * BITS_PER_BYTE); } while (offset[0] == offset[1]); memcpy(error_data, correct_data, size); @@ -71,7 +71,7 @@ static void double_bit_error_data(void *error_data, void *correct_data, static unsigned int random_ecc_bit(size_t size) { - unsigned int offset = prandom_u32() % (3 * BITS_PER_BYTE); + unsigned int offset = prandom_u32_max(3 * BITS_PER_BYTE); if (size == 256) { /* @@ -79,7 +79,7 @@ static unsigned int random_ecc_bit(size_t size) * and 17th bit) in ECC code for 256 byte data block */ while (offset == 16 || offset == 17) - offset = prandom_u32() % (3 * BITS_PER_BYTE); + offset = prandom_u32_max(3 * BITS_PER_BYTE); } return offset; diff --git a/drivers/mtd/tests/stresstest.c b/drivers/mtd/tests/stresstest.c index cb29c8c1b370..d2faaca7f19d 100644 --- a/drivers/mtd/tests/stresstest.c +++ b/drivers/mtd/tests/stresstest.c @@ -45,9 +45,8 @@ static int rand_eb(void) unsigned int eb; again: - eb = prandom_u32(); /* Read or write up 2 eraseblocks at a time - hence 'ebcnt - 1' */ - eb %= (ebcnt - 1); + eb = prandom_u32_max(ebcnt - 1); if (bbt[eb]) goto again; return eb; @@ -55,20 +54,12 @@ again: static int rand_offs(void) { - unsigned int offs; - - offs = prandom_u32(); - offs %= bufsize; - return offs; + return prandom_u32_max(bufsize); } static int rand_len(int offs) { - unsigned int len; - - len = prandom_u32(); - len %= (bufsize - offs); - return len; + return prandom_u32_max(bufsize - offs); } static int do_read(void) @@ -127,7 +118,7 @@ static int do_write(void) static int do_operation(void) { - if (prandom_u32() & 1) + if (prandom_u32_max(2)) return do_read(); else return do_write(); diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c index 31d427ee191a..908d0e088557 100644 --- a/drivers/mtd/ubi/debug.c +++ b/drivers/mtd/ubi/debug.c @@ -590,7 +590,7 @@ int ubi_dbg_power_cut(struct ubi_device *ubi, int caller) if (ubi->dbg.power_cut_max > ubi->dbg.power_cut_min) { range = ubi->dbg.power_cut_max - ubi->dbg.power_cut_min; - ubi->dbg.power_cut_counter += prandom_u32() % range; + ubi->dbg.power_cut_counter += prandom_u32_max(range); } return 0; } diff --git a/drivers/mtd/ubi/debug.h b/drivers/mtd/ubi/debug.h index 118248a5d7d4..dc8d8f83657a 100644 --- a/drivers/mtd/ubi/debug.h +++ b/drivers/mtd/ubi/debug.h @@ -73,7 +73,7 @@ static inline int ubi_dbg_is_bgt_disabled(const struct ubi_device *ubi) static inline int ubi_dbg_is_bitflip(const struct ubi_device *ubi) { if (ubi->dbg.emulate_bitflips) - return !(prandom_u32() % 200); + return !prandom_u32_max(200); return 0; } @@ -87,7 +87,7 @@ static inline int ubi_dbg_is_bitflip(const struct ubi_device *ubi) static inline int ubi_dbg_is_write_failure(const struct ubi_device *ubi) { if (ubi->dbg.emulate_io_failures) - return !(prandom_u32() % 500); + return !prandom_u32_max(500); return 0; } @@ -101,7 +101,7 @@ static inline int ubi_dbg_is_write_failure(const struct ubi_device *ubi) static inline int ubi_dbg_is_erase_failure(const struct ubi_device *ubi) { if (ubi->dbg.emulate_io_failures) - return !(prandom_u32() % 400); + return !prandom_u32_max(400); return 0; } diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index e86503d97f32..f597b313acaa 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -4105,8 +4105,7 @@ static int cnic_cm_alloc_mem(struct cnic_dev *dev) for (i = 0; i < MAX_CM_SK_TBL_SZ; i++) atomic_set(&cp->csk_tbl[i].ref_count, 0); - port_id = prandom_u32(); - port_id %= CNIC_LOCAL_PORT_RANGE; + port_id = prandom_u32_max(CNIC_LOCAL_PORT_RANGE); if (cnic_init_id_tbl(&cp->csk_port_tbl, CNIC_LOCAL_PORT_RANGE, CNIC_LOCAL_PORT_MIN, port_id)) { cnic_cm_free_mem(dev); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index 539992dad8ba..a4256087ac82 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c @@ -919,8 +919,8 @@ static int csk_wait_memory(struct chtls_dev *cdev, current_timeo = *timeo_p; noblock = (*timeo_p ? false : true); if (csk_mem_free(cdev, sk)) { - current_timeo = (prandom_u32() % (HZ / 5)) + 2; - vm_wait = (prandom_u32() % (HZ / 5)) + 2; + current_timeo = prandom_u32_max(HZ / 5) + 2; + vm_wait = prandom_u32_max(HZ / 5) + 2; } add_wait_queue(sk_sleep(sk), &wait); diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 3e69079ed694..7df78a721b04 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -438,7 +438,7 @@ static int transmit(struct baycom_state *bc, int cnt, unsigned char stat) if ((--bc->hdlctx.slotcnt) > 0) return 0; bc->hdlctx.slotcnt = bc->ch_params.slottime; - if ((prandom_u32() % 256) > bc->ch_params.ppersist) + if (prandom_u32_max(256) > bc->ch_params.ppersist) return 0; } } diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c index a6184d6c7b15..bef904325a0f 100644 --- a/drivers/net/hamradio/hdlcdrv.c +++ b/drivers/net/hamradio/hdlcdrv.c @@ -377,7 +377,7 @@ void hdlcdrv_arbitrate(struct net_device *dev, struct hdlcdrv_state *s) if ((--s->hdlctx.slotcnt) > 0) return; s->hdlctx.slotcnt = s->ch_params.slottime; - if ((prandom_u32() % 256) > s->ch_params.ppersist) + if (prandom_u32_max(256) > s->ch_params.ppersist) return; start_tx(dev, s); } diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 980f2be32f05..97a6cc5c7ae8 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -626,7 +626,7 @@ static void yam_arbitrate(struct net_device *dev) yp->slotcnt = yp->slot / 10; /* is random > persist ? */ - if ((prandom_u32() % 256) > yp->pers) + if (prandom_u32_max(256) > yp->pers) return; yam_start_tx(dev, yp); diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 9e9adde335c8..349b7b1dbbf2 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -1758,7 +1758,7 @@ static int qca808x_phy_fast_retrain_config(struct phy_device *phydev) static int qca808x_phy_ms_random_seed_set(struct phy_device *phydev) { - u16 seed_value = (prandom_u32() % QCA808X_MASTER_SLAVE_SEED_RANGE); + u16 seed_value = prandom_u32_max(QCA808X_MASTER_SLAVE_SEED_RANGE); return at803x_debug_reg_mask(phydev, QCA808X_PHY_DEBUG_LOCAL_SEED, QCA808X_MASTER_SLAVE_SEED_CFG, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index 479041f070f9..10d9d9c63b28 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -1128,7 +1128,7 @@ static void brcmf_p2p_afx_handler(struct work_struct *work) if (afx_hdl->is_listen && afx_hdl->my_listen_chan) /* 100ms ~ 300ms */ err = brcmf_p2p_discover_listen(p2p, afx_hdl->my_listen_chan, - 100 * (1 + prandom_u32() % 3)); + 100 * (1 + prandom_u32_max(3))); else err = brcmf_p2p_act_frm_search(p2p, afx_hdl->peer_listen_chan); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index ed586e6d7d64..de0c545d50fd 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -1099,7 +1099,7 @@ static void iwl_mvm_mac_ctxt_cmd_fill_ap(struct iwl_mvm *mvm, iwl_mvm_mac_ap_iterator, &data); if (data.beacon_device_ts) { - u32 rand = (prandom_u32() % (64 - 36)) + 36; + u32 rand = prandom_u32_max(64 - 36) + 36; mvmvif->ap_beacon_time = data.beacon_device_ts + ieee80211_tu_to_usec(data.beacon_int * rand / 100); diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index 39e16eab47aa..ddc048069af2 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -2233,7 +2233,7 @@ static void fcoe_ctlr_vn_restart(struct fcoe_ctlr *fip) if (fip->probe_tries < FIP_VN_RLIM_COUNT) { fip->probe_tries++; - wait = prandom_u32() % FIP_VN_PROBE_WAIT; + wait = prandom_u32_max(FIP_VN_PROBE_WAIT); } else wait = FIP_VN_RLIM_INT; mod_timer(&fip->timer, jiffies + msecs_to_jiffies(wait)); @@ -3125,7 +3125,7 @@ static void fcoe_ctlr_vn_timeout(struct fcoe_ctlr *fip) fcoe_all_vn2vn, 0); fip->port_ka_time = jiffies + msecs_to_jiffies(FIP_VN_BEACON_INT + - (prandom_u32() % FIP_VN_BEACON_FUZZ)); + prandom_u32_max(FIP_VN_BEACON_FUZZ)); } if (time_before(fip->port_ka_time, next_time)) next_time = fip->port_ka_time; diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index cecfb2cb4c7b..df2fe7bd26d1 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -618,7 +618,7 @@ static int qedi_cm_alloc_mem(struct qedi_ctx *qedi) sizeof(struct qedi_endpoint *)), GFP_KERNEL); if (!qedi->ep_tbl) return -ENOMEM; - port_id = prandom_u32() % QEDI_LOCAL_PORT_RANGE; + port_id = prandom_u32_max(QEDI_LOCAL_PORT_RANGE); if (qedi_init_id_tbl(&qedi->lcl_port_tbl, QEDI_LOCAL_PORT_RANGE, QEDI_LOCAL_PORT_MIN, port_id)) { qedi_cm_free_mem(qedi); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 42351d7a0dd6..f0c6e7e7b92b 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -362,7 +362,7 @@ static int ceph_fill_fragtree(struct inode *inode, if (nsplits != ci->i_fragtree_nsplits) { update = true; } else if (nsplits) { - i = prandom_u32() % nsplits; + i = prandom_u32_max(nsplits); id = le32_to_cpu(fragtree->splits[i].frag); if (!__ceph_find_frag(ci, id)) update = true; diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 8d0a6d2c2da4..3fbabc98e1f7 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -29,7 +29,7 @@ static int __mdsmap_get_random_mds(struct ceph_mdsmap *m, bool ignore_laggy) return -1; /* pick */ - n = prandom_u32() % n; + n = prandom_u32_max(n); for (j = 0, i = 0; i < m->possible_max_rank; i++) { if (CEPH_MDS_IS_READY(i, ignore_laggy)) j++; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d733db8a0b02..989365b878a6 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3782,8 +3782,7 @@ cont_thread: } if (!progress) { elr->lr_next_sched = jiffies + - (prandom_u32() - % (EXT4_DEF_LI_MAX_START_DELAY * HZ)); + prandom_u32_max(EXT4_DEF_LI_MAX_START_DELAY * HZ); } if (time_before(elr->lr_next_sched, next_wakeup)) next_wakeup = elr->lr_next_sched; @@ -3930,8 +3929,8 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, * spread the inode table initialization requests * better. */ - elr->lr_next_sched = jiffies + (prandom_u32() % - (EXT4_DEF_LI_MAX_START_DELAY * HZ)); + elr->lr_next_sched = jiffies + prandom_u32_max( + EXT4_DEF_LI_MAX_START_DELAY * HZ); return elr; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index d36bcb23ccfe..4546e01b2ee0 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -282,7 +282,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, /* let's select beginning hot/small space first in no_heap mode*/ if (f2fs_need_rand_seg(sbi)) - p->offset = prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec); + p->offset = prandom_u32_max(MAIN_SECS(sbi) * sbi->segs_per_sec); else if (test_opt(sbi, NOHEAP) && (type == CURSEG_HOT_DATA || IS_NODESEG(type))) p->offset = 0; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 289bcb7ca300..acf3d3fa4363 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -2534,7 +2534,7 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) sanity_check_seg_type(sbi, seg_type); if (f2fs_need_rand_seg(sbi)) - return prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec); + return prandom_u32_max(MAIN_SECS(sbi) * sbi->segs_per_sec); /* if segs_per_sec is large than 1, we need to keep original policy. */ if (__is_large_section(sbi)) @@ -2588,7 +2588,7 @@ static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec) curseg->alloc_type = LFS; if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) curseg->fragment_remained_chunk = - prandom_u32() % sbi->max_fragment_chunk + 1; + prandom_u32_max(sbi->max_fragment_chunk) + 1; } static int __next_free_blkoff(struct f2fs_sb_info *sbi, @@ -2625,9 +2625,9 @@ static void __refresh_next_blkoff(struct f2fs_sb_info *sbi, /* To allocate block chunks in different sizes, use random number */ if (--seg->fragment_remained_chunk <= 0) { seg->fragment_remained_chunk = - prandom_u32() % sbi->max_fragment_chunk + 1; + prandom_u32_max(sbi->max_fragment_chunk) + 1; seg->next_blkoff += - prandom_u32() % sbi->max_fragment_hole + 1; + prandom_u32_max(sbi->max_fragment_hole) + 1; } } } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index fc718f6178f2..f4d3b568aa64 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2467,7 +2467,7 @@ error_dump: static inline int chance(unsigned int n, unsigned int out_of) { - return !!((prandom_u32() % out_of) + 1 <= n); + return !!(prandom_u32_max(out_of) + 1 <= n); } @@ -2485,13 +2485,13 @@ static int power_cut_emulated(struct ubifs_info *c, int lnum, int write) if (chance(1, 2)) { d->pc_delay = 1; /* Fail within 1 minute */ - delay = prandom_u32() % 60000; + delay = prandom_u32_max(60000); d->pc_timeout = jiffies; d->pc_timeout += msecs_to_jiffies(delay); ubifs_warn(c, "failing after %lums", delay); } else { d->pc_delay = 2; - delay = prandom_u32() % 10000; + delay = prandom_u32_max(10000); /* Fail within 10000 operations */ d->pc_cnt_max = delay; ubifs_warn(c, "failing after %lu calls", delay); @@ -2571,7 +2571,7 @@ static int corrupt_data(const struct ubifs_info *c, const void *buf, unsigned int from, to, ffs = chance(1, 2); unsigned char *p = (void *)buf; - from = prandom_u32() % len; + from = prandom_u32_max(len); /* Corruption span max to end of write unit */ to = min(len, ALIGN(from + 1, c->max_write_size)); diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index d76a19e460cd..cfbc31f709f4 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -1970,28 +1970,28 @@ static int dbg_populate_lsave(struct ubifs_info *c) if (!dbg_is_chk_gen(c)) return 0; - if (prandom_u32() & 3) + if (prandom_u32_max(4)) return 0; for (i = 0; i < c->lsave_cnt; i++) c->lsave[i] = c->main_first; list_for_each_entry(lprops, &c->empty_list, list) - c->lsave[prandom_u32() % c->lsave_cnt] = lprops->lnum; + c->lsave[prandom_u32_max(c->lsave_cnt)] = lprops->lnum; list_for_each_entry(lprops, &c->freeable_list, list) - c->lsave[prandom_u32() % c->lsave_cnt] = lprops->lnum; + c->lsave[prandom_u32_max(c->lsave_cnt)] = lprops->lnum; list_for_each_entry(lprops, &c->frdi_idx_list, list) - c->lsave[prandom_u32() % c->lsave_cnt] = lprops->lnum; + c->lsave[prandom_u32_max(c->lsave_cnt)] = lprops->lnum; heap = &c->lpt_heap[LPROPS_DIRTY_IDX - 1]; for (i = 0; i < heap->cnt; i++) - c->lsave[prandom_u32() % c->lsave_cnt] = heap->arr[i]->lnum; + c->lsave[prandom_u32_max(c->lsave_cnt)] = heap->arr[i]->lnum; heap = &c->lpt_heap[LPROPS_DIRTY - 1]; for (i = 0; i < heap->cnt; i++) - c->lsave[prandom_u32() % c->lsave_cnt] = heap->arr[i]->lnum; + c->lsave[prandom_u32_max(c->lsave_cnt)] = heap->arr[i]->lnum; heap = &c->lpt_heap[LPROPS_FREE - 1]; for (i = 0; i < heap->cnt; i++) - c->lsave[prandom_u32() % c->lsave_cnt] = heap->arr[i]->lnum; + c->lsave[prandom_u32_max(c->lsave_cnt)] = heap->arr[i]->lnum; return 1; } diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index 58c92c96ecef..01362ad5f804 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -700,7 +700,7 @@ static int alloc_idx_lebs(struct ubifs_info *c, int cnt) c->ilebs[c->ileb_cnt++] = lnum; dbg_cmt("LEB %d", lnum); } - if (dbg_is_chk_index(c) && !(prandom_u32() & 7)) + if (dbg_is_chk_index(c) && !prandom_u32_max(8)) return -ENOSPC; return 0; } diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index e2bdf089c0a3..6261599bb389 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1520,7 +1520,7 @@ xfs_alloc_ag_vextent_lastblock( #ifdef DEBUG /* Randomly don't execute the first algorithm. */ - if (prandom_u32() & 1) + if (prandom_u32_max(2)) return 0; #endif diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 6cdfd64bc56b..7838b31126e2 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -636,7 +636,7 @@ xfs_ialloc_ag_alloc( /* randomly do sparse inode allocations */ if (xfs_has_sparseinodes(tp->t_mountp) && igeo->ialloc_min_blks < igeo->ialloc_blks) - do_sparse = prandom_u32() & 1; + do_sparse = prandom_u32_max(2); #endif /* diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 296faa41d81d..7db588ed0be5 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -274,7 +274,7 @@ xfs_errortag_test( ASSERT(error_tag < XFS_ERRTAG_MAX); randfactor = mp->m_errortag[error_tag]; - if (!randfactor || prandom_u32() % randfactor) + if (!randfactor || prandom_u32_max(randfactor)) return false; xfs_warn_ratelimited(mp, diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 378956c93c94..efef68c9352a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -516,7 +516,7 @@ static inline int node_random(const nodemask_t *maskp) bit = first_node(*maskp); break; default: - bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_int() % w); + bit = find_nth_bit(maskp->bits, MAX_NUMNODES, prandom_u32_max(w)); break; } return bit; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 59cf4dc728a5..53c6c98bda7b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1032,7 +1032,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, hdr->size = size; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); - start = (get_random_int() % hole) & ~(alignment - 1); + start = prandom_u32_max(hole) & ~(alignment - 1); /* Leave a random number of instructions before BPF code. */ *image_ptr = &hdr->image[start]; @@ -1094,7 +1094,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, hole = min_t(unsigned int, size - (proglen + sizeof(*ro_header)), BPF_PROG_CHUNK_SIZE - sizeof(*ro_header)); - start = (get_random_int() % hole) & ~(alignment - 1); + start = prandom_u32_max(hole) & ~(alignment - 1); *image_ptr = &ro_header->image[start]; *rw_image = &(*rw_header)->image[start]; diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 353004155d65..43efb2a04160 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -399,7 +399,7 @@ static int *get_random_order(int count) order[n] = n; for (n = count - 1; n > 1; n--) { - r = get_random_int() % (n + 1); + r = prandom_u32_max(n + 1); if (r != n) { tmp = order[n]; order[n] = order[r]; @@ -538,7 +538,7 @@ static void stress_one_work(struct work_struct *work) { struct stress *stress = container_of(work, typeof(*stress), work); const int nlocks = stress->nlocks; - struct ww_mutex *lock = stress->locks + (get_random_int() % nlocks); + struct ww_mutex *lock = stress->locks + prandom_u32_max(nlocks); int err; do { diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index cee5da1e54c4..8058bec87ace 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -310,7 +310,7 @@ static void clocksource_verify_choose_cpus(void) * CPUs that are currently online. */ for (i = 1; i < n; i++) { - cpu = prandom_u32() % nr_cpu_ids; + cpu = prandom_u32_max(nr_cpu_ids); cpu = cpumask_next(cpu - 1, cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(cpu_online_mask); diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 423784d9c058..96e092de5b72 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -139,7 +139,7 @@ bool should_fail(struct fault_attr *attr, ssize_t size) return false; } - if (attr->probability <= prandom_u32() % 100) + if (attr->probability <= prandom_u32_max(100)) return false; if (!fail_stacktrace(attr)) diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c index 10754586403b..7c3c011abd29 100644 --- a/lib/find_bit_benchmark.c +++ b/lib/find_bit_benchmark.c @@ -174,8 +174,8 @@ static int __init find_bit_test(void) bitmap_zero(bitmap2, BITMAP_LEN); while (nbits--) { - __set_bit(prandom_u32() % BITMAP_LEN, bitmap); - __set_bit(prandom_u32() % BITMAP_LEN, bitmap2); + __set_bit(prandom_u32_max(BITMAP_LEN), bitmap); + __set_bit(prandom_u32_max(BITMAP_LEN), bitmap2); } test_find_next_bit(bitmap, BITMAP_LEN); diff --git a/lib/kobject.c b/lib/kobject.c index 5f0e71ab292c..a0b2dbfcfa23 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -694,7 +694,7 @@ static void kobject_release(struct kref *kref) { struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE - unsigned long delay = HZ + HZ * (get_random_int() & 0x3); + unsigned long delay = HZ + HZ * prandom_u32_max(4); pr_info("kobject: '%s' (%p): %s, parent %p (delayed %ld)\n", kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); diff --git a/lib/reed_solomon/test_rslib.c b/lib/reed_solomon/test_rslib.c index d9d1c33aebda..4d241bdc88aa 100644 --- a/lib/reed_solomon/test_rslib.c +++ b/lib/reed_solomon/test_rslib.c @@ -183,7 +183,7 @@ static int get_rcw_we(struct rs_control *rs, struct wspace *ws, do { /* Must not choose the same location twice */ - errloc = prandom_u32() % len; + errloc = prandom_u32_max(len); } while (errlocs[errloc] != 0); errlocs[errloc] = 1; @@ -194,12 +194,12 @@ static int get_rcw_we(struct rs_control *rs, struct wspace *ws, for (i = 0; i < eras; i++) { do { /* Must not choose the same location twice */ - errloc = prandom_u32() % len; + errloc = prandom_u32_max(len); } while (errlocs[errloc] != 0); derrlocs[i] = errloc; - if (ewsc && (prandom_u32() & 1)) { + if (ewsc && prandom_u32_max(2)) { /* Erasure with the symbol intact */ errlocs[errloc] = 2; } else { diff --git a/lib/sbitmap.c b/lib/sbitmap.c index a8108a962dfd..055dac069afb 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -33,7 +33,7 @@ static inline unsigned update_alloc_hint_before_get(struct sbitmap *sb, hint = this_cpu_read(*sb->alloc_hint); if (unlikely(hint >= depth)) { - hint = depth ? prandom_u32() % depth : 0; + hint = depth ? prandom_u32_max(depth) : 0; this_cpu_write(*sb->alloc_hint, hint); } diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c index 437d8e6b7cb1..86fadd3ba08c 100644 --- a/lib/test-string_helpers.c +++ b/lib/test-string_helpers.c @@ -587,7 +587,7 @@ static int __init test_string_helpers_init(void) for (i = 0; i < UNESCAPE_ALL_MASK + 1; i++) test_string_unescape("unescape", i, false); test_string_unescape("unescape inplace", - get_random_int() % (UNESCAPE_ANY + 1), true); + prandom_u32_max(UNESCAPE_ANY + 1), true); /* Without dictionary */ for (i = 0; i < ESCAPE_ALL_MASK + 1; i++) diff --git a/lib/test_hexdump.c b/lib/test_hexdump.c index 5144899d3c6b..0927f44cd478 100644 --- a/lib/test_hexdump.c +++ b/lib/test_hexdump.c @@ -149,7 +149,7 @@ static void __init test_hexdump(size_t len, int rowsize, int groupsize, static void __init test_hexdump_set(int rowsize, bool ascii) { size_t d = min_t(size_t, sizeof(data_b), rowsize); - size_t len = get_random_int() % d + 1; + size_t len = prandom_u32_max(d) + 1; test_hexdump(len, rowsize, 4, ascii); test_hexdump(len, rowsize, 2, ascii); @@ -208,11 +208,11 @@ static void __init test_hexdump_overflow(size_t buflen, size_t len, static void __init test_hexdump_overflow_set(size_t buflen, bool ascii) { unsigned int i = 0; - int rs = (get_random_int() % 2 + 1) * 16; + int rs = (prandom_u32_max(2) + 1) * 16; do { int gs = 1 << i; - size_t len = get_random_int() % rs + gs; + size_t len = prandom_u32_max(rs) + gs; test_hexdump_overflow(buflen, rounddown(len, gs), rs, gs, ascii); } while (i++ < 3); @@ -223,11 +223,11 @@ static int __init test_hexdump_init(void) unsigned int i; int rowsize; - rowsize = (get_random_int() % 2 + 1) * 16; + rowsize = (prandom_u32_max(2) + 1) * 16; for (i = 0; i < 16; i++) test_hexdump_set(rowsize, false); - rowsize = (get_random_int() % 2 + 1) * 16; + rowsize = (prandom_u32_max(2) + 1) * 16; for (i = 0; i < 16; i++) test_hexdump_set(rowsize, true); diff --git a/lib/test_list_sort.c b/lib/test_list_sort.c index ade7a1ea0c8e..19ff229b9c3a 100644 --- a/lib/test_list_sort.c +++ b/lib/test_list_sort.c @@ -71,7 +71,7 @@ static void list_sort_test(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, el); /* force some equivalencies */ - el->value = prandom_u32() % (TEST_LIST_LEN / 3); + el->value = prandom_u32_max(TEST_LIST_LEN / 3); el->serial = i; el->poison1 = TEST_POISON1; el->poison2 = TEST_POISON2; diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index f25692def781..2503ae2ae65d 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -1292,7 +1292,7 @@ static void match_all_not_assigned(struct kunit *test) KASAN_TEST_NEEDS_CONFIG_OFF(test, CONFIG_KASAN_GENERIC); for (i = 0; i < 256; i++) { - size = (get_random_int() % 1024) + 1; + size = prandom_u32_max(1024) + 1; ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); KUNIT_EXPECT_GE(test, (u8)get_tag(ptr), (u8)KASAN_TAG_MIN); @@ -1301,7 +1301,7 @@ static void match_all_not_assigned(struct kunit *test) } for (i = 0; i < 256; i++) { - order = (get_random_int() % 4) + 1; + order = prandom_u32_max(4) + 1; pages = alloc_pages(GFP_KERNEL, order); ptr = page_address(pages); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); @@ -1314,7 +1314,7 @@ static void match_all_not_assigned(struct kunit *test) return; for (i = 0; i < 256; i++) { - size = (get_random_int() % 1024) + 1; + size = prandom_u32_max(1024) + 1; ptr = vmalloc(size); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); KUNIT_EXPECT_GE(test, (u8)get_tag(ptr), (u8)KASAN_TAG_MIN); diff --git a/mm/slub.c b/mm/slub.c index 96dd392d7f99..157527d7101b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1881,7 +1881,7 @@ static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab) return false; freelist_count = oo_objects(s->oo); - pos = get_random_int() % freelist_count; + pos = prandom_u32_max(freelist_count); page_limit = slab->objects * s->size; start = fixup_red_left(s, slab_address(slab)); diff --git a/net/802/garp.c b/net/802/garp.c index f6012f8e59f0..fc9eb02a912f 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -407,7 +407,7 @@ static void garp_join_timer_arm(struct garp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(garp_join_time) * prandom_u32() >> 32; + delay = prandom_u32_max(msecs_to_jiffies(garp_join_time)); mod_timer(&app->join_timer, jiffies + delay); } diff --git a/net/802/mrp.c b/net/802/mrp.c index 35e04cc5390c..155f74d8b14f 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -592,7 +592,7 @@ static void mrp_join_timer_arm(struct mrp_applicant *app) { unsigned long delay; - delay = (u64)msecs_to_jiffies(mrp_join_time) * prandom_u32() >> 32; + delay = prandom_u32_max(msecs_to_jiffies(mrp_join_time)); mod_timer(&app->join_timer, jiffies + delay); } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 6a6898ee4049..db60217f911b 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -222,7 +222,7 @@ static void pick_new_mon(struct ceph_mon_client *monc) max--; } - n = prandom_u32() % max; + n = prandom_u32_max(max); if (o >= 0 && n >= o) n++; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 87b883c7bfd6..4e4f1e4bc265 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1479,7 +1479,7 @@ static bool target_should_be_paused(struct ceph_osd_client *osdc, static int pick_random_replica(const struct ceph_osds *acting) { - int i = prandom_u32() % acting->size; + int i = prandom_u32_max(acting->size); dout("%s picked osd%d, primary osd%d\n", __func__, acting->osds[i], acting->primary); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e93edb810103..3c4786b99907 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -111,7 +111,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) unsigned long neigh_rand_reach_time(unsigned long base) { - return base ? (prandom_u32() % base) + (base >> 1) : 0; + return base ? prandom_u32_max(base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 88906ba6d9a7..5ca4f953034c 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2324,7 +2324,7 @@ static inline int f_pick(struct pktgen_dev *pkt_dev) pkt_dev->curfl = 0; /*reset */ } } else { - flow = prandom_u32() % pkt_dev->cflows; + flow = prandom_u32_max(pkt_dev->cflows); pkt_dev->curfl = flow; if (pkt_dev->flows[flow].count > pkt_dev->lflow) { @@ -2380,10 +2380,9 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev) else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) { __u16 t; if (pkt_dev->flags & F_QUEUE_MAP_RND) { - t = prandom_u32() % - (pkt_dev->queue_map_max - - pkt_dev->queue_map_min + 1) - + pkt_dev->queue_map_min; + t = prandom_u32_max(pkt_dev->queue_map_max - + pkt_dev->queue_map_min + 1) + + pkt_dev->queue_map_min; } else { t = pkt_dev->cur_queue_map + 1; if (t > pkt_dev->queue_map_max) @@ -2412,7 +2411,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACSRC_RND) - mc = prandom_u32() % pkt_dev->src_mac_count; + mc = prandom_u32_max(pkt_dev->src_mac_count); else { mc = pkt_dev->cur_src_mac_offset++; if (pkt_dev->cur_src_mac_offset >= @@ -2438,7 +2437,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACDST_RND) - mc = prandom_u32() % pkt_dev->dst_mac_count; + mc = prandom_u32_max(pkt_dev->dst_mac_count); else { mc = pkt_dev->cur_dst_mac_offset++; @@ -2470,18 +2469,18 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) } if ((pkt_dev->flags & F_VID_RND) && (pkt_dev->vlan_id != 0xffff)) { - pkt_dev->vlan_id = prandom_u32() & (4096 - 1); + pkt_dev->vlan_id = prandom_u32_max(4096); } if ((pkt_dev->flags & F_SVID_RND) && (pkt_dev->svlan_id != 0xffff)) { - pkt_dev->svlan_id = prandom_u32() & (4096 - 1); + pkt_dev->svlan_id = prandom_u32_max(4096); } if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { if (pkt_dev->flags & F_UDPSRC_RND) - pkt_dev->cur_udp_src = prandom_u32() % - (pkt_dev->udp_src_max - pkt_dev->udp_src_min) - + pkt_dev->udp_src_min; + pkt_dev->cur_udp_src = prandom_u32_max( + pkt_dev->udp_src_max - pkt_dev->udp_src_min) + + pkt_dev->udp_src_min; else { pkt_dev->cur_udp_src++; @@ -2492,9 +2491,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) { if (pkt_dev->flags & F_UDPDST_RND) { - pkt_dev->cur_udp_dst = prandom_u32() % - (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min) - + pkt_dev->udp_dst_min; + pkt_dev->cur_udp_dst = prandom_u32_max( + pkt_dev->udp_dst_max - pkt_dev->udp_dst_min) + + pkt_dev->udp_dst_min; } else { pkt_dev->cur_udp_dst++; if (pkt_dev->cur_udp_dst >= pkt_dev->udp_dst_max) @@ -2509,7 +2508,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (imn < imx) { __u32 t; if (pkt_dev->flags & F_IPSRC_RND) - t = prandom_u32() % (imx - imn) + imn; + t = prandom_u32_max(imx - imn) + imn; else { t = ntohl(pkt_dev->cur_saddr); t++; @@ -2531,8 +2530,8 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->flags & F_IPDST_RND) { do { - t = prandom_u32() % - (imx - imn) + imn; + t = prandom_u32_max(imx - imn) + + imn; s = htonl(t); } while (ipv4_is_loopback(s) || ipv4_is_multicast(s) || @@ -2579,9 +2578,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) { __u32 t; if (pkt_dev->flags & F_TXSIZE_RND) { - t = prandom_u32() % - (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size) - + pkt_dev->min_pkt_size; + t = prandom_u32_max(pkt_dev->max_pkt_size - + pkt_dev->min_pkt_size) + + pkt_dev->min_pkt_size; } else { t = pkt_dev->cur_pkt_size + 1; if (t > pkt_dev->max_pkt_size) @@ -2590,7 +2589,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) pkt_dev->cur_pkt_size = t; } else if (pkt_dev->n_imix_entries > 0) { struct imix_pkt *entry; - __u32 t = prandom_u32() % IMIX_PRECISION; + __u32 t = prandom_u32_max(IMIX_PRECISION); __u8 entry_index = pkt_dev->imix_distribution[t]; entry = &pkt_dev->imix_entries[entry_index]; diff --git a/net/core/stream.c b/net/core/stream.c index 1105057ce00a..75fded8495f5 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -123,7 +123,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) DEFINE_WAIT_FUNC(wait, woken_wake_function); if (sk_stream_memory_free(sk)) - current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; + current_timeo = vm_wait = prandom_u32_max(HZ / 5) + 2; add_wait_queue(sk_sleep(sk), &wait); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index df0660d818ac..81be3e0f0e70 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -213,7 +213,7 @@ static void igmp_stop_timer(struct ip_mc_list *im) /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { - int tv = prandom_u32() % max_delay; + int tv = prandom_u32_max(max_delay); im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) @@ -222,7 +222,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) static void igmp_gq_start_timer(struct in_device *in_dev) { - int tv = prandom_u32() % in_dev->mr_maxdelay; + int tv = prandom_u32_max(in_dev->mr_maxdelay); unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && @@ -236,7 +236,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev) static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { - int tv = prandom_u32() % delay; + int tv = prandom_u32_max(delay); if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index ebca860e113f..4e84ed21d16f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -314,7 +314,7 @@ other_half_scan: if (likely(remaining > 1)) remaining &= ~1U; - offset = prandom_u32() % remaining; + offset = prandom_u32_max(remaining); /* __inet_hash_connect() favors ports having @low parity * We do the opposite to not pollute connect() users. */ diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index a0ad34e4f044..d3dc28156622 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1037,7 +1037,7 @@ ok: * on low contention the randomness is maximal and on high contention * it may be inexistent. */ - i = max_t(int, i, (prandom_u32() & 7) * 2); + i = max_t(int, i, prandom_u32_max(8) * 2); WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 10ce86bf228e..417834b7169d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -104,7 +104,7 @@ static inline u32 cstamp_delta(unsigned long cstamp) static inline s32 rfc3315_s14_backoff_init(s32 irt) { /* multiply 'initial retransmission time' by 0.9 .. 1.1 */ - u64 tmp = (900000 + prandom_u32() % 200001) * (u64)irt; + u64 tmp = (900000 + prandom_u32_max(200001)) * (u64)irt; do_div(tmp, 1000000); return (s32)tmp; } @@ -112,11 +112,11 @@ static inline s32 rfc3315_s14_backoff_init(s32 irt) static inline s32 rfc3315_s14_backoff_update(s32 rt, s32 mrt) { /* multiply 'retransmission timeout' by 1.9 .. 2.1 */ - u64 tmp = (1900000 + prandom_u32() % 200001) * (u64)rt; + u64 tmp = (1900000 + prandom_u32_max(200001)) * (u64)rt; do_div(tmp, 1000000); if ((s32)tmp > mrt) { /* multiply 'maximum retransmission time' by 0.9 .. 1.1 */ - tmp = (900000 + prandom_u32() % 200001) * (u64)mrt; + tmp = (900000 + prandom_u32_max(200001)) * (u64)mrt; do_div(tmp, 1000000); } return (s32)tmp; @@ -3967,7 +3967,7 @@ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else - rand_num = prandom_u32() % (idev->cnf.rtr_solicit_delay ? : 1); + rand_num = prandom_u32_max(idev->cnf.rtr_solicit_delay ?: 1); nonce = 0; if (idev->cnf.enhanced_dad || diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 0566ab03ddbe..7860383295d8 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1050,7 +1050,7 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, /* called with mc_lock */ static void mld_gq_start_work(struct inet6_dev *idev) { - unsigned long tv = prandom_u32() % idev->mc_maxdelay; + unsigned long tv = prandom_u32_max(idev->mc_maxdelay); idev->mc_gq_running = 1; if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) @@ -1068,7 +1068,7 @@ static void mld_gq_stop_work(struct inet6_dev *idev) /* called with mc_lock */ static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = prandom_u32() % delay; + unsigned long tv = prandom_u32_max(delay); if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) in6_dev_hold(idev); @@ -1085,7 +1085,7 @@ static void mld_ifc_stop_work(struct inet6_dev *idev) /* called with mc_lock */ static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) { - unsigned long tv = prandom_u32() % delay; + unsigned long tv = prandom_u32_max(delay); if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) in6_dev_hold(idev); @@ -1130,7 +1130,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) } if (delay >= resptime) - delay = prandom_u32() % resptime; + delay = prandom_u32_max(resptime); if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); @@ -2574,7 +2574,7 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); - delay = prandom_u32() % unsolicited_report_interval(ma->idev); + delay = prandom_u32_max(unsolicited_report_interval(ma->idev)); if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); diff --git a/net/netfilter/ipvs/ip_vs_twos.c b/net/netfilter/ipvs/ip_vs_twos.c index acb55d8393ef..f2579fc9c75b 100644 --- a/net/netfilter/ipvs/ip_vs_twos.c +++ b/net/netfilter/ipvs/ip_vs_twos.c @@ -71,8 +71,8 @@ static struct ip_vs_dest *ip_vs_twos_schedule(struct ip_vs_service *svc, * from 0 to total_weight */ total_weight += 1; - rweight1 = prandom_u32() % total_weight; - rweight2 = prandom_u32() % total_weight; + rweight1 = prandom_u32_max(total_weight); + rweight2 = prandom_u32_max(total_weight); /* Pick two weighted servers */ list_for_each_entry_rcu(dest, &svc->destinations, n_list) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d3f6db350de7..6ce8dd19f33c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1350,7 +1350,7 @@ static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) if (READ_ONCE(history[i]) == rxhash) count++; - victim = prandom_u32() % ROLLOVER_HLEN; + victim = prandom_u32_max(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index abe1bcc5c797..62d682b96b88 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -25,7 +25,7 @@ static struct tc_action_ops act_gact_ops; static int gact_net_rand(struct tcf_gact *gact) { smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ - if (prandom_u32() % gact->tcfg_pval) + if (prandom_u32_max(gact->tcfg_pval)) return gact->tcf_action; return gact->tcfg_paction; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 5ba36f70e3a1..7a25477f5d99 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -168,7 +168,7 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, psample_group = rcu_dereference_bh(s->psample_group); /* randomly sample packets according to rate */ - if (psample_group && (prandom_u32() % s->rate == 0)) { + if (psample_group && (prandom_u32_max(s->rate) == 0)) { if (!skb_at_tc_ingress(skb)) { md.in_ifindex = skb->skb_iif; md.out_ifindex = skb->dev->ifindex; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 18f4273a835b..bab45b3b1fdb 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -513,8 +513,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto finish_segs; } - skb->data[prandom_u32() % skb_headlen(skb)] ^= - 1<<(prandom_u32() % 8); + skb->data[prandom_u32_max(skb_headlen(skb))] ^= + 1<q.qlen >= sch->limit)) { diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 171f1a35d205..1e354ba44960 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8319,7 +8319,7 @@ static int sctp_get_port_local(struct sock *sk, union sctp_addr *addr) inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - rover = prandom_u32() % remaining + low; + rover = prandom_u32_max(remaining) + low; do { rover++; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index c3c693b51c94..f075a9fb5ccc 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -677,7 +677,7 @@ static void cache_limit_defers(void) /* Consider removing either the first or the last */ if (cache_defer_cnt > DFR_MAX) { - if (prandom_u32() & 1) + if (prandom_u32_max(2)) discard = list_entry(cache_defer_list.next, struct cache_deferred_req, recent); else diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index e976007f4fd0..f55ff5155b6e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1619,7 +1619,7 @@ static int xs_get_random_port(void) if (max < min) return -EADDRINUSE; range = max - min + 1; - rand = (unsigned short) prandom_u32() % range; + rand = prandom_u32_max(range); return rand + min; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index f1c3b8eb4b3d..e902b01ea3cb 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3010,7 +3010,7 @@ static int tipc_sk_insert(struct tipc_sock *tsk) struct net *net = sock_net(sk); struct tipc_net *tn = net_generic(net, tipc_net_id); u32 remaining = (TIPC_MAX_PORT - TIPC_MIN_PORT) + 1; - u32 portid = prandom_u32() % remaining + TIPC_MIN_PORT; + u32 portid = prandom_u32_max(remaining) + TIPC_MIN_PORT; while (remaining--) { portid++; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 81df34b3da6e..3d2fe7712ac5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2072,7 +2072,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) } else { u32 spi = 0; for (h = 0; h < high-low+1; h++) { - spi = low + prandom_u32()%(high-low+1); + spi = low + prandom_u32_max(high - low + 1); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { newspi = htonl(spi); -- cgit From 8b3ccbc1f1f91847160951aa15dd27c22dddcb49 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 16:43:38 +0200 Subject: treewide: use prandom_u32_max() when possible, part 2 Rather than incurring a division or requesting too many random bytes for the given range, use the prandom_u32_max() function, which only takes the minimum required bytes from the RNG and avoids divisions. This was done by hand, covering things that coccinelle could not do on its own. Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Reviewed-by: Jan Kara # for ext2, ext4, and sbitmap Acked-by: Jakub Kicinski Signed-off-by: Jason A. Donenfeld --- fs/ext2/ialloc.c | 3 +-- fs/ext4/ialloc.c | 5 ++--- lib/sbitmap.c | 2 +- lib/test_vmalloc.c | 17 ++++------------- 4 files changed, 8 insertions(+), 19 deletions(-) diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 998dd2ac8008..f4944c4dee60 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -277,8 +277,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent) int best_ndir = inodes_per_group; int best_group = -1; - group = prandom_u32(); - parent_group = (unsigned)group % ngroups; + parent_group = prandom_u32_max(ngroups); for (i = 0; i < ngroups; i++) { group = (parent_group + i) % ngroups; desc = ext2_get_group_desc (sb, group, NULL); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 208b87ce8858..7575aa359675 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -463,10 +463,9 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, hinfo.hash_version = DX_HASH_HALF_MD4; hinfo.seed = sbi->s_hash_seed; ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo); - grp = hinfo.hash; + parent_group = hinfo.hash % ngroups; } else - grp = prandom_u32(); - parent_group = (unsigned)grp % ngroups; + parent_group = prandom_u32_max(ngroups); for (i = 0; i < ngroups; i++) { g = (parent_group + i) % ngroups; get_orlov_stats(sb, g, flex_size, &stats); diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 055dac069afb..7280ae8ca88c 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -21,7 +21,7 @@ static int init_alloc_hint(struct sbitmap *sb, gfp_t flags) int i; for_each_possible_cpu(i) - *per_cpu_ptr(sb->alloc_hint, i) = prandom_u32() % depth; + *per_cpu_ptr(sb->alloc_hint, i) = prandom_u32_max(depth); } return 0; } diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index 4f2f2d1bac56..a26bbbf20e62 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -151,9 +151,7 @@ static int random_size_alloc_test(void) int i; for (i = 0; i < test_loop_count; i++) { - n = prandom_u32(); - n = (n % 100) + 1; - + n = prandom_u32_max(100) + 1; p = vmalloc(n * PAGE_SIZE); if (!p) @@ -293,16 +291,12 @@ pcpu_alloc_test(void) return -1; for (i = 0; i < 35000; i++) { - unsigned int r; - - r = prandom_u32(); - size = (r % (PAGE_SIZE / 4)) + 1; + size = prandom_u32_max(PAGE_SIZE / 4) + 1; /* * Maximum PAGE_SIZE */ - r = prandom_u32(); - align = 1 << ((r % 11) + 1); + align = 1 << (prandom_u32_max(11) + 1); pcpu[i] = __alloc_percpu(size, align); if (!pcpu[i]) @@ -393,14 +387,11 @@ static struct test_driver { static void shuffle_array(int *arr, int n) { - unsigned int rnd; int i, j; for (i = n - 1; i > 0; i--) { - rnd = prandom_u32(); - /* Cut the range. */ - j = rnd % i; + j = prandom_u32_max(i); /* Swap indexes. */ swap(arr[i], arr[j]); -- cgit From 7e3cf0843fe505491baa05e355e83e6997e089dd Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 17:23:53 +0200 Subject: treewide: use get_random_{u8,u16}() when possible, part 1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rather than truncate a 32-bit value to a 16-bit value or an 8-bit value, simply use the get_random_{u8,u16}() functions, which are faster than wasting the additional bytes from a 32-bit value. This was done mechanically with this coccinelle script: @@ expression E; identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; typedef u16; typedef __be16; typedef __le16; typedef u8; @@ ( - (get_random_u32() & 0xffff) + get_random_u16() | - (get_random_u32() & 0xff) + get_random_u8() | - (get_random_u32() % 65536) + get_random_u16() | - (get_random_u32() % 256) + get_random_u8() | - (get_random_u32() >> 16) + get_random_u16() | - (get_random_u32() >> 24) + get_random_u8() | - (u16)get_random_u32() + get_random_u16() | - (u8)get_random_u32() + get_random_u8() | - (__be16)get_random_u32() + (__be16)get_random_u16() | - (__le16)get_random_u32() + (__le16)get_random_u16() | - prandom_u32_max(65536) + get_random_u16() | - prandom_u32_max(256) + get_random_u8() | - E->inet_id = get_random_u32() + E->inet_id = get_random_u16() ) @@ identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; typedef u16; identifier v; @@ - u16 v = get_random_u32(); + u16 v = get_random_u16(); @@ identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; typedef u8; identifier v; @@ - u8 v = get_random_u32(); + u8 v = get_random_u8(); @@ identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; typedef u16; u16 v; @@ - v = get_random_u32(); + v = get_random_u16(); @@ identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; typedef u8; u8 v; @@ - v = get_random_u32(); + v = get_random_u8(); // Find a potential literal @literal_mask@ expression LITERAL; type T; identifier get_random_u32 =~ "get_random_int|prandom_u32|get_random_u32"; position p; @@ ((T)get_random_u32()@p & (LITERAL)) // Examine limits @script:python add_one@ literal << literal_mask.LITERAL; RESULT; @@ value = None if literal.startswith('0x'): value = int(literal, 16) elif literal[0] in '123456789': value = int(literal, 10) if value is None: print("I don't know how to handle %s" % (literal)) cocci.include_match(False) elif value < 256: coccinelle.RESULT = cocci.make_ident("get_random_u8") elif value < 65536: coccinelle.RESULT = cocci.make_ident("get_random_u16") else: print("Skipping large mask of %s" % (literal)) cocci.include_match(False) // Replace the literal mask with the calculated result. @plus_one@ expression literal_mask.LITERAL; position literal_mask.p; identifier add_one.RESULT; identifier FUNC; @@ - (FUNC()@p & (LITERAL)) + (RESULT() & LITERAL) Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Acked-by: Jakub Kicinski Acked-by: Toke Høiland-Jørgensen # for sch_cake Signed-off-by: Jason A. Donenfeld --- arch/arm/kernel/signal.c | 2 +- arch/arm64/kernel/syscall.c | 2 +- crypto/testmgr.c | 8 ++++---- drivers/media/common/v4l2-tpg/v4l2-tpg-core.c | 2 +- drivers/media/test-drivers/vivid/vivid-radio-rx.c | 4 ++-- drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c | 2 +- drivers/net/hamradio/baycom_epp.c | 2 +- drivers/net/hamradio/hdlcdrv.c | 2 +- drivers/net/hamradio/yam.c | 2 +- drivers/net/wireguard/selftest/allowedips.c | 4 ++-- drivers/net/wireless/st/cw1200/wsm.c | 2 +- drivers/scsi/lpfc/lpfc_hbadisc.c | 6 +++--- lib/cmdline_kunit.c | 4 ++-- net/dccp/ipv4.c | 4 ++-- net/ipv4/datagram.c | 2 +- net/ipv4/ip_output.c | 2 +- net/ipv4/tcp_ipv4.c | 4 ++-- net/mac80211/scan.c | 2 +- net/netfilter/nf_nat_core.c | 4 ++-- net/sched/sch_cake.c | 6 +++--- net/sctp/socket.c | 2 +- 21 files changed, 34 insertions(+), 34 deletions(-) diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index ea128e32e8ca..e07f359254c3 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -655,7 +655,7 @@ struct page *get_signal_page(void) PAGE_SIZE / sizeof(u32)); /* Give the signal return code some randomness */ - offset = 0x200 + (get_random_int() & 0x7fc); + offset = 0x200 + (get_random_u16() & 0x7fc); signal_return_offset = offset; /* Copy signal return handlers into the page */ diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 733451fe7e41..d72e8f23422d 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -67,7 +67,7 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, * * The resulting 5 bits of entropy is seen in SP[8:4]. */ - choose_random_kstack_offset(get_random_int() & 0x1FF); + choose_random_kstack_offset(get_random_u16() & 0x1FF); } static inline bool has_syscall_work(unsigned long flags) diff --git a/crypto/testmgr.c b/crypto/testmgr.c index bff4833dbe7c..bcd059caa1c8 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -927,7 +927,7 @@ static void generate_random_bytes(u8 *buf, size_t count) b = 0xff; break; default: - b = (u8)prandom_u32(); + b = get_random_u8(); break; } memset(buf, b, count); @@ -935,8 +935,8 @@ static void generate_random_bytes(u8 *buf, size_t count) break; case 2: /* Ascending or descending bytes, plus optional mutations */ - increment = (u8)prandom_u32(); - b = (u8)prandom_u32(); + increment = get_random_u8(); + b = get_random_u8(); for (i = 0; i < count; i++, b += increment) buf[i] = b; mutate_buffer(buf, count); @@ -944,7 +944,7 @@ static void generate_random_bytes(u8 *buf, size_t count) default: /* Fully random bytes */ for (i = 0; i < count; i++) - buf[i] = (u8)prandom_u32(); + buf[i] = get_random_u8(); } } diff --git a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c index 9b7bcdce6e44..303d02b1d71c 100644 --- a/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c +++ b/drivers/media/common/v4l2-tpg/v4l2-tpg-core.c @@ -870,7 +870,7 @@ static void precalculate_color(struct tpg_data *tpg, int k) g = tpg_colors[col].g; b = tpg_colors[col].b; } else if (tpg->pattern == TPG_PAT_NOISE) { - r = g = b = prandom_u32_max(256); + r = g = b = get_random_u8(); } else if (k == TPG_COLOR_RANDOM) { r = g = b = tpg->qual_offset + prandom_u32_max(196); } else if (k >= TPG_COLOR_RAMP) { diff --git a/drivers/media/test-drivers/vivid/vivid-radio-rx.c b/drivers/media/test-drivers/vivid/vivid-radio-rx.c index 232cab508f48..8bd09589fb15 100644 --- a/drivers/media/test-drivers/vivid/vivid-radio-rx.c +++ b/drivers/media/test-drivers/vivid/vivid-radio-rx.c @@ -104,8 +104,8 @@ retry: break; case 2: rds.block |= V4L2_RDS_BLOCK_ERROR; - rds.lsb = prandom_u32_max(256); - rds.msb = prandom_u32_max(256); + rds.lsb = get_random_u8(); + rds.msb = get_random_u8(); break; case 3: /* Skip block altogether */ if (i) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index f90bfba4b303..eda129d0143e 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1466,7 +1466,7 @@ static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt) tp->write_seq = snd_isn; tp->snd_nxt = snd_isn; tp->snd_una = snd_isn; - inet_sk(sk)->inet_id = prandom_u32(); + inet_sk(sk)->inet_id = get_random_u16(); assign_rxopt(sk, opt); if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10)) diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 7df78a721b04..791b4a53d69f 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -438,7 +438,7 @@ static int transmit(struct baycom_state *bc, int cnt, unsigned char stat) if ((--bc->hdlctx.slotcnt) > 0) return 0; bc->hdlctx.slotcnt = bc->ch_params.slottime; - if (prandom_u32_max(256) > bc->ch_params.ppersist) + if (get_random_u8() > bc->ch_params.ppersist) return 0; } } diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c index bef904325a0f..2263029d1a20 100644 --- a/drivers/net/hamradio/hdlcdrv.c +++ b/drivers/net/hamradio/hdlcdrv.c @@ -377,7 +377,7 @@ void hdlcdrv_arbitrate(struct net_device *dev, struct hdlcdrv_state *s) if ((--s->hdlctx.slotcnt) > 0) return; s->hdlctx.slotcnt = s->ch_params.slottime; - if (prandom_u32_max(256) > s->ch_params.ppersist) + if (get_random_u8() > s->ch_params.ppersist) return; start_tx(dev, s); } diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 97a6cc5c7ae8..2ed2f836f09a 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -626,7 +626,7 @@ static void yam_arbitrate(struct net_device *dev) yp->slotcnt = yp->slot / 10; /* is random > persist ? */ - if (prandom_u32_max(256) > yp->pers) + if (get_random_u8() > yp->pers) return; yam_start_tx(dev, yp); diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index 41db10f9be49..dd897c0740a2 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -310,7 +310,7 @@ static __init bool randomized_test(void) for (k = 0; k < 4; ++k) mutated[k] = (mutated[k] & mutate_mask[k]) | (~mutate_mask[k] & - prandom_u32_max(256)); + get_random_u8()); cidr = prandom_u32_max(32) + 1; peer = peers[prandom_u32_max(NUM_PEERS)]; if (wg_allowedips_insert_v4(&t, @@ -354,7 +354,7 @@ static __init bool randomized_test(void) for (k = 0; k < 4; ++k) mutated[k] = (mutated[k] & mutate_mask[k]) | (~mutate_mask[k] & - prandom_u32_max(256)); + get_random_u8()); cidr = prandom_u32_max(128) + 1; peer = peers[prandom_u32_max(NUM_PEERS)]; if (wg_allowedips_insert_v6(&t, diff --git a/drivers/net/wireless/st/cw1200/wsm.c b/drivers/net/wireless/st/cw1200/wsm.c index 5a3e7a626702..4a9e4b5d3547 100644 --- a/drivers/net/wireless/st/cw1200/wsm.c +++ b/drivers/net/wireless/st/cw1200/wsm.c @@ -1594,7 +1594,7 @@ static int cw1200_get_prio_queue(struct cw1200_common *priv, edca = &priv->edca.params[i]; score = ((edca->aifns + edca->cwmin) << 16) + ((edca->cwmax - edca->cwmin) * - (get_random_int() & 0xFFFF)); + get_random_u16()); if (score < best && (winner < 0 || i != 3)) { best = score; winner = i; diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index c7f834ba8edb..d38ebd7281b9 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -2156,8 +2156,8 @@ lpfc_check_pending_fcoe_event(struct lpfc_hba *phba, uint8_t unreg_fcf) * This function makes an running random selection decision on FCF record to * use through a sequence of @fcf_cnt eligible FCF records with equal * probability. To perform integer manunipulation of random numbers with - * size unit32_t, the lower 16 bits of the 32-bit random number returned - * from prandom_u32() are taken as the random random number generated. + * size unit32_t, a 16-bit random number returned from get_random_u16() is + * taken as the random random number generated. * * Returns true when outcome is for the newly read FCF record should be * chosen; otherwise, return false when outcome is for keeping the previously @@ -2169,7 +2169,7 @@ lpfc_sli4_new_fcf_random_select(struct lpfc_hba *phba, uint32_t fcf_cnt) uint32_t rand_num; /* Get 16-bit uniform random number */ - rand_num = 0xFFFF & prandom_u32(); + rand_num = get_random_u16(); /* Decision with probability 1/fcf_cnt */ if ((fcf_cnt * rand_num) < 0xFFFF) diff --git a/lib/cmdline_kunit.c b/lib/cmdline_kunit.c index a72a2c16066e..d4572dbc9145 100644 --- a/lib/cmdline_kunit.c +++ b/lib/cmdline_kunit.c @@ -76,7 +76,7 @@ static void cmdline_test_lead_int(struct kunit *test) int rc = cmdline_test_values[i]; int offset; - sprintf(in, "%u%s", get_random_int() % 256, str); + sprintf(in, "%u%s", get_random_u8(), str); /* Only first '-' after the number will advance the pointer */ offset = strlen(in) - strlen(str) + !!(rc == 2); cmdline_do_one_test(test, in, rc, offset); @@ -94,7 +94,7 @@ static void cmdline_test_tail_int(struct kunit *test) int rc = strcmp(str, "") ? (strcmp(str, "-") ? 0 : 1) : 1; int offset; - sprintf(in, "%s%u", str, get_random_int() % 256); + sprintf(in, "%s%u", str, get_random_u8()); /* * Only first and leading '-' not followed by integer * will advance the pointer. diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 6a6e121dc00c..713b7b8dad7e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -144,7 +144,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = prandom_u32(); + inet->inet_id = get_random_u16(); err = dccp_connect(sk); rt = NULL; @@ -443,7 +443,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = prandom_u32(); + newinet->inet_id = get_random_u16(); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 405a8c2aea64..0ee7fd259730 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len reuseport_has_conns(sk, true); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = prandom_u32(); + inet->inet_id = get_random_u16(); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1ae83ad629b2..922c87ef1ab5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -172,7 +172,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, * Avoid using the hashed IP ident generator. */ if (sk->sk_protocol == IPPROTO_TCP) - iph->id = (__force __be16)prandom_u32(); + iph->id = (__force __be16)get_random_u16(); else __ip_select_ident(net, iph, 1); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6376ad915765..7a250ef9d1b7 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -323,7 +323,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr); } - inet->inet_id = prandom_u32(); + inet->inet_id = get_random_u16(); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -1543,7 +1543,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = prandom_u32(); + newinet->inet_id = get_random_u16(); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 0e8c4f48c36d..dc3cdee51e66 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -641,7 +641,7 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, if (flags & IEEE80211_PROBE_FLAG_RANDOM_SN) { struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - u16 sn = get_random_u32(); + u16 sn = get_random_u16(); info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO; hdr->seq_ctrl = diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d8e6380f6337..18319a6e6806 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -468,7 +468,7 @@ find_free_id: if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) off = (ntohs(*keyptr) - ntohs(range->base_proto.all)); else - off = prandom_u32(); + off = get_random_u16(); attempts = range_size; if (attempts > max_attempts) @@ -490,7 +490,7 @@ another_round: if (attempts >= range_size || attempts < 16) return; attempts /= 2; - off = prandom_u32(); + off = get_random_u16(); goto another_round; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 55c6879d2c7e..7193d25932ce 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2092,11 +2092,11 @@ retry: WARN_ON(host_load > CAKE_QUEUES); - /* The shifted prandom_u32() is a way to apply dithering to - * avoid accumulating roundoff errors + /* The get_random_u16() is a way to apply dithering to avoid + * accumulating roundoff errors */ flow->deficit += (b->flow_quantum * quantum_div[host_load] + - (prandom_u32() >> 16)) >> 16; + get_random_u16()) >> 16; list_move_tail(&flow->flowchain, &b->old_flows); goto retry; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1e354ba44960..83628c347744 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9448,7 +9448,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = prandom_u32(); + newinet->inet_id = get_random_u16(); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; -- cgit From f743f16c548b1a2633e8b6034058d6475d7f26a3 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 17:23:53 +0200 Subject: treewide: use get_random_{u8,u16}() when possible, part 2 Rather than truncate a 32-bit value to a 16-bit value or an 8-bit value, simply use the get_random_{u8,u16}() functions, which are faster than wasting the additional bytes from a 32-bit value. This was done by hand, identifying all of the places where one of the random integer functions was used in a non-32-bit context. Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Acked-by: Jakub Kicinski Acked-by: Heiko Carstens # for s390 Signed-off-by: Jason A. Donenfeld --- arch/s390/kernel/process.c | 2 +- drivers/mtd/nand/raw/nandsim.c | 2 +- drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c | 2 +- lib/test_vmalloc.c | 2 +- net/rds/bind.c | 2 +- net/sched/sch_sfb.c | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 5ec78555dd2e..42af4b3aa02b 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -230,7 +230,7 @@ unsigned long arch_align_stack(unsigned long sp) static inline unsigned long brk_rnd(void) { - return (get_random_int() & BRK_RND_MASK) << PAGE_SHIFT; + return (get_random_u16() & BRK_RND_MASK) << PAGE_SHIFT; } unsigned long arch_randomize_brk(struct mm_struct *mm) diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c index 50bcf745e816..d211939c8bdd 100644 --- a/drivers/mtd/nand/raw/nandsim.c +++ b/drivers/mtd/nand/raw/nandsim.c @@ -1402,7 +1402,7 @@ static int ns_do_read_error(struct nandsim *ns, int num) static void ns_do_bit_flips(struct nandsim *ns, int num) { - if (bitflips && prandom_u32() < (1 << 22)) { + if (bitflips && get_random_u16() < (1 << 6)) { int flips = 1; if (bitflips > 1) flips = prandom_u32_max(bitflips) + 1; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c index d0a7465be586..170c61c8136c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c @@ -177,7 +177,7 @@ static int brcmf_pno_set_random(struct brcmf_if *ifp, struct brcmf_pno_info *pi) memcpy(pfn_mac.mac, mac_addr, ETH_ALEN); for (i = 0; i < ETH_ALEN; i++) { pfn_mac.mac[i] &= mac_mask[i]; - pfn_mac.mac[i] |= get_random_int() & ~(mac_mask[i]); + pfn_mac.mac[i] |= get_random_u8() & ~(mac_mask[i]); } /* Clear multi bit */ pfn_mac.mac[0] &= 0xFE; diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index a26bbbf20e62..cf7780572f5b 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -80,7 +80,7 @@ static int random_size_align_alloc_test(void) int i; for (i = 0; i < test_loop_count; i++) { - rnd = prandom_u32(); + rnd = get_random_u8(); /* * Maximum 1024 pages, if PAGE_SIZE is 4096. diff --git a/net/rds/bind.c b/net/rds/bind.c index 5b5fb4ca8d3e..97a29172a8ee 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -104,7 +104,7 @@ static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr, return -EINVAL; last = rover; } else { - rover = max_t(u16, prandom_u32(), 2); + rover = max_t(u16, get_random_u16(), 2); last = rover - 1; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index e2389fa3cff8..0366a1a029a9 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -379,7 +379,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, goto enqueue; } - r = prandom_u32() & SFB_MAX_PROB; + r = get_random_u16() & SFB_MAX_PROB; if (unlikely(r < p_min)) { if (unlikely(p_min > SFB_MAX_PROB / 2)) { -- cgit From a251c17aa558d8e3128a528af5cf8b9d7caae4fd Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 17:43:22 +0200 Subject: treewide: use get_random_u32() when possible MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The prandom_u32() function has been a deprecated inline wrapper around get_random_u32() for several releases now, and compiles down to the exact same code. Replace the deprecated wrapper with a direct call to the real function. The same also applies to get_random_int(), which is just a wrapper around get_random_u32(). This was done as a basic find and replace. Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Reviewed-by: Jan Kara # for ext4 Acked-by: Toke Høiland-Jørgensen # for sch_cake Acked-by: Chuck Lever # for nfsd Acked-by: Jakub Kicinski Acked-by: Mika Westerberg # for thunderbolt Acked-by: Darrick J. Wong # for xfs Acked-by: Helge Deller # for parisc Acked-by: Heiko Carstens # for s390 Signed-off-by: Jason A. Donenfeld --- Documentation/networking/filter.rst | 2 +- arch/parisc/kernel/process.c | 2 +- arch/parisc/kernel/sys_parisc.c | 4 ++-- arch/s390/mm/mmap.c | 2 +- arch/x86/kernel/cpu/amd.c | 2 +- drivers/gpu/drm/i915/i915_gem_gtt.c | 6 +++--- drivers/gpu/drm/i915/selftests/i915_selftest.c | 2 +- drivers/gpu/drm/tests/drm_buddy_test.c | 2 +- drivers/gpu/drm/tests/drm_mm_test.c | 2 +- drivers/infiniband/hw/cxgb4/cm.c | 4 ++-- drivers/infiniband/hw/hfi1/tid_rdma.c | 2 +- drivers/infiniband/hw/mlx4/mad.c | 2 +- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 2 +- drivers/md/raid5-cache.c | 2 +- drivers/media/test-drivers/vivid/vivid-touch-cap.c | 4 ++-- drivers/misc/habanalabs/gaudi2/gaudi2.c | 2 +- drivers/net/bonding/bond_main.c | 2 +- drivers/net/ethernet/broadcom/cnic.c | 2 +- .../ethernet/chelsio/inline_crypto/chtls/chtls_cm.c | 2 +- drivers/net/ethernet/rocker/rocker_main.c | 6 +++--- drivers/net/wireless/marvell/mwifiex/cfg80211.c | 4 ++-- drivers/net/wireless/microchip/wilc1000/cfg80211.c | 2 +- drivers/net/wireless/quantenna/qtnfmac/cfg80211.c | 2 +- drivers/net/wireless/ti/wlcore/main.c | 2 +- drivers/nvme/common/auth.c | 2 +- drivers/scsi/cxgbi/cxgb4i/cxgb4i.c | 4 ++-- drivers/target/iscsi/cxgbit/cxgbit_cm.c | 2 +- drivers/thunderbolt/xdomain.c | 2 +- drivers/video/fbdev/uvesafb.c | 2 +- fs/exfat/inode.c | 2 +- fs/ext4/ialloc.c | 2 +- fs/ext4/ioctl.c | 4 ++-- fs/ext4/mmp.c | 2 +- fs/f2fs/namei.c | 2 +- fs/fat/inode.c | 2 +- fs/nfsd/nfs4state.c | 4 ++-- fs/ntfs3/fslog.c | 6 +++--- fs/ubifs/journal.c | 2 +- fs/xfs/libxfs/xfs_ialloc.c | 2 +- fs/xfs/xfs_icache.c | 2 +- fs/xfs/xfs_log.c | 2 +- include/net/netfilter/nf_queue.h | 2 +- include/net/red.h | 2 +- include/net/sock.h | 2 +- kernel/bpf/bloom_filter.c | 2 +- kernel/bpf/core.c | 2 +- kernel/bpf/hashtab.c | 2 +- kernel/bpf/verifier.c | 2 +- kernel/kcsan/selftest.c | 2 +- lib/random32.c | 2 +- lib/reed_solomon/test_rslib.c | 6 +++--- lib/test_fprobe.c | 2 +- lib/test_kprobes.c | 2 +- lib/test_min_heap.c | 6 +++--- lib/test_rhashtable.c | 6 +++--- mm/shmem.c | 2 +- mm/slab.c | 2 +- net/core/pktgen.c | 4 ++-- net/ipv4/route.c | 2 +- net/ipv4/tcp_cdg.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/ip6_flowlabel.c | 2 +- net/ipv6/output_core.c | 2 +- net/netfilter/ipvs/ip_vs_conn.c | 2 +- net/netfilter/xt_statistic.c | 2 +- net/openvswitch/actions.c | 2 +- net/sched/sch_cake.c | 2 +- net/sched/sch_netem.c | 18 +++++++++--------- net/sunrpc/auth_gss/gss_krb5_wrap.c | 4 ++-- net/sunrpc/xprt.c | 2 +- net/unix/af_unix.c | 2 +- 71 files changed, 100 insertions(+), 100 deletions(-) diff --git a/Documentation/networking/filter.rst b/Documentation/networking/filter.rst index 43cdc4d34745..f69da5074860 100644 --- a/Documentation/networking/filter.rst +++ b/Documentation/networking/filter.rst @@ -305,7 +305,7 @@ Possible BPF extensions are shown in the following table: vlan_tci skb_vlan_tag_get(skb) vlan_avail skb_vlan_tag_present(skb) vlan_tpid skb->vlan_proto - rand prandom_u32() + rand get_random_u32() =================================== ================================================= These extensions can also be prefixed with '#'. diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 7c37e09c92da..18c4f0e3e906 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -288,7 +288,7 @@ __get_wchan(struct task_struct *p) static inline unsigned long brk_rnd(void) { - return (get_random_int() & BRK_RND_MASK) << PAGE_SHIFT; + return (get_random_u32() & BRK_RND_MASK) << PAGE_SHIFT; } unsigned long arch_randomize_brk(struct mm_struct *mm) diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 2b34294517a1..848b0702005d 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -239,14 +239,14 @@ static unsigned long mmap_rnd(void) unsigned long rnd = 0; if (current->flags & PF_RANDOMIZE) - rnd = get_random_int() & MMAP_RND_MASK; + rnd = get_random_u32() & MMAP_RND_MASK; return rnd << PAGE_SHIFT; } unsigned long arch_mmap_rnd(void) { - return (get_random_int() & MMAP_RND_MASK) << PAGE_SHIFT; + return (get_random_u32() & MMAP_RND_MASK) << PAGE_SHIFT; } static unsigned long mmap_legacy_base(void) diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 5980ce348832..3327c47bc181 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -37,7 +37,7 @@ static inline int mmap_is_legacy(struct rlimit *rlim_stack) unsigned long arch_mmap_rnd(void) { - return (get_random_int() & MMAP_RND_MASK) << PAGE_SHIFT; + return (get_random_u32() & MMAP_RND_MASK) << PAGE_SHIFT; } static unsigned long mmap_base_legacy(unsigned long rnd) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 48276c0e479d..860b60273df3 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -503,7 +503,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) va_align.flags = ALIGN_VA_32 | ALIGN_VA_64; /* A random value per boot for bit slice [12:upper_bit) */ - va_align.bits = get_random_int() & va_align.mask; + va_align.bits = get_random_u32() & va_align.mask; } if (cpu_has(c, X86_FEATURE_MWAITX)) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 329ff75b80b9..7bd1861ddbdf 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -137,12 +137,12 @@ static u64 random_offset(u64 start, u64 end, u64 len, u64 align) range = round_down(end - len, align) - round_up(start, align); if (range) { if (sizeof(unsigned long) == sizeof(u64)) { - addr = get_random_long(); + addr = get_random_u64(); } else { - addr = get_random_int(); + addr = get_random_u32(); if (range > U32_MAX) { addr <<= 32; - addr |= get_random_int(); + addr |= get_random_u32(); } } div64_u64_rem(addr, range, &addr); diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c index c4e932368b37..39da0fb0d6d2 100644 --- a/drivers/gpu/drm/i915/selftests/i915_selftest.c +++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c @@ -135,7 +135,7 @@ static int __run_selftests(const char *name, int err = 0; while (!i915_selftest.random_seed) - i915_selftest.random_seed = get_random_int(); + i915_selftest.random_seed = get_random_u32(); i915_selftest.timeout_jiffies = i915_selftest.timeout_ms ? diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c index 7a2b2d6bc3fe..62f69589a72d 100644 --- a/drivers/gpu/drm/tests/drm_buddy_test.c +++ b/drivers/gpu/drm/tests/drm_buddy_test.c @@ -729,7 +729,7 @@ static void drm_test_buddy_alloc_limit(struct kunit *test) static int drm_buddy_init_test(struct kunit *test) { while (!random_seed) - random_seed = get_random_int(); + random_seed = get_random_u32(); return 0; } diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c index 659d1af4dca7..c4b66eeae203 100644 --- a/drivers/gpu/drm/tests/drm_mm_test.c +++ b/drivers/gpu/drm/tests/drm_mm_test.c @@ -2212,7 +2212,7 @@ err_nodes: static int drm_mm_init_test(struct kunit *test) { while (!random_seed) - random_seed = get_random_int(); + random_seed = get_random_u32(); return 0; } diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 14392c942f49..499a425a3379 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -734,7 +734,7 @@ static int send_connect(struct c4iw_ep *ep) &ep->com.remote_addr; int ret; enum chip_type adapter_type = ep->com.dev->rdev.lldi.adapter_type; - u32 isn = (prandom_u32() & ~7UL) - 1; + u32 isn = (get_random_u32() & ~7UL) - 1; struct net_device *netdev; u64 params; @@ -2469,7 +2469,7 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb, } if (!is_t4(adapter_type)) { - u32 isn = (prandom_u32() & ~7UL) - 1; + u32 isn = (get_random_u32() & ~7UL) - 1; skb = get_skb(skb, roundup(sizeof(*rpl5), 16), GFP_KERNEL); rpl5 = __skb_put_zero(skb, roundup(sizeof(*rpl5), 16)); diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 2a7abf7a1f7f..18b05ffb415a 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -850,7 +850,7 @@ void hfi1_kern_init_ctxt_generations(struct hfi1_ctxtdata *rcd) int i; for (i = 0; i < RXE_NUM_TID_FLOWS; i++) { - rcd->flows[i].generation = mask_generation(prandom_u32()); + rcd->flows[i].generation = mask_generation(get_random_u32()); kern_set_hw_flow(rcd, KERN_GENERATION_RESERVED, i); } } diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index d13ecbdd4391..a37cfac5e23f 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -96,7 +96,7 @@ static void __propagate_pkey_ev(struct mlx4_ib_dev *dev, int port_num, __be64 mlx4_ib_gen_node_guid(void) { #define NODE_GUID_HI ((u64) (((u64)IB_OPENIB_OUI) << 40)) - return cpu_to_be64(NODE_GUID_HI | prandom_u32()); + return cpu_to_be64(NODE_GUID_HI | get_random_u32()); } __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index ebb35b809f26..b610d36295bb 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -465,7 +465,7 @@ static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, goto err_qp; } - psn = prandom_u32() & 0xffffff; + psn = get_random_u32() & 0xffffff; ret = ipoib_cm_modify_rx_qp(dev, cm_id, p->qp, psn); if (ret) goto err_modify; diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 79c73330020b..832d8566e165 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -2994,7 +2994,7 @@ static int r5l_load_log(struct r5l_log *log) } create: if (create_super) { - log->last_cp_seq = prandom_u32(); + log->last_cp_seq = get_random_u32(); cp = 0; r5l_log_write_empty_meta_block(log, cp, log->last_cp_seq); /* diff --git a/drivers/media/test-drivers/vivid/vivid-touch-cap.c b/drivers/media/test-drivers/vivid/vivid-touch-cap.c index 792660a85bc1..6cc32eb54f9d 100644 --- a/drivers/media/test-drivers/vivid/vivid-touch-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-touch-cap.c @@ -210,7 +210,7 @@ static void vivid_fill_buff_noise(__s16 *tch_buf, int size) /* Fill 10% of the values within range -3 and 3, zero the others */ for (i = 0; i < size; i++) { - unsigned int rand = get_random_int(); + unsigned int rand = get_random_u32(); if (rand % 10) tch_buf[i] = 0; @@ -272,7 +272,7 @@ void vivid_fillbuff_tch(struct vivid_dev *dev, struct vivid_buffer *buf) return; if (test_pat_idx == 0) - dev->tch_pat_random = get_random_int(); + dev->tch_pat_random = get_random_u32(); rand = dev->tch_pat_random; switch (test_pattern) { diff --git a/drivers/misc/habanalabs/gaudi2/gaudi2.c b/drivers/misc/habanalabs/gaudi2/gaudi2.c index 75c4bef7841c..65e6cae6100a 100644 --- a/drivers/misc/habanalabs/gaudi2/gaudi2.c +++ b/drivers/misc/habanalabs/gaudi2/gaudi2.c @@ -2948,7 +2948,7 @@ static void gaudi2_user_interrupt_setup(struct hl_device *hdev) static inline int gaudi2_get_non_zero_random_int(void) { - int rand = get_random_int(); + int rand = get_random_u32(); return rand ? rand : 1; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 24bb50dfd362..e84c49bf4d0c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4806,7 +4806,7 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond) switch (packets_per_slave) { case 0: - slave_id = prandom_u32(); + slave_id = get_random_u32(); break; case 1: slave_id = this_cpu_inc_return(*bond->rr_tx_counter); diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index f597b313acaa..2198e35d9e18 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -4164,7 +4164,7 @@ static int cnic_cm_init_bnx2_hw(struct cnic_dev *dev) { u32 seed; - seed = prandom_u32(); + seed = get_random_u32(); cnic_ctx_wr(dev, 45, 0, seed); return 0; } diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index eda129d0143e..c2e7037c7ba1 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1063,7 +1063,7 @@ static void chtls_pass_accept_rpl(struct sk_buff *skb, opt2 |= WND_SCALE_EN_V(WSCALE_OK(tp)); rpl5->opt0 = cpu_to_be64(opt0); rpl5->opt2 = cpu_to_be32(opt2); - rpl5->iss = cpu_to_be32((prandom_u32() & ~7UL) - 1); + rpl5->iss = cpu_to_be32((get_random_u32() & ~7UL) - 1); set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id); t4_set_arp_err_handler(skb, sk, chtls_accept_rpl_arp_failure); cxgb4_l2t_send(csk->egress_dev, skb, csk->l2t_entry); diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 023682cd2768..5672d952452f 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -129,7 +129,7 @@ static int rocker_reg_test(const struct rocker *rocker) u64 test_reg; u64 rnd; - rnd = prandom_u32(); + rnd = get_random_u32(); rnd >>= 1; rocker_write32(rocker, TEST_REG, rnd); test_reg = rocker_read32(rocker, TEST_REG); @@ -139,9 +139,9 @@ static int rocker_reg_test(const struct rocker *rocker) return -EIO; } - rnd = prandom_u32(); + rnd = get_random_u32(); rnd <<= 31; - rnd |= prandom_u32(); + rnd |= get_random_u32(); rocker_write64(rocker, TEST_REG64, rnd); test_reg = rocker_read64(rocker, TEST_REG64); if (test_reg != rnd * 2) { diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index 535995e8279f..bcd564dc3554 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -239,7 +239,7 @@ mwifiex_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, tx_info->pkt_len = pkt_len; mwifiex_form_mgmt_frame(skb, buf, len); - *cookie = prandom_u32() | 1; + *cookie = get_random_u32() | 1; if (ieee80211_is_action(mgmt->frame_control)) skb = mwifiex_clone_skb_for_tx_status(priv, @@ -303,7 +303,7 @@ mwifiex_cfg80211_remain_on_channel(struct wiphy *wiphy, duration); if (!ret) { - *cookie = prandom_u32() | 1; + *cookie = get_random_u32() | 1; priv->roc_cfg.cookie = *cookie; priv->roc_cfg.chan = *chan; diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index b89047965e78..9bbfff803357 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -1161,7 +1161,7 @@ static int mgmt_tx(struct wiphy *wiphy, const u8 *vendor_ie; int ret = 0; - *cookie = prandom_u32(); + *cookie = get_random_u32(); priv->tx_cookie = *cookie; mgmt = (const struct ieee80211_mgmt *)buf; diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c index bfdf03bfa6c5..73e6f9408b51 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c @@ -449,7 +449,7 @@ qtnf_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, { struct qtnf_vif *vif = qtnf_netdev_get_priv(wdev->netdev); const struct ieee80211_mgmt *mgmt_frame = (void *)params->buf; - u32 short_cookie = prandom_u32(); + u32 short_cookie = get_random_u32(); u16 flags = 0; u16 freq; diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 3e3922d4c788..28c0f06e311f 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -6100,7 +6100,7 @@ static int wl1271_register_hw(struct wl1271 *wl) wl1271_warning("Fuse mac address is zero. using random mac"); /* Use TI oui and a random nic */ oui_addr = WLCORE_TI_OUI_ADDRESS; - nic_addr = get_random_int(); + nic_addr = get_random_u32(); } else { oui_addr = wl->fuse_oui_addr; /* fuse has the BD_ADDR, the WLAN addresses are the next two */ diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c index 04bd28f17dcc..d90e4f0c08b7 100644 --- a/drivers/nvme/common/auth.c +++ b/drivers/nvme/common/auth.c @@ -23,7 +23,7 @@ u32 nvme_auth_get_seqnum(void) mutex_lock(&nvme_dhchap_mutex); if (!nvme_dhchap_seqnum) - nvme_dhchap_seqnum = prandom_u32(); + nvme_dhchap_seqnum = get_random_u32(); else { nvme_dhchap_seqnum++; if (!nvme_dhchap_seqnum) diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c index 53d91bf9c12a..c07d2e3b4bcf 100644 --- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c +++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c @@ -254,7 +254,7 @@ static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb, } else if (is_t5(lldi->adapter_type)) { struct cpl_t5_act_open_req *req = (struct cpl_t5_act_open_req *)skb->head; - u32 isn = (prandom_u32() & ~7UL) - 1; + u32 isn = (get_random_u32() & ~7UL) - 1; INIT_TP_WR(req, 0); OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, @@ -282,7 +282,7 @@ static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb, } else { struct cpl_t6_act_open_req *req = (struct cpl_t6_act_open_req *)skb->head; - u32 isn = (prandom_u32() & ~7UL) - 1; + u32 isn = (get_random_u32() & ~7UL) - 1; INIT_TP_WR(req, 0); OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c index 3336d2b78bf7..d9204c590d9a 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c @@ -1202,7 +1202,7 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req) opt2 |= CONG_CNTRL_V(CONG_ALG_NEWRENO); opt2 |= T5_ISS_F; - rpl5->iss = cpu_to_be32((prandom_u32() & ~7UL) - 1); + rpl5->iss = cpu_to_be32((get_random_u32() & ~7UL) - 1); opt2 |= T5_OPT_2_VALID_F; diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index bbb248a2686f..f00b2f62d8e3 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -2437,7 +2437,7 @@ int tb_xdomain_init(void) tb_property_add_immediate(xdomain_property_dir, "deviceid", 0x1); tb_property_add_immediate(xdomain_property_dir, "devicerv", 0x80000100); - xdomain_property_block_gen = prandom_u32(); + xdomain_property_block_gen = get_random_u32(); return 0; } diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index fd5d701106e1..00d789b6c0fa 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -167,7 +167,7 @@ static int uvesafb_exec(struct uvesafb_ktask *task) memcpy(&m->id, &uvesafb_cn_id, sizeof(m->id)); m->seq = seq; m->len = len; - m->ack = prandom_u32(); + m->ack = get_random_u32(); /* uvesafb_task structure */ memcpy(m + 1, &task->t, sizeof(task->t)); diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index a795437b86d0..5590a1e83126 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -552,7 +552,7 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); - inode->i_generation = prandom_u32(); + inode->i_generation = get_random_u32(); if (info->attr & ATTR_SUBDIR) { /* directory */ inode->i_generation &= ~1; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 7575aa359675..e9bc46684106 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1279,7 +1279,7 @@ got: EXT4_GROUP_INFO_IBITMAP_CORRUPT); goto out; } - inode->i_generation = prandom_u32(); + inode->i_generation = get_random_u32(); /* Precompute checksum seed for inode metadata */ if (ext4_has_metadata_csum(sb)) { diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 4d49c5cfb690..ded535535b27 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -454,8 +454,8 @@ static long swap_inode_boot_loader(struct super_block *sb, inode->i_ctime = inode_bl->i_ctime = current_time(inode); inode_inc_iversion(inode); - inode->i_generation = prandom_u32(); - inode_bl->i_generation = prandom_u32(); + inode->i_generation = get_random_u32(); + inode_bl->i_generation = get_random_u32(); ext4_reset_inode_seed(inode); ext4_reset_inode_seed(inode_bl); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 9af68a7ecdcf..588cb09c5291 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -265,7 +265,7 @@ static unsigned int mmp_new_seq(void) u32 new_seq; do { - new_seq = prandom_u32(); + new_seq = get_random_u32(); } while (new_seq > EXT4_MMP_SEQ_MAX); return new_seq; diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index d5065a5af1f8..a389772fd212 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -50,7 +50,7 @@ static struct inode *f2fs_new_inode(struct user_namespace *mnt_userns, inode->i_blocks = 0; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); F2FS_I(inode)->i_crtime = inode->i_mtime; - inode->i_generation = prandom_u32(); + inode->i_generation = get_random_u32(); if (S_ISDIR(inode->i_mode)) F2FS_I(inode)->i_current_depth = 1; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index a38238d75c08..1cbcc4608dc7 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -523,7 +523,7 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); - inode->i_generation = prandom_u32(); + inode->i_generation = get_random_u32(); if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) { inode->i_generation &= ~1; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 198d7abf34e4..4e718500a00c 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4375,8 +4375,8 @@ nfsd4_init_leases_net(struct nfsd_net *nn) nn->nfsd4_grace = 90; nn->somebody_reclaimed = false; nn->track_reclaim_completes = false; - nn->clverifier_counter = prandom_u32(); - nn->clientid_base = prandom_u32(); + nn->clverifier_counter = get_random_u32(); + nn->clientid_base = get_random_u32(); nn->clientid_counter = nn->clientid_base + 1; nn->s2s_cp_cl_id = nn->clientid_counter++; diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index e7c494005122..0d611a6c5511 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -3819,7 +3819,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) } log_init_pg_hdr(log, page_size, page_size, 1, 1); - log_create(log, l_size, 0, get_random_int(), false, false); + log_create(log, l_size, 0, get_random_u32(), false, false); log->ra = ra; @@ -3893,7 +3893,7 @@ check_restart_area: /* Do some checks based on whether we have a valid log page. */ if (!rst_info.valid_page) { - open_log_count = get_random_int(); + open_log_count = get_random_u32(); goto init_log_instance; } open_log_count = le32_to_cpu(ra2->open_log_count); @@ -4044,7 +4044,7 @@ find_oldest: memcpy(ra->clients, Add2Ptr(ra2, t16), le16_to_cpu(ra2->ra_len) - t16); - log->current_openlog_count = get_random_int(); + log->current_openlog_count = get_random_u32(); ra->open_log_count = cpu_to_le32(log->current_openlog_count); log->ra_size = offsetof(struct RESTART_AREA, clients) + sizeof(struct CLIENT_REC); diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 75dab0ae3939..4619652046cf 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -503,7 +503,7 @@ static void mark_inode_clean(struct ubifs_info *c, struct ubifs_inode *ui) static void set_dent_cookie(struct ubifs_info *c, struct ubifs_dent_node *dent) { if (c->double_hash) - dent->cookie = (__force __le32) prandom_u32(); + dent->cookie = (__force __le32) get_random_u32(); else dent->cookie = 0; } diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 7838b31126e2..94db50eb706a 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -805,7 +805,7 @@ sparse_alloc: * number from being easily guessable. */ error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag->pag_agno, - args.agbno, args.len, prandom_u32()); + args.agbno, args.len, get_random_u32()); if (error) return error; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 2bbe7916a998..eae7427062cf 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -596,7 +596,7 @@ xfs_iget_cache_miss( */ if (xfs_has_v3inodes(mp) && (flags & XFS_IGET_CREATE) && !xfs_has_ikeep(mp)) { - VFS_I(ip)->i_generation = prandom_u32(); + VFS_I(ip)->i_generation = get_random_u32(); } else { struct xfs_buf *bp; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index f6e7e4fd72ae..f02a0dd522b3 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -3544,7 +3544,7 @@ xlog_ticket_alloc( tic->t_curr_res = unit_res; tic->t_cnt = cnt; tic->t_ocnt = cnt; - tic->t_tid = prandom_u32(); + tic->t_tid = get_random_u32(); if (permanent) tic->t_flags |= XLOG_TIC_PERM_RESERV; diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 980daa6e1e3a..c81021ab07aa 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -43,7 +43,7 @@ void nf_queue_entry_free(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) { while (*jhash_initval == 0) - *jhash_initval = prandom_u32(); + *jhash_initval = get_random_u32(); } static inline u32 hash_v4(const struct iphdr *iph, u32 initval) diff --git a/include/net/red.h b/include/net/red.h index 454ac2b65d8c..425364de0df7 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -363,7 +363,7 @@ static inline unsigned long red_calc_qavg(const struct red_parms *p, static inline u32 red_random(const struct red_parms *p) { - return reciprocal_divide(prandom_u32(), p->max_P_reciprocal); + return reciprocal_divide(get_random_u32(), p->max_P_reciprocal); } static inline int red_mark_probability(const struct red_parms *p, diff --git a/include/net/sock.h b/include/net/sock.h index 08038a385ef2..9e464f6409a7 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2109,7 +2109,7 @@ static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) static inline u32 net_tx_rndhash(void) { - u32 v = prandom_u32(); + u32 v = get_random_u32(); return v ?: 1; } diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index b9ea539a5561..48ee750849f2 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -158,7 +158,7 @@ static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) attr->value_size / sizeof(u32); if (!(attr->map_flags & BPF_F_ZERO_SEED)) - bloom->hash_seed = get_random_int(); + bloom->hash_seed = get_random_u32(); return &bloom->map; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 53c6c98bda7b..25a54e04560e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1216,7 +1216,7 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, bool emit_zext) { struct bpf_insn *to = to_buff; - u32 imm_rnd = get_random_int(); + u32 imm_rnd = get_random_u32(); s16 off; BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index ed3f8a53603b..f39ee3e05589 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -527,7 +527,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (htab->map.map_flags & BPF_F_ZERO_SEED) htab->hashrnd = 0; else - htab->hashrnd = get_random_int(); + htab->hashrnd = get_random_u32(); htab_init_buckets(htab); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6f6d2d511c06..014ee0953dbd 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13350,7 +13350,7 @@ static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env, aux[adj_idx].ptr_type == PTR_TO_CTX) continue; - imm_rnd = get_random_int(); + imm_rnd = get_random_u32(); rnd_hi32_patch[0] = insn; rnd_hi32_patch[1].imm = imm_rnd; rnd_hi32_patch[3].dst_reg = load_reg; diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c index 75712959c84e..58b94deae5c0 100644 --- a/kernel/kcsan/selftest.c +++ b/kernel/kcsan/selftest.c @@ -26,7 +26,7 @@ static bool __init test_requires(void) { /* random should be initialized for the below tests */ - return prandom_u32() + prandom_u32() != 0; + return get_random_u32() + get_random_u32() != 0; } /* diff --git a/lib/random32.c b/lib/random32.c index d5d9029362cb..d4f19e1a69d4 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -47,7 +47,7 @@ * @state: pointer to state structure holding seeded state. * * This is used for pseudo-randomness with no outside seeding. - * For more random results, use prandom_u32(). + * For more random results, use get_random_u32(). */ u32 prandom_u32_state(struct rnd_state *state) { diff --git a/lib/reed_solomon/test_rslib.c b/lib/reed_solomon/test_rslib.c index 4d241bdc88aa..848e7eb5da92 100644 --- a/lib/reed_solomon/test_rslib.c +++ b/lib/reed_solomon/test_rslib.c @@ -164,7 +164,7 @@ static int get_rcw_we(struct rs_control *rs, struct wspace *ws, /* Load c with random data and encode */ for (i = 0; i < dlen; i++) - c[i] = prandom_u32() & nn; + c[i] = get_random_u32() & nn; memset(c + dlen, 0, nroots * sizeof(*c)); encode_rs16(rs, c, dlen, c + dlen, 0); @@ -178,7 +178,7 @@ static int get_rcw_we(struct rs_control *rs, struct wspace *ws, for (i = 0; i < errs; i++) { do { /* Error value must be nonzero */ - errval = prandom_u32() & nn; + errval = get_random_u32() & nn; } while (errval == 0); do { @@ -206,7 +206,7 @@ static int get_rcw_we(struct rs_control *rs, struct wspace *ws, /* Erasure with corrupted symbol */ do { /* Error value must be nonzero */ - errval = prandom_u32() & nn; + errval = get_random_u32() & nn; } while (errval == 0); errlocs[errloc] = 1; diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index ed70637a2ffa..e0381b3ec410 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -145,7 +145,7 @@ static unsigned long get_ftrace_location(void *func) static int fprobe_test_init(struct kunit *test) { do { - rand1 = prandom_u32(); + rand1 = get_random_u32(); } while (rand1 <= div_factor); target = fprobe_selftest_target; diff --git a/lib/test_kprobes.c b/lib/test_kprobes.c index a5edc2ebc947..eeb1d728d974 100644 --- a/lib/test_kprobes.c +++ b/lib/test_kprobes.c @@ -341,7 +341,7 @@ static int kprobes_test_init(struct kunit *test) stacktrace_driver = kprobe_stacktrace_driver; do { - rand1 = prandom_u32(); + rand1 = get_random_u32(); } while (rand1 <= div_factor); return 0; } diff --git a/lib/test_min_heap.c b/lib/test_min_heap.c index d19c8080fd4d..7b01b4387cfb 100644 --- a/lib/test_min_heap.c +++ b/lib/test_min_heap.c @@ -83,7 +83,7 @@ static __init int test_heapify_all(bool min_heap) /* Test with randomly generated values. */ heap.nr = ARRAY_SIZE(values); for (i = 0; i < heap.nr; i++) - values[i] = get_random_int(); + values[i] = get_random_u32(); min_heapify_all(&heap, &funcs); err += pop_verify_heap(min_heap, &heap, &funcs); @@ -116,7 +116,7 @@ static __init int test_heap_push(bool min_heap) /* Test with randomly generated values. */ while (heap.nr < heap.size) { - temp = get_random_int(); + temp = get_random_u32(); min_heap_push(&heap, &temp, &funcs); } err += pop_verify_heap(min_heap, &heap, &funcs); @@ -158,7 +158,7 @@ static __init int test_heap_pop_push(bool min_heap) /* Test with randomly generated values. */ for (i = 0; i < ARRAY_SIZE(data); i++) { - temp = get_random_int(); + temp = get_random_u32(); min_heap_pop_push(&heap, &temp, &funcs); } err += pop_verify_heap(min_heap, &heap, &funcs); diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 5a1dd4736b56..b358a74ed7ed 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -291,7 +291,7 @@ static int __init test_rhltable(unsigned int entries) if (WARN_ON(err)) goto out_free; - k = prandom_u32(); + k = get_random_u32(); ret = 0; for (i = 0; i < entries; i++) { rhl_test_objects[i].value.id = k; @@ -369,12 +369,12 @@ static int __init test_rhltable(unsigned int entries) pr_info("test %d random rhlist add/delete operations\n", entries); for (j = 0; j < entries; j++) { u32 i = prandom_u32_max(entries); - u32 prand = prandom_u32(); + u32 prand = get_random_u32(); cond_resched(); if (prand == 0) - prand = prandom_u32(); + prand = get_random_u32(); if (prand & 1) { prand >>= 1; diff --git a/mm/shmem.c b/mm/shmem.c index 86214d48dd09..8280a5cb48df 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2332,7 +2332,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, struct inode *dir, inode_init_owner(&init_user_ns, inode, dir, mode); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); - inode->i_generation = prandom_u32(); + inode->i_generation = get_random_u32(); info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); diff --git a/mm/slab.c b/mm/slab.c index a5486ff8362a..60cd19b9ee04 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2380,7 +2380,7 @@ static bool freelist_state_initialize(union freelist_init_state *state, unsigned int rand; /* Use best entropy available to define a random shift */ - rand = get_random_int(); + rand = get_random_u32(); /* Use a random state if the pre-computed list is not available */ if (!cachep->random_seq) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 5ca4f953034c..c3763056c554 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2464,7 +2464,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) for (i = 0; i < pkt_dev->nr_labels; i++) if (pkt_dev->labels[i] & MPLS_STACK_BOTTOM) pkt_dev->labels[i] = MPLS_STACK_BOTTOM | - ((__force __be32)prandom_u32() & + ((__force __be32)get_random_u32() & htonl(0x000fffff)); } @@ -2568,7 +2568,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) for (i = 0; i < 4; i++) { pkt_dev->cur_in6_daddr.s6_addr32[i] = - (((__force __be32)prandom_u32() | + (((__force __be32)get_random_u32() | pkt_dev->min_in6_daddr.s6_addr32[i]) & pkt_dev->max_in6_daddr.s6_addr32[i]); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 795cbe1de912..1a37a07c7163 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3664,7 +3664,7 @@ static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); - atomic_set(&net->ipv4.dev_addr_genid, get_random_int()); + atomic_set(&net->ipv4.dev_addr_genid, get_random_u32()); return 0; } diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index ddc7ba0554bd..efcd145f06db 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -243,7 +243,7 @@ static bool tcp_cdg_backoff(struct sock *sk, u32 grad) struct cdg *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - if (prandom_u32() <= nexp_u32(grad * backoff_factor)) + if (get_random_u32() <= nexp_u32(grad * backoff_factor)) return false; if (use_ineff) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d63118ce5900..9f2688246dee 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -246,7 +246,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - rand = prandom_u32(); + rand = get_random_u32(); first = reciprocal_scale(rand, remaining) + low; /* * force rand to be an odd multiple of UDP_HTABLE_SIZE diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index ceb85c67ce39..18481eb76a0a 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -220,7 +220,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net, spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { - fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK; + fl->label = htonl(get_random_u32())&IPV6_FLOWLABEL_MASK; if (fl->label) { lfl = __fl_lookup(net, fl->label); if (!lfl) diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 2880dc7d9a49..2685c3f15e9d 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -18,7 +18,7 @@ static u32 __ipv6_select_ident(struct net *net, u32 id; do { - id = prandom_u32(); + id = get_random_u32(); } while (!id); return id; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index fb67f1ca2495..8c04bb57dd6f 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1308,7 +1308,7 @@ void ip_vs_random_dropentry(struct netns_ipvs *ipvs) * Randomly scan 1/32 of the whole table every second */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { - unsigned int hash = prandom_u32() & ip_vs_conn_tab_mask; + unsigned int hash = get_random_u32() & ip_vs_conn_tab_mask; hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->ipvs != ipvs) diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c index 203e24ae472c..b26c1dcfc27b 100644 --- a/net/netfilter/xt_statistic.c +++ b/net/netfilter/xt_statistic.c @@ -34,7 +34,7 @@ statistic_mt(const struct sk_buff *skb, struct xt_action_param *par) switch (info->mode) { case XT_STATISTIC_MODE_RANDOM: - if ((prandom_u32() & 0x7FFFFFFF) < info->u.random.probability) + if ((get_random_u32() & 0x7FFFFFFF) < info->u.random.probability) ret = !ret; break; case XT_STATISTIC_MODE_NTH: diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 868db4669a29..ca3ebfdb3023 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1033,7 +1033,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, actions = nla_next(sample_arg, &rem); if ((arg->probability != U32_MAX) && - (!arg->probability || prandom_u32() > arg->probability)) { + (!arg->probability || get_random_u32() > arg->probability)) { if (last) consume_skb(skb); return 0; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 7193d25932ce..817cd0695b35 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -573,7 +573,7 @@ static bool cobalt_should_drop(struct cobalt_vars *vars, /* Simple BLUE implementation. Lack of ECN is deliberate. */ if (vars->p_drop) - drop |= (prandom_u32() < vars->p_drop); + drop |= (get_random_u32() < vars->p_drop); /* Overload the drop_next field as an activity timeout */ if (!vars->count) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index bab45b3b1fdb..fb00ac40ecb7 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -171,7 +171,7 @@ static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) static void init_crandom(struct crndstate *state, unsigned long rho) { state->rho = rho; - state->last = prandom_u32(); + state->last = get_random_u32(); } /* get_crandom - correlated random number generator @@ -184,9 +184,9 @@ static u32 get_crandom(struct crndstate *state) unsigned long answer; if (!state || state->rho == 0) /* no correlation */ - return prandom_u32(); + return get_random_u32(); - value = prandom_u32(); + value = get_random_u32(); rho = (u64)state->rho + 1; answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32; state->last = answer; @@ -200,7 +200,7 @@ static u32 get_crandom(struct crndstate *state) static bool loss_4state(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; - u32 rnd = prandom_u32(); + u32 rnd = get_random_u32(); /* * Makes a comparison between rnd and the transition @@ -268,15 +268,15 @@ static bool loss_gilb_ell(struct netem_sched_data *q) switch (clg->state) { case GOOD_STATE: - if (prandom_u32() < clg->a1) + if (get_random_u32() < clg->a1) clg->state = BAD_STATE; - if (prandom_u32() < clg->a4) + if (get_random_u32() < clg->a4) return true; break; case BAD_STATE: - if (prandom_u32() < clg->a2) + if (get_random_u32() < clg->a2) clg->state = GOOD_STATE; - if (prandom_u32() > clg->a3) + if (get_random_u32() > clg->a3) return true; } @@ -632,7 +632,7 @@ static void get_slot_next(struct netem_sched_data *q, u64 now) if (!q->slot_dist) next_delay = q->slot_config.min_delay + - (prandom_u32() * + (get_random_u32() * (q->slot_config.max_delay - q->slot_config.min_delay) >> 32); else diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 5f96e75f9eec..48337687848c 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -130,8 +130,8 @@ gss_krb5_make_confounder(char *p, u32 conflen) /* initialize to random value */ if (i == 0) { - i = prandom_u32(); - i = (i << 32) | prandom_u32(); + i = get_random_u32(); + i = (i << 32) | get_random_u32(); } switch (conflen) { diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index f8fae7815649..9407007f47ae 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1868,7 +1868,7 @@ xprt_alloc_xid(struct rpc_xprt *xprt) static void xprt_init_xid(struct rpc_xprt *xprt) { - xprt->xid = prandom_u32(); + xprt->xid = get_random_u32(); } static void diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 15dbb392c875..b3545fc68097 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1147,7 +1147,7 @@ static int unix_autobind(struct sock *sk) addr->name->sun_family = AF_UNIX; refcount_set(&addr->refcnt, 1); - ordernum = prandom_u32(); + ordernum = get_random_u32(); lastnum = ordernum & 0xFFFFF; retry: ordernum = (ordernum + 1) & 0xFFFFF; -- cgit From 197173db990cad244221ba73c43b1df6170ae278 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 17:49:46 +0200 Subject: treewide: use get_random_bytes() when possible The prandom_bytes() function has been a deprecated inline wrapper around get_random_bytes() for several releases now, and compiles down to the exact same code. Replace the deprecated wrapper with a direct call to the real function. This was done as a basic find and replace. Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Reviewed-by: Christophe Leroy # powerpc Acked-by: Jakub Kicinski Signed-off-by: Jason A. Donenfeld --- arch/powerpc/crypto/crc-vpmsum_test.c | 2 +- block/blk-crypto-fallback.c | 2 +- crypto/async_tx/raid6test.c | 2 +- drivers/dma/dmatest.c | 2 +- drivers/mtd/nand/raw/nandsim.c | 2 +- drivers/mtd/tests/mtd_nandecctest.c | 2 +- drivers/mtd/tests/speedtest.c | 2 +- drivers/mtd/tests/stresstest.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/rocker/rocker_main.c | 2 +- drivers/net/wireguard/selftest/allowedips.c | 12 ++++++------ fs/ubifs/debug.c | 2 +- kernel/kcsan/selftest.c | 2 +- lib/random32.c | 2 +- lib/test_objagg.c | 2 +- lib/uuid.c | 2 +- net/ipv4/route.c | 2 +- net/mac80211/rc80211_minstrel_ht.c | 2 +- net/sched/sch_pie.c | 2 +- 19 files changed, 24 insertions(+), 24 deletions(-) diff --git a/arch/powerpc/crypto/crc-vpmsum_test.c b/arch/powerpc/crypto/crc-vpmsum_test.c index c1c1ef9457fb..273c527868db 100644 --- a/arch/powerpc/crypto/crc-vpmsum_test.c +++ b/arch/powerpc/crypto/crc-vpmsum_test.c @@ -82,7 +82,7 @@ static int __init crc_test_init(void) if (len <= offset) continue; - prandom_bytes(data, len); + get_random_bytes(data, len); len -= offset; crypto_shash_update(crct10dif_shash, data+offset, len); diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index 621abd1b0e4d..ad9844c5b40c 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -539,7 +539,7 @@ static int blk_crypto_fallback_init(void) if (blk_crypto_fallback_inited) return 0; - prandom_bytes(blank_key, BLK_CRYPTO_MAX_KEY_SIZE); + get_random_bytes(blank_key, BLK_CRYPTO_MAX_KEY_SIZE); err = bioset_init(&crypto_bio_split, 64, 0, 0); if (err) diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c index 9719c7520661..d3fbee1e03e5 100644 --- a/crypto/async_tx/raid6test.c +++ b/crypto/async_tx/raid6test.c @@ -37,7 +37,7 @@ static void makedata(int disks) int i; for (i = 0; i < disks; i++) { - prandom_bytes(page_address(data[i]), PAGE_SIZE); + get_random_bytes(page_address(data[i]), PAGE_SIZE); dataptrs[i] = data[i]; dataoffs[i] = 0; } diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 9fe2ae794316..ffe621695e47 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -312,7 +312,7 @@ static unsigned long dmatest_random(void) { unsigned long buf; - prandom_bytes(&buf, sizeof(buf)); + get_random_bytes(&buf, sizeof(buf)); return buf; } diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c index d211939c8bdd..672719023241 100644 --- a/drivers/mtd/nand/raw/nandsim.c +++ b/drivers/mtd/nand/raw/nandsim.c @@ -1393,7 +1393,7 @@ static int ns_do_read_error(struct nandsim *ns, int num) unsigned int page_no = ns->regs.row; if (ns_read_error(page_no)) { - prandom_bytes(ns->buf.byte, num); + get_random_bytes(ns->buf.byte, num); NS_WARN("simulating read error in page %u\n", page_no); return 1; } diff --git a/drivers/mtd/tests/mtd_nandecctest.c b/drivers/mtd/tests/mtd_nandecctest.c index 1c7201b0f372..440988562cfd 100644 --- a/drivers/mtd/tests/mtd_nandecctest.c +++ b/drivers/mtd/tests/mtd_nandecctest.c @@ -266,7 +266,7 @@ static int nand_ecc_test_run(const size_t size) goto error; } - prandom_bytes(correct_data, size); + get_random_bytes(correct_data, size); ecc_sw_hamming_calculate(correct_data, size, correct_ecc, sm_order); for (i = 0; i < ARRAY_SIZE(nand_ecc_test); i++) { nand_ecc_test[i].prepare(error_data, error_ecc, diff --git a/drivers/mtd/tests/speedtest.c b/drivers/mtd/tests/speedtest.c index c9ec7086bfa1..075bce32caa5 100644 --- a/drivers/mtd/tests/speedtest.c +++ b/drivers/mtd/tests/speedtest.c @@ -223,7 +223,7 @@ static int __init mtd_speedtest_init(void) if (!iobuf) goto out; - prandom_bytes(iobuf, mtd->erasesize); + get_random_bytes(iobuf, mtd->erasesize); bbt = kzalloc(ebcnt, GFP_KERNEL); if (!bbt) diff --git a/drivers/mtd/tests/stresstest.c b/drivers/mtd/tests/stresstest.c index d2faaca7f19d..75b6ddc5dc4d 100644 --- a/drivers/mtd/tests/stresstest.c +++ b/drivers/mtd/tests/stresstest.c @@ -183,7 +183,7 @@ static int __init mtd_stresstest_init(void) goto out; for (i = 0; i < ebcnt; i++) offsets[i] = mtd->erasesize; - prandom_bytes(writebuf, bufsize); + get_random_bytes(writebuf, bufsize); bbt = kzalloc(ebcnt, GFP_KERNEL); if (!bbt) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index eed98c10ca9d..04cf7684f1b0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3874,7 +3874,7 @@ static void bnxt_init_vnics(struct bnxt *bp) if (bp->vnic_info[i].rss_hash_key) { if (i == 0) - prandom_bytes(vnic->rss_hash_key, + get_random_bytes(vnic->rss_hash_key, HW_HASH_KEY_SIZE); else memcpy(vnic->rss_hash_key, diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 5672d952452f..9e59669a93dd 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -224,7 +224,7 @@ static int rocker_dma_test_offset(const struct rocker *rocker, if (err) goto unmap; - prandom_bytes(buf, ROCKER_TEST_DMA_BUF_SIZE); + get_random_bytes(buf, ROCKER_TEST_DMA_BUF_SIZE); for (i = 0; i < ROCKER_TEST_DMA_BUF_SIZE; i++) expect[i] = ~buf[i]; err = rocker_dma_test_one(rocker, wait, ROCKER_TEST_DMA_CTRL_INVERT, diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index dd897c0740a2..19eac00b2381 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -284,7 +284,7 @@ static __init bool randomized_test(void) mutex_lock(&mutex); for (i = 0; i < NUM_RAND_ROUTES; ++i) { - prandom_bytes(ip, 4); + get_random_bytes(ip, 4); cidr = prandom_u32_max(32) + 1; peer = peers[prandom_u32_max(NUM_PEERS)]; if (wg_allowedips_insert_v4(&t, (struct in_addr *)ip, cidr, @@ -299,7 +299,7 @@ static __init bool randomized_test(void) } for (j = 0; j < NUM_MUTATED_ROUTES; ++j) { memcpy(mutated, ip, 4); - prandom_bytes(mutate_mask, 4); + get_random_bytes(mutate_mask, 4); mutate_amount = prandom_u32_max(32); for (k = 0; k < mutate_amount / 8; ++k) mutate_mask[k] = 0xff; @@ -328,7 +328,7 @@ static __init bool randomized_test(void) } for (i = 0; i < NUM_RAND_ROUTES; ++i) { - prandom_bytes(ip, 16); + get_random_bytes(ip, 16); cidr = prandom_u32_max(128) + 1; peer = peers[prandom_u32_max(NUM_PEERS)]; if (wg_allowedips_insert_v6(&t, (struct in6_addr *)ip, cidr, @@ -343,7 +343,7 @@ static __init bool randomized_test(void) } for (j = 0; j < NUM_MUTATED_ROUTES; ++j) { memcpy(mutated, ip, 16); - prandom_bytes(mutate_mask, 16); + get_random_bytes(mutate_mask, 16); mutate_amount = prandom_u32_max(128); for (k = 0; k < mutate_amount / 8; ++k) mutate_mask[k] = 0xff; @@ -381,13 +381,13 @@ static __init bool randomized_test(void) for (j = 0;; ++j) { for (i = 0; i < NUM_QUERIES; ++i) { - prandom_bytes(ip, 4); + get_random_bytes(ip, 4); if (lookup(t.root4, 32, ip) != horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) { horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip); pr_err("allowedips random v4 self-test: FAIL\n"); goto free; } - prandom_bytes(ip, 16); + get_random_bytes(ip, 16); if (lookup(t.root6, 128, ip) != horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) { pr_err("allowedips random v6 self-test: FAIL\n"); goto free; diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index f4d3b568aa64..3f128b9fdfbb 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -2581,7 +2581,7 @@ static int corrupt_data(const struct ubifs_info *c, const void *buf, if (ffs) memset(p + from, 0xFF, to - from); else - prandom_bytes(p + from, to - from); + get_random_bytes(p + from, to - from); return to; } diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c index 58b94deae5c0..00cdf8fa5693 100644 --- a/kernel/kcsan/selftest.c +++ b/kernel/kcsan/selftest.c @@ -46,7 +46,7 @@ static bool __init test_encode_decode(void) unsigned long addr; size_t verif_size; - prandom_bytes(&addr, sizeof(addr)); + get_random_bytes(&addr, sizeof(addr)); if (addr < PAGE_SIZE) addr = PAGE_SIZE; diff --git a/lib/random32.c b/lib/random32.c index d4f19e1a69d4..32060b852668 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -69,7 +69,7 @@ EXPORT_SYMBOL(prandom_u32_state); * @bytes: the requested number of bytes * * This is used for pseudo-randomness with no outside seeding. - * For more random results, use prandom_bytes(). + * For more random results, use get_random_bytes(). */ void prandom_bytes_state(struct rnd_state *state, void *buf, size_t bytes) { diff --git a/lib/test_objagg.c b/lib/test_objagg.c index da137939a410..c0c957c50635 100644 --- a/lib/test_objagg.c +++ b/lib/test_objagg.c @@ -157,7 +157,7 @@ static int test_nodelta_obj_get(struct world *world, struct objagg *objagg, int err; if (should_create_root) - prandom_bytes(world->next_root_buf, + get_random_bytes(world->next_root_buf, sizeof(world->next_root_buf)); objagg_obj = world_obj_get(world, objagg, key_id); diff --git a/lib/uuid.c b/lib/uuid.c index 562d53977cab..e309b4c5be3d 100644 --- a/lib/uuid.c +++ b/lib/uuid.c @@ -52,7 +52,7 @@ EXPORT_SYMBOL(generate_random_guid); static void __uuid_gen_common(__u8 b[16]) { - prandom_bytes(b, 16); + get_random_bytes(b, 16); /* reversion 0b10 */ b[8] = (b[8] & 0x3F) | 0x80; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1a37a07c7163..cd1fa9f70f1a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3719,7 +3719,7 @@ int __init ip_rt_init(void) ip_idents = idents_hash; - prandom_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); + get_random_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents); diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 7f3f5f51081d..3d91b98db099 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -2036,7 +2036,7 @@ static void __init init_sample_table(void) memset(sample_table, 0xff, sizeof(sample_table)); for (col = 0; col < SAMPLE_COLUMNS; col++) { - prandom_bytes(rnd, sizeof(rnd)); + get_random_bytes(rnd, sizeof(rnd)); for (i = 0; i < MCS_GROUP_RATES; i++) { new_idx = (i + rnd[i]) % MCS_GROUP_RATES; while (sample_table[col][new_idx] != 0xff) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 974038ba6c7b..265c238047a4 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -72,7 +72,7 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, if (vars->accu_prob >= (MAX_PROB / 2) * 17) return true; - prandom_bytes(&rnd, 8); + get_random_bytes(&rnd, 8); if ((rnd >> BITS_PER_BYTE) < local_prob) { vars->accu_prob = 0; return true; -- cgit From de492c83cae0af72de370b9404aacda93dafcad5 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Wed, 5 Oct 2022 17:50:20 +0200 Subject: prandom: remove unused functions With no callers left of prandom_u32() and prandom_bytes(), as well as get_random_int(), remove these deprecated wrappers, in favor of get_random_u32() and get_random_bytes(). Reviewed-by: Greg Kroah-Hartman Reviewed-by: Kees Cook Reviewed-by: Yury Norov Acked-by: Jakub Kicinski Signed-off-by: Jason A. Donenfeld --- drivers/char/random.c | 11 +++++------ include/linux/prandom.h | 12 ------------ include/linux/random.h | 5 ----- 3 files changed, 5 insertions(+), 23 deletions(-) diff --git a/drivers/char/random.c b/drivers/char/random.c index 01acf235f263..2fe28eeb2f38 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -97,7 +97,7 @@ MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression"); * Returns whether or not the input pool has been seeded and thus guaranteed * to supply cryptographically secure random numbers. This applies to: the * /dev/urandom device, the get_random_bytes function, and the get_random_{u8, - * u16,u32,u64,int,long} family of functions. + * u16,u32,u64,long} family of functions. * * Returns: true if the input pool has been seeded. * false if the input pool has not been seeded. @@ -161,15 +161,14 @@ EXPORT_SYMBOL(wait_for_random_bytes); * u16 get_random_u16() * u32 get_random_u32() * u64 get_random_u64() - * unsigned int get_random_int() * unsigned long get_random_long() * * These interfaces will return the requested number of random bytes * into the given buffer or as a return value. This is equivalent to - * a read from /dev/urandom. The u8, u16, u32, u64, int, and long - * family of functions may be higher performance for one-off random - * integers, because they do a bit of buffering and do not invoke - * reseeding until the buffer is emptied. + * a read from /dev/urandom. The u8, u16, u32, u64, long family of + * functions may be higher performance for one-off random integers, + * because they do a bit of buffering and do not invoke reseeding + * until the buffer is emptied. * *********************************************************************/ diff --git a/include/linux/prandom.h b/include/linux/prandom.h index 78db003bc290..e0a0759dd09c 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -12,18 +12,6 @@ #include #include -/* Deprecated: use get_random_u32 instead. */ -static inline u32 prandom_u32(void) -{ - return get_random_u32(); -} - -/* Deprecated: use get_random_bytes instead. */ -static inline void prandom_bytes(void *buf, size_t nbytes) -{ - return get_random_bytes(buf, nbytes); -} - struct rnd_state { __u32 s1, s2, s3, s4; }; diff --git a/include/linux/random.h b/include/linux/random.h index 08322f700cdc..147a5e0d0b8e 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -42,10 +42,6 @@ u8 get_random_u8(void); u16 get_random_u16(void); u32 get_random_u32(void); u64 get_random_u64(void); -static inline unsigned int get_random_int(void) -{ - return get_random_u32(); -} static inline unsigned long get_random_long(void) { #if BITS_PER_LONG == 64 @@ -100,7 +96,6 @@ declare_get_random_var_wait(u8, u8) declare_get_random_var_wait(u16, u16) declare_get_random_var_wait(u32, u32) declare_get_random_var_wait(u64, u32) -declare_get_random_var_wait(int, unsigned int) declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var -- cgit From 10f6913c548b32ecb73801a16b120e761c6957ea Mon Sep 17 00:00:00 2001 From: Wenting Zhang Date: Fri, 8 Jul 2022 16:38:22 -0400 Subject: riscv: always honor the CONFIG_CMDLINE_FORCE when parsing dtb MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When CONFIG_CMDLINE_FORCE is enabled, cmdline provided by CONFIG_CMDLINE are always used. This allows CONFIG_CMDLINE to be used regardless of the result of device tree scanning. This especially fixes the case where a device tree without the chosen node is supplied to the kernel. In such cases, early_init_dt_scan would return true. But inside early_init_dt_scan_chosen, the cmdline won't be updated as there is no chosen node in the device tree. As a result, CONFIG_CMDLINE is not copied into boot_command_line even if CONFIG_CMDLINE_FORCE is enabled. This commit allows properly update boot_command_line in this situation. Fixes: 8fd6e05c7463 ("arch: riscv: support kernel command line forcing when no DTB passed") Signed-off-by: Wenting Zhang Reviewed-by: Björn Töpel Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/PSBPR04MB399135DFC54928AB958D0638B1829@PSBPR04MB3991.apcprd04.prod.outlook.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/setup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 2dfc463b86bb..ad76bb59b059 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -252,10 +252,10 @@ static void __init parse_dtb(void) pr_info("Machine model: %s\n", name); dump_stack_set_arch_desc("%s (DT)", name); } - return; + } else { + pr_err("No DTB passed to the kernel\n"); } - pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); pr_info("Forcing kernel command line to: %s\n", boot_command_line); -- cgit From 49b0dea1eb5e0fd5e498a2c2ce50d2e036494072 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Tue, 11 Oct 2022 15:35:48 +0100 Subject: ALSA: hda: hda_cs_dsp_ctl: Minor clean and redundant code removal The cs_dsp core will return an error if passed a NULL cs_dsp struct so there is no need for the hda_cs_dsp_write|read_ctl functions to manually check that. The cs_dsp core will also check the data is within bounds of the control so the additional bounds check is redundant too. Simplify things a bit by removing said code. Signed-off-by: Stefan Binding Link: https://lore.kernel.org/r/20221011143552.621792-2-sbinding@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_cs_dsp_ctl.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/sound/pci/hda/hda_cs_dsp_ctl.c b/sound/pci/hda/hda_cs_dsp_ctl.c index 89ee549cb7d5..41d3e8fd289d 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.c +++ b/sound/pci/hda/hda_cs_dsp_ctl.c @@ -199,16 +199,10 @@ EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_control_remove, SND_HDA_CS_DSP_CONTROLS); int hda_cs_dsp_write_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg, const void *buf, size_t len) { - struct cs_dsp_coeff_ctl *cs_ctl; + struct cs_dsp_coeff_ctl *cs_ctl = cs_dsp_get_ctl(dsp, name, type, alg); struct hda_cs_dsp_coeff_ctl *ctl; int ret; - cs_ctl = cs_dsp_get_ctl(dsp, name, type, alg); - if (!cs_ctl) - return -EINVAL; - - ctl = cs_ctl->priv; - ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, buf, len); if (ret) return ret; @@ -216,6 +210,8 @@ int hda_cs_dsp_write_ctl(struct cs_dsp *dsp, const char *name, int type, if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) return 0; + ctl = cs_ctl->priv; + snd_ctl_notify(ctl->card, SNDRV_CTL_EVENT_MASK_VALUE, &ctl->kctl->id); return 0; @@ -225,13 +221,8 @@ EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_write_ctl, SND_HDA_CS_DSP_CONTROLS); int hda_cs_dsp_read_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg, void *buf, size_t len) { - struct cs_dsp_coeff_ctl *cs_ctl; - - cs_ctl = cs_dsp_get_ctl(dsp, name, type, alg); - if (!cs_ctl) - return -EINVAL; + return cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(dsp, name, type, alg), 0, buf, len); - return cs_dsp_coeff_read_ctrl(cs_ctl, 0, buf, len); } EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_read_ctl, SND_HDA_CS_DSP_CONTROLS); -- cgit From 06f3a0a758c4246dc644e22fb33f85c6e5f92af6 Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Tue, 11 Oct 2022 15:35:49 +0100 Subject: ALSA: hda: hda_cs_dsp_ctl: Ensure pwr_lock is held before reading/writing controls These apis require the pwr_lock to be held. Signed-off-by: Stefan Binding Link: https://lore.kernel.org/r/20221011143552.621792-3-sbinding@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_cs_dsp_ctl.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/hda_cs_dsp_ctl.c b/sound/pci/hda/hda_cs_dsp_ctl.c index 41d3e8fd289d..75fb69185817 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.c +++ b/sound/pci/hda/hda_cs_dsp_ctl.c @@ -199,11 +199,14 @@ EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_control_remove, SND_HDA_CS_DSP_CONTROLS); int hda_cs_dsp_write_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg, const void *buf, size_t len) { - struct cs_dsp_coeff_ctl *cs_ctl = cs_dsp_get_ctl(dsp, name, type, alg); + struct cs_dsp_coeff_ctl *cs_ctl; struct hda_cs_dsp_coeff_ctl *ctl; int ret; + mutex_lock(&dsp->pwr_lock); + cs_ctl = cs_dsp_get_ctl(dsp, name, type, alg); ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, buf, len); + mutex_unlock(&dsp->pwr_lock); if (ret) return ret; @@ -221,7 +224,13 @@ EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_write_ctl, SND_HDA_CS_DSP_CONTROLS); int hda_cs_dsp_read_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg, void *buf, size_t len) { - return cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(dsp, name, type, alg), 0, buf, len); + int ret; + + mutex_lock(&dsp->pwr_lock); + ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(dsp, name, type, alg), 0, buf, len); + mutex_unlock(&dsp->pwr_lock); + + return ret; } EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_read_ctl, SND_HDA_CS_DSP_CONTROLS); -- cgit From 2176c6b599dba55a640cffec0182c0b6bab680d1 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 11 Oct 2022 15:35:50 +0100 Subject: ALSA: hda/cs_dsp_ctl: Fix mutex inversion when creating controls Redesign the creation of ALSA controls so that the cs_dsp pwr_lock is not held when calling snd_ctl_add(). Instead of creating the ALSA control from the cs_dsp control_add callback, do it after cs_dsp_power_up() has completed. The existing functions are changed to return void instead of passing errors back - this duplicates the original behaviour, as cs_dsp does not abort firmware load if creation of a control fails. It is safe to walk the control list without taking any mutex provided that the caller is not trying to load a new firmware or remove the driver in parallel. There is no other situation that the list can change. So the caller can trigger creation of ALSA controls after cs_dsp_power_up() has returned. A cs_dsp control will have a non-NULL priv pointer if we have created an ALSA control. With the previous code the ALSA controls were created from the cs_dsp control_add callback. But this is called with pwr_lock held (as it is part of the DSP power-up sequence). The kernel lock checking will show a mutex inversion between this and the control creation path: control_add pwr_lock held, takes controls_rwsem (in snd_ctl_add) get/put controls_rwsem held, takes pwr_lock to call cs_dsp. This is not completely theoretical. Although the time window is very small, it is possible for these to run in parallel and deadlock the old implementation. Signed-off-by: Richard Fitzgerald Signed-off-by: Stefan Binding Link: https://lore.kernel.org/r/20221011143552.621792-4-sbinding@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/cs35l41_hda.c | 8 +++--- sound/pci/hda/hda_cs_dsp_ctl.c | 59 +++++++++++++++++++++++++----------------- sound/pci/hda/hda_cs_dsp_ctl.h | 2 +- 3 files changed, 40 insertions(+), 29 deletions(-) diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index 3952f2853703..102ac4a94a9d 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -91,20 +91,18 @@ static const struct reg_sequence cs35l41_hda_mute[] = { { CS35L41_AMP_DIG_VOL_CTRL, 0x0000A678 }, // AMP_VOL_PCM Mute }; -static int cs35l41_control_add(struct cs_dsp_coeff_ctl *cs_ctl) +static void cs35l41_add_controls(struct cs35l41_hda *cs35l41) { - struct cs35l41_hda *cs35l41 = container_of(cs_ctl->dsp, struct cs35l41_hda, cs_dsp); struct hda_cs_dsp_ctl_info info; info.device_name = cs35l41->amp_name; info.fw_type = cs35l41->firmware_type; info.card = cs35l41->codec->card; - return hda_cs_dsp_control_add(cs_ctl, &info); + hda_cs_dsp_add_controls(&cs35l41->cs_dsp, &info); } static const struct cs_dsp_client_ops client_ops = { - .control_add = cs35l41_control_add, .control_remove = hda_cs_dsp_control_remove, }; @@ -435,6 +433,8 @@ static int cs35l41_init_dsp(struct cs35l41_hda *cs35l41) if (ret) goto err_release; + cs35l41_add_controls(cs35l41); + ret = cs35l41_save_calibration(cs35l41); err_release: diff --git a/sound/pci/hda/hda_cs_dsp_ctl.c b/sound/pci/hda/hda_cs_dsp_ctl.c index 75fb69185817..1622a22f96f6 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.c +++ b/sound/pci/hda/hda_cs_dsp_ctl.c @@ -97,7 +97,7 @@ static unsigned int wmfw_convert_flags(unsigned int in) return out; } -static int hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char *name) +static void hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char *name) { struct cs_dsp_coeff_ctl *cs_ctl = ctl->cs_ctl; struct snd_kcontrol_new kcontrol = {0}; @@ -107,7 +107,7 @@ static int hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char if (cs_ctl->len > ADSP_MAX_STD_CTRL_SIZE) { dev_err(cs_ctl->dsp->dev, "KControl %s: length %zu exceeds maximum %d\n", name, cs_ctl->len, ADSP_MAX_STD_CTRL_SIZE); - return -EINVAL; + return; } kcontrol.name = name; @@ -120,24 +120,21 @@ static int hda_cs_dsp_add_kcontrol(struct hda_cs_dsp_coeff_ctl *ctl, const char /* Save ctl inside private_data, ctl is owned by cs_dsp, * and will be freed when cs_dsp removes the control */ kctl = snd_ctl_new1(&kcontrol, (void *)ctl); - if (!kctl) { - ret = -ENOMEM; - return ret; - } + if (!kctl) + return; ret = snd_ctl_add(ctl->card, kctl); if (ret) { dev_err(cs_ctl->dsp->dev, "Failed to add KControl %s = %d\n", kcontrol.name, ret); - return ret; + return; } dev_dbg(cs_ctl->dsp->dev, "Added KControl: %s\n", kcontrol.name); ctl->kctl = kctl; - - return 0; } -int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ctl_info *info) +static void hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, + const struct hda_cs_dsp_ctl_info *info) { struct cs_dsp *cs_dsp = cs_ctl->dsp; char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; @@ -145,13 +142,10 @@ int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ct const char *region_name; int ret; - if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) - return 0; - region_name = cs_dsp_mem_region_name(cs_ctl->alg_region.type); if (!region_name) { - dev_err(cs_dsp->dev, "Unknown region type: %d\n", cs_ctl->alg_region.type); - return -EINVAL; + dev_warn(cs_dsp->dev, "Unknown region type: %d\n", cs_ctl->alg_region.type); + return; } ret = scnprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s %.12s %x", info->device_name, @@ -171,22 +165,39 @@ int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ct ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); if (!ctl) - return -ENOMEM; + return; ctl->cs_ctl = cs_ctl; ctl->card = info->card; cs_ctl->priv = ctl; - ret = hda_cs_dsp_add_kcontrol(ctl, name); - if (ret) { - dev_err(cs_dsp->dev, "Error (%d) adding control %s\n", ret, name); - kfree(ctl); - return ret; - } + hda_cs_dsp_add_kcontrol(ctl, name); +} - return 0; +void hda_cs_dsp_add_controls(struct cs_dsp *dsp, const struct hda_cs_dsp_ctl_info *info) +{ + struct cs_dsp_coeff_ctl *cs_ctl; + + /* + * pwr_lock would cause mutex inversion with ALSA control lock compared + * to the get/put functions. + * It is safe to walk the list without holding a mutex because entries + * are persistent and only cs_dsp_power_up() or cs_dsp_remove() can + * change the list. + */ + lockdep_assert_not_held(&dsp->pwr_lock); + + list_for_each_entry(cs_ctl, &dsp->ctl_list, list) { + if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) + continue; + + if (cs_ctl->priv) + continue; + + hda_cs_dsp_control_add(cs_ctl, info); + } } -EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_control_add, SND_HDA_CS_DSP_CONTROLS); +EXPORT_SYMBOL_NS_GPL(hda_cs_dsp_add_controls, SND_HDA_CS_DSP_CONTROLS); void hda_cs_dsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl) { diff --git a/sound/pci/hda/hda_cs_dsp_ctl.h b/sound/pci/hda/hda_cs_dsp_ctl.h index 4babc69cf2f0..2cf93359c4f2 100644 --- a/sound/pci/hda/hda_cs_dsp_ctl.h +++ b/sound/pci/hda/hda_cs_dsp_ctl.h @@ -29,7 +29,7 @@ struct hda_cs_dsp_ctl_info { extern const char * const hda_cs_dsp_fw_ids[HDA_CS_DSP_NUM_FW]; -int hda_cs_dsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl, struct hda_cs_dsp_ctl_info *info); +void hda_cs_dsp_add_controls(struct cs_dsp *dsp, const struct hda_cs_dsp_ctl_info *info); void hda_cs_dsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl); int hda_cs_dsp_write_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg, const void *buf, size_t len); -- cgit From 23904f7b2518e9b6bbfe2ac7bbe9e284bcdda18e Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Tue, 11 Oct 2022 15:35:51 +0100 Subject: ALSA: hda: cs35l41: Remove suspend/resume hda hooks The current code uses calls from the HDA Codec driver to determine when to suspend/resume by calling hooks via the hda_component binding. However, this means the cs35l41 driver relies on the HDA Codec driver to tell it when to suspend or resume, creating an additional external dependency, and potentially creating race conditions in the future. It is better for the cs35l41 hda driver to decide for itself when the part should be suspended or resumed. This makes supporting system suspend easier. Signed-off-by: Stefan Binding Link: https://lore.kernel.org/r/20221011143552.621792-5-sbinding@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/cs35l41_hda.c | 31 ++++++++++++------------------- sound/pci/hda/hda_component.h | 2 -- sound/pci/hda/patch_realtek.c | 19 +------------------ 3 files changed, 13 insertions(+), 39 deletions(-) diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index 102ac4a94a9d..89f6b4a28d3d 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -487,10 +487,10 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action) struct regmap *reg = cs35l41->regmap; int ret = 0; - mutex_lock(&cs35l41->fw_mutex); - switch (action) { case HDA_GEN_PCM_ACT_OPEN: + pm_runtime_get_sync(dev); + mutex_lock(&cs35l41->fw_mutex); cs35l41->playback_started = true; if (cs35l41->firmware_running) { regmap_multi_reg_write(reg, cs35l41_hda_config_dsp, @@ -508,15 +508,21 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action) CS35L41_AMP_EN_MASK, 1 << CS35L41_AMP_EN_SHIFT); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) regmap_write(reg, CS35L41_GPIO1_CTRL1, 0x00008001); + mutex_unlock(&cs35l41->fw_mutex); break; case HDA_GEN_PCM_ACT_PREPARE: + mutex_lock(&cs35l41->fw_mutex); ret = cs35l41_global_enable(reg, cs35l41->hw_cfg.bst_type, 1); + mutex_unlock(&cs35l41->fw_mutex); break; case HDA_GEN_PCM_ACT_CLEANUP: + mutex_lock(&cs35l41->fw_mutex); regmap_multi_reg_write(reg, cs35l41_hda_mute, ARRAY_SIZE(cs35l41_hda_mute)); ret = cs35l41_global_enable(reg, cs35l41->hw_cfg.bst_type, 0); + mutex_unlock(&cs35l41->fw_mutex); break; case HDA_GEN_PCM_ACT_CLOSE: + mutex_lock(&cs35l41->fw_mutex); ret = regmap_update_bits(reg, CS35L41_PWR_CTRL2, CS35L41_AMP_EN_MASK, 0 << CS35L41_AMP_EN_SHIFT); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) @@ -530,14 +536,16 @@ static void cs35l41_hda_playback_hook(struct device *dev, int action) } cs35l41_irq_release(cs35l41); cs35l41->playback_started = false; + mutex_unlock(&cs35l41->fw_mutex); + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); break; default: dev_warn(cs35l41->dev, "Playback action not supported: %d\n", action); break; } - mutex_unlock(&cs35l41->fw_mutex); - if (ret) dev_err(cs35l41->dev, "Regmap access fail: %d\n", ret); } @@ -618,19 +626,6 @@ static int cs35l41_runtime_resume(struct device *dev) return 0; } -static int cs35l41_hda_suspend_hook(struct device *dev) -{ - dev_dbg(dev, "Request Suspend\n"); - pm_runtime_mark_last_busy(dev); - return pm_runtime_put_autosuspend(dev); -} - -static int cs35l41_hda_resume_hook(struct device *dev) -{ - dev_dbg(dev, "Request Resume\n"); - return pm_runtime_get_sync(dev); -} - static int cs35l41_smart_amp(struct cs35l41_hda *cs35l41) { int halo_sts; @@ -863,8 +858,6 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas ret = cs35l41_create_controls(cs35l41); comps->playback_hook = cs35l41_hda_playback_hook; - comps->suspend_hook = cs35l41_hda_suspend_hook; - comps->resume_hook = cs35l41_hda_resume_hook; pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); diff --git a/sound/pci/hda/hda_component.h b/sound/pci/hda/hda_component.h index 1223621bd62c..534e845b9cd1 100644 --- a/sound/pci/hda/hda_component.h +++ b/sound/pci/hda/hda_component.h @@ -16,6 +16,4 @@ struct hda_component { char name[HDA_MAX_NAME_SIZE]; struct hda_codec *codec; void (*playback_hook)(struct device *dev, int action); - int (*suspend_hook)(struct device *dev); - int (*resume_hook)(struct device *dev); }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4b076912bbf4..e6c4bb5fa041 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4022,22 +4022,16 @@ static void alc5505_dsp_init(struct hda_codec *codec) static int alc269_suspend(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - int i; if (spec->has_alc5505_dsp) alc5505_dsp_suspend(codec); - for (i = 0; i < HDA_MAX_COMPONENTS; i++) - if (spec->comps[i].suspend_hook) - spec->comps[i].suspend_hook(spec->comps[i].dev); - return alc_suspend(codec); } static int alc269_resume(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - int i; if (spec->codec_variant == ALC269_TYPE_ALC269VB) alc269vb_toggle_power_output(codec, 0); @@ -4068,10 +4062,6 @@ static int alc269_resume(struct hda_codec *codec) if (spec->has_alc5505_dsp) alc5505_dsp_resume(codec); - for (i = 0; i < HDA_MAX_COMPONENTS; i++) - if (spec->comps[i].resume_hook) - spec->comps[i].resume_hook(spec->comps[i].dev); - return 0; } #endif /* CONFIG_PM */ @@ -6664,19 +6654,12 @@ static int comp_bind(struct device *dev) { struct hda_codec *cdc = dev_to_hda_codec(dev); struct alc_spec *spec = cdc->spec; - int ret, i; + int ret; ret = component_bind_all(dev, spec->comps); if (ret) return ret; - if (snd_hdac_is_power_on(&cdc->core)) { - codec_dbg(cdc, "Resuming after bind.\n"); - for (i = 0; i < HDA_MAX_COMPONENTS; i++) - if (spec->comps[i].resume_hook) - spec->comps[i].resume_hook(spec->comps[i].dev); - } - return 0; } -- cgit From 88672826e2a465d2f4c0a50fb5ced2956f4ffcbc Mon Sep 17 00:00:00 2001 From: Stefan Binding Date: Tue, 11 Oct 2022 15:35:52 +0100 Subject: ALSA: hda: cs35l41: Support System Suspend Add support for system suspend into the CS35L41 HDA Driver. Since S4 suspend may power off the system, it is required that the driver ensure the part is safe to be shutdown before system suspend, as well as ensuring that the firmware is unloaded before shutdown. The part must then be restored on system resume, including re-downloading the firmware. Signed-off-by: Stefan Binding Link: https://lore.kernel.org/r/20221011143552.621792-6-sbinding@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/cs35l41_hda.c | 160 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 136 insertions(+), 24 deletions(-) diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index 89f6b4a28d3d..e5f0549bf06d 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -461,9 +461,12 @@ static void cs35l41_remove_dsp(struct cs35l41_hda *cs35l41) struct cs_dsp *dsp = &cs35l41->cs_dsp; cancel_work_sync(&cs35l41->fw_load_work); + + mutex_lock(&cs35l41->fw_mutex); cs35l41_shutdown_dsp(cs35l41); cs_dsp_remove(dsp); cs35l41->halo_initialized = false; + mutex_unlock(&cs35l41->fw_mutex); } /* Protection release cycle to get the speaker out of Safe-Mode */ @@ -570,45 +573,148 @@ static int cs35l41_hda_channel_map(struct device *dev, unsigned int tx_num, unsi rx_slot); } +static void cs35l41_ready_for_reset(struct cs35l41_hda *cs35l41) +{ + mutex_lock(&cs35l41->fw_mutex); + if (cs35l41->firmware_running) { + + regcache_cache_only(cs35l41->regmap, false); + + cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap); + cs35l41_shutdown_dsp(cs35l41); + cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type); + + regcache_cache_only(cs35l41->regmap, true); + regcache_mark_dirty(cs35l41->regmap); + } + mutex_unlock(&cs35l41->fw_mutex); +} + +static int cs35l41_system_suspend(struct device *dev) +{ + struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + int ret; + + dev_dbg(cs35l41->dev, "System Suspend\n"); + + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { + dev_err(cs35l41->dev, "System Suspend not supported\n"); + return -EINVAL; + } + + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; + + /* Shutdown DSP before system suspend */ + cs35l41_ready_for_reset(cs35l41); + + /* + * Reset GPIO may be shared, so cannot reset here. + * However beyond this point, amps may be powered down. + */ + return 0; +} + +static int cs35l41_system_resume(struct device *dev) +{ + struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + int ret; + + dev_dbg(cs35l41->dev, "System Resume\n"); + + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { + dev_err(cs35l41->dev, "System Resume not supported\n"); + return -EINVAL; + } + + if (cs35l41->reset_gpio) { + usleep_range(2000, 2100); + gpiod_set_value_cansleep(cs35l41->reset_gpio, 1); + } + + usleep_range(2000, 2100); + + ret = pm_runtime_force_resume(dev); + + mutex_lock(&cs35l41->fw_mutex); + if (!ret && cs35l41->request_fw_load && !cs35l41->fw_request_ongoing) { + cs35l41->fw_request_ongoing = true; + schedule_work(&cs35l41->fw_load_work); + } + mutex_unlock(&cs35l41->fw_mutex); + + return ret; +} + static int cs35l41_runtime_suspend(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + int ret = 0; - dev_dbg(cs35l41->dev, "Suspend\n"); + dev_dbg(cs35l41->dev, "Runtime Suspend\n"); - if (!cs35l41->firmware_running) + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { + dev_dbg(cs35l41->dev, "Runtime Suspend not supported\n"); return 0; + } - if (cs35l41_enter_hibernate(cs35l41->dev, cs35l41->regmap, cs35l41->hw_cfg.bst_type) < 0) - return 0; + mutex_lock(&cs35l41->fw_mutex); + + if (cs35l41->playback_started) { + regmap_multi_reg_write(cs35l41->regmap, cs35l41_hda_mute, + ARRAY_SIZE(cs35l41_hda_mute)); + cs35l41_global_enable(cs35l41->regmap, cs35l41->hw_cfg.bst_type, 0); + regmap_update_bits(cs35l41->regmap, CS35L41_PWR_CTRL2, + CS35L41_AMP_EN_MASK, 0 << CS35L41_AMP_EN_SHIFT); + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) + regmap_write(cs35l41->regmap, CS35L41_GPIO1_CTRL1, 0x00000001); + regmap_update_bits(cs35l41->regmap, CS35L41_PWR_CTRL2, + CS35L41_VMON_EN_MASK | CS35L41_IMON_EN_MASK, + 0 << CS35L41_VMON_EN_SHIFT | 0 << CS35L41_IMON_EN_SHIFT); + cs35l41->playback_started = false; + } + + if (cs35l41->firmware_running) { + ret = cs35l41_enter_hibernate(cs35l41->dev, cs35l41->regmap, + cs35l41->hw_cfg.bst_type); + if (ret) + goto err; + } else { + cs35l41_safe_reset(cs35l41->regmap, cs35l41->hw_cfg.bst_type); + } regcache_cache_only(cs35l41->regmap, true); regcache_mark_dirty(cs35l41->regmap); - return 0; +err: + mutex_unlock(&cs35l41->fw_mutex); + + return ret; } static int cs35l41_runtime_resume(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); - int ret; + int ret = 0; - dev_dbg(cs35l41->dev, "Resume.\n"); + dev_dbg(cs35l41->dev, "Runtime Resume\n"); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { - dev_dbg(cs35l41->dev, "System does not support Resume\n"); + dev_dbg(cs35l41->dev, "Runtime Resume not supported\n"); return 0; } - if (!cs35l41->firmware_running) - return 0; + mutex_lock(&cs35l41->fw_mutex); regcache_cache_only(cs35l41->regmap, false); - ret = cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap); - if (ret) { - regcache_cache_only(cs35l41->regmap, true); - return ret; + if (cs35l41->firmware_running) { + ret = cs35l41_exit_hibernate(cs35l41->dev, cs35l41->regmap); + if (ret) { + dev_warn(cs35l41->dev, "Unable to exit Hibernate."); + goto err; + } } /* Test key needs to be unlocked to allow the OTP settings to re-apply */ @@ -617,13 +723,16 @@ static int cs35l41_runtime_resume(struct device *dev) cs35l41_test_key_lock(cs35l41->dev, cs35l41->regmap); if (ret) { dev_err(cs35l41->dev, "Failed to restore register cache: %d\n", ret); - return ret; + goto err; } if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST) cs35l41_init_boost(cs35l41->dev, cs35l41->regmap, &cs35l41->hw_cfg); - return 0; +err: + mutex_unlock(&cs35l41->fw_mutex); + + return ret; } static int cs35l41_smart_amp(struct cs35l41_hda *cs35l41) @@ -673,8 +782,6 @@ clean_dsp: static void cs35l41_load_firmware(struct cs35l41_hda *cs35l41, bool load) { - pm_runtime_get_sync(cs35l41->dev); - if (cs35l41->firmware_running && !load) { dev_dbg(cs35l41->dev, "Unloading Firmware\n"); cs35l41_shutdown_dsp(cs35l41); @@ -684,9 +791,6 @@ static void cs35l41_load_firmware(struct cs35l41_hda *cs35l41, bool load) } else { dev_dbg(cs35l41->dev, "Unable to Load firmware.\n"); } - - pm_runtime_mark_last_busy(cs35l41->dev); - pm_runtime_put_autosuspend(cs35l41->dev); } static int cs35l41_fw_load_ctl_get(struct snd_kcontrol *kcontrol, @@ -702,16 +806,21 @@ static void cs35l41_fw_load_work(struct work_struct *work) { struct cs35l41_hda *cs35l41 = container_of(work, struct cs35l41_hda, fw_load_work); + pm_runtime_get_sync(cs35l41->dev); + mutex_lock(&cs35l41->fw_mutex); /* Recheck if playback is ongoing, mutex will block playback during firmware loading */ if (cs35l41->playback_started) - dev_err(cs35l41->dev, "Cannot Load/Unload firmware during Playback\n"); + dev_err(cs35l41->dev, "Cannot Load/Unload firmware during Playback. Retrying...\n"); else cs35l41_load_firmware(cs35l41, cs35l41->request_fw_load); cs35l41->fw_request_ongoing = false; mutex_unlock(&cs35l41->fw_mutex); + + pm_runtime_mark_last_busy(cs35l41->dev); + pm_runtime_put_autosuspend(cs35l41->dev); } static int cs35l41_fw_load_ctl_put(struct snd_kcontrol *kcontrol, @@ -835,6 +944,8 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas pm_runtime_get_sync(dev); + mutex_lock(&cs35l41->fw_mutex); + comps->dev = dev; if (!cs35l41->acpi_subsystem_id) cs35l41->acpi_subsystem_id = kasprintf(GFP_KERNEL, "%.8x", @@ -847,10 +958,8 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas if (firmware_autostart) { dev_dbg(cs35l41->dev, "Firmware Autostart.\n"); cs35l41->request_fw_load = true; - mutex_lock(&cs35l41->fw_mutex); if (cs35l41_smart_amp(cs35l41) < 0) dev_warn(cs35l41->dev, "Cannot Run Firmware, reverting to dsp bypass...\n"); - mutex_unlock(&cs35l41->fw_mutex); } else { dev_dbg(cs35l41->dev, "Firmware Autostart is disabled.\n"); } @@ -859,6 +968,8 @@ static int cs35l41_hda_bind(struct device *dev, struct device *master, void *mas comps->playback_hook = cs35l41_hda_playback_hook; + mutex_unlock(&cs35l41->fw_mutex); + pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); @@ -1426,6 +1537,7 @@ EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41); const struct dev_pm_ops cs35l41_hda_pm_ops = { RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(cs35l41_system_suspend, cs35l41_system_resume) }; EXPORT_SYMBOL_NS_GPL(cs35l41_hda_pm_ops, SND_HDA_SCODEC_CS35L41); -- cgit From b675d4bdfefac2fd46838383ecb3c06ad0f4c94d Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Tue, 11 Oct 2022 22:51:55 +0000 Subject: mm: cgroup: fix comments for get from fd/file helpers Fix the documentation comments for cgroup_[v1v2_]get_from_[fd/file](). Reported-by: kernel test robot Signed-off-by: Yosry Ahmed Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 6349a9fe9ec1..d922773fa90b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6246,6 +6246,7 @@ static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) /** * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports * cgroup2. + * @f: file corresponding to cgroup2_dir */ static struct cgroup *cgroup_get_from_file(struct file *f) { @@ -6753,7 +6754,7 @@ out: EXPORT_SYMBOL_GPL(cgroup_get_from_path); /** - * cgroup_get_from_fd - get a cgroup pointer from a fd + * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained @@ -6778,6 +6779,7 @@ struct cgroup *cgroup_v1v2_get_from_fd(int fd) /** * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports * cgroup2. + * @fd: fd obtained by open(cgroup2_dir) */ struct cgroup *cgroup_get_from_fd(int fd) { -- cgit From a8e5e5146ad08d794c58252bab00b261045ef16d Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Thu, 6 Oct 2022 17:33:54 +0100 Subject: arm64: mte: Avoid setting PG_mte_tagged if no tags cleared or restored Prior to commit 69e3b846d8a7 ("arm64: mte: Sync tags for pages where PTE is untagged"), mte_sync_tags() was only called for pte_tagged() entries (those mapped with PROT_MTE). Therefore mte_sync_tags() could safely use test_and_set_bit(PG_mte_tagged, &page->flags) without inadvertently setting PG_mte_tagged on an untagged page. The above commit was required as guests may enable MTE without any control at the stage 2 mapping, nor a PROT_MTE mapping in the VMM. However, the side-effect was that any page with a PTE that looked like swap (or migration) was getting PG_mte_tagged set automatically. A subsequent page copy (e.g. migration) copied the tags to the destination page even if the tags were owned by KASAN. This issue was masked by the page_kasan_tag_reset() call introduced in commit e5b8d9218951 ("arm64: mte: reset the page tag in page->flags"). When this commit was reverted (20794545c146), KASAN started reporting access faults because the overriding tags in a page did not match the original page->flags (with CONFIG_KASAN_HW_TAGS=y): BUG: KASAN: invalid-access in copy_page+0x10/0xd0 arch/arm64/lib/copy_page.S:26 Read at addr f5ff000017f2e000 by task syz-executor.1/2218 Pointer tag: [f5], memory tag: [f2] Move the PG_mte_tagged bit setting from mte_sync_tags() to the actual place where tags are cleared (mte_sync_page_tags()) or restored (mte_restore_tags()). Signed-off-by: Catalin Marinas Reported-by: syzbot+c2c79c6d6eddc5262b77@syzkaller.appspotmail.com Fixes: 69e3b846d8a7 ("arm64: mte: Sync tags for pages where PTE is untagged") Cc: # 5.14.x Cc: Steven Price Cc: Andrey Konovalov Cc: Vincenzo Frascino Cc: Will Deacon Link: https://lore.kernel.org/r/0000000000004387dc05e5888ae5@google.com/ Reviewed-by: Steven Price Link: https://lore.kernel.org/r/20221006163354.3194102-1-catalin.marinas@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/mte.c | 9 +++++++-- arch/arm64/mm/mteswap.c | 7 ++++++- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index aca88470fb69..7467217c1eaf 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -48,7 +48,12 @@ static void mte_sync_page_tags(struct page *page, pte_t old_pte, if (!pte_is_tagged) return; - mte_clear_page_tags(page_address(page)); + /* + * Test PG_mte_tagged again in case it was racing with another + * set_pte_at(). + */ + if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + mte_clear_page_tags(page_address(page)); } void mte_sync_tags(pte_t old_pte, pte_t pte) @@ -64,7 +69,7 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) /* if PG_mte_tagged is set, tags have already been initialised */ for (i = 0; i < nr_pages; i++, page++) { - if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + if (!test_bit(PG_mte_tagged, &page->flags)) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); } diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c index 4334dec93bd4..bed803d8e158 100644 --- a/arch/arm64/mm/mteswap.c +++ b/arch/arm64/mm/mteswap.c @@ -53,7 +53,12 @@ bool mte_restore_tags(swp_entry_t entry, struct page *page) if (!tags) return false; - mte_restore_page_tags(page_address(page), tags); + /* + * Test PG_mte_tagged again in case it was racing with another + * set_pte_at(). + */ + if (!test_and_set_bit(PG_mte_tagged, &page->flags)) + mte_restore_page_tags(page_address(page), tags); return true; } -- cgit From a1ae8d4d9be0178132df7c4931a1ba77d0e76039 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 28 Sep 2022 09:23:26 +0300 Subject: nvme-rdma: fix possible hang caused during ctrl deletion When we delete a controller, we execute the following: 1. nvme_stop_ctrl() - stop some work elements that may be inflight or scheduled (specifically also .stop_ctrl which cancels ctrl error recovery work) 2. nvme_remove_namespaces() - which first flushes scan_work to avoid competing ns addition/removal 3. continue to teardown the controller However, if err_work was scheduled to run in (1), it is designed to cancel any inflight I/O, particularly I/O that is originating from ns scan_work in (2), but because it is cancelled in .stop_ctrl(), we can prevent forward progress of (2) as ns scanning is blocking on I/O (that will never be cancelled). The race is: 1. transport layer error observed -> err_work is scheduled 2. scan_work executes, discovers ns, generate I/O to it 3. nvme_ctop_ctrl() -> .stop_ctrl() -> cancel_work_sync(err_work) - err_work never executed 4. nvme_remove_namespaces() -> flush_work(scan_work) --> deadlock, because scan_work is blocked on I/O that was supposed to be cancelled by err_work, but was cancelled before executing. Fix this by flushing err_work instead of cancelling it, to force it to execute and cancel all inflight I/O. Fixes: b435ecea2a4d ("nvme: Add .stop_ctrl to nvme ctrl ops") Fixes: f6c8e432cb04 ("nvme: flush namespace scanning work just before removing namespaces") Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/rdma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 5ad0ab2853a4..6e079abb22ee 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -996,7 +996,7 @@ static void nvme_rdma_stop_ctrl(struct nvme_ctrl *nctrl) { struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); - cancel_work_sync(&ctrl->err_work); + flush_work(&ctrl->err_work); cancel_delayed_work_sync(&ctrl->reconnect_work); } -- cgit From c4abd8757189c7ca5803828f9c892328d7d94943 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 28 Sep 2022 09:23:25 +0300 Subject: nvme-tcp: fix possible hang caused during ctrl deletion When we delete a controller, we execute the following: 1. nvme_stop_ctrl() - stop some work elements that may be inflight or scheduled (specifically also .stop_ctrl which cancels ctrl error recovery work) 2. nvme_remove_namespaces() - which first flushes scan_work to avoid competing ns addition/removal 3. continue to teardown the controller However, if err_work was scheduled to run in (1), it is designed to cancel any inflight I/O, particularly I/O that is originating from ns scan_work in (2), but because it is cancelled in .stop_ctrl(), we can prevent forward progress of (2) as ns scanning is blocking on I/O (that will never be cancelled). The race is: 1. transport layer error observed -> err_work is scheduled 2. scan_work executes, discovers ns, generate I/O to it 3. nvme_ctop_ctrl() -> .stop_ctrl() -> cancel_work_sync(err_work) - err_work never executed 4. nvme_remove_namespaces() -> flush_work(scan_work) --> deadlock, because scan_work is blocked on I/O that was supposed to be cancelled by err_work, but was cancelled before executing (see stack trace [1]). Fix this by flushing err_work instead of cancelling it, to force it to execute and cancel all inflight I/O. [1]: -- Call Trace: __schedule+0x390/0x910 ? scan_shadow_nodes+0x40/0x40 schedule+0x55/0xe0 io_schedule+0x16/0x40 do_read_cache_page+0x55d/0x850 ? __page_cache_alloc+0x90/0x90 read_cache_page+0x12/0x20 read_part_sector+0x3f/0x110 amiga_partition+0x3d/0x3e0 ? osf_partition+0x33/0x220 ? put_partition+0x90/0x90 bdev_disk_changed+0x1fe/0x4d0 blkdev_get_whole+0x7b/0x90 blkdev_get_by_dev+0xda/0x2d0 device_add_disk+0x356/0x3b0 nvme_mpath_set_live+0x13c/0x1a0 [nvme_core] ? nvme_parse_ana_log+0xae/0x1a0 [nvme_core] nvme_update_ns_ana_state+0x3a/0x40 [nvme_core] nvme_mpath_add_disk+0x120/0x160 [nvme_core] nvme_alloc_ns+0x594/0xa00 [nvme_core] nvme_validate_or_alloc_ns+0xb9/0x1a0 [nvme_core] ? __nvme_submit_sync_cmd+0x1d2/0x210 [nvme_core] nvme_scan_work+0x281/0x410 [nvme_core] process_one_work+0x1be/0x380 worker_thread+0x37/0x3b0 ? process_one_work+0x380/0x380 kthread+0x12d/0x150 ? set_kthread_struct+0x50/0x50 ret_from_fork+0x1f/0x30 INFO: task nvme:6725 blocked for more than 491 seconds. Not tainted 5.15.65-f0.el7.x86_64 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:nvme state:D stack: 0 pid: 6725 ppid: 1761 flags:0x00004000 Call Trace: __schedule+0x390/0x910 ? sched_clock+0x9/0x10 schedule+0x55/0xe0 schedule_timeout+0x24b/0x2e0 ? try_to_wake_up+0x358/0x510 ? finish_task_switch+0x88/0x2c0 wait_for_completion+0xa5/0x110 __flush_work+0x144/0x210 ? worker_attach_to_pool+0xc0/0xc0 flush_work+0x10/0x20 nvme_remove_namespaces+0x41/0xf0 [nvme_core] nvme_do_delete_ctrl+0x47/0x66 [nvme_core] nvme_sysfs_delete.cold.96+0x8/0xd [nvme_core] dev_attr_store+0x14/0x30 sysfs_kf_write+0x38/0x50 kernfs_fop_write_iter+0x146/0x1d0 new_sync_write+0x114/0x1b0 ? intel_pmu_handle_irq+0xe0/0x420 vfs_write+0x18d/0x270 ksys_write+0x61/0xe0 __x64_sys_write+0x1a/0x20 do_syscall_64+0x37/0x90 entry_SYSCALL_64_after_hwframe+0x61/0xcb -- Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver") Reported-by: Jonathan Nicklin Signed-off-by: Sagi Grimberg Tested-by: Jonathan Nicklin Signed-off-by: Christoph Hellwig --- drivers/nvme/host/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 93e2e313fa70..1eed0fc26b3a 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2181,7 +2181,7 @@ out_fail: static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl) { - cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work); + flush_work(&to_tcp_ctrl(ctrl)->err_work); cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work); } -- cgit From 80b2624094c8d369a3c6eab515e8f1564d2e5db2 Mon Sep 17 00:00:00 2001 From: Abhijit Date: Mon, 10 Oct 2022 10:30:05 +0200 Subject: nvme-pci: add NVME_QUIRK_BOGUS_NID for Lexar NM760 Add a quirk to fix Lexar NM760 SSD drives reporting duplicate nsids. Signed-off-by: Abhijit Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 5b796efa325b..fd2c0231d2e2 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3527,6 +3527,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1d97, 0x2263), /* Lexar NM610 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1d97, 0x2269), /* Lexar NM760 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), -- cgit From d5d3c100ac40dcb03959a6f1d2f0f13204c4f145 Mon Sep 17 00:00:00 2001 From: Xi Ruoyao Date: Wed, 28 Sep 2022 17:39:13 +0800 Subject: nvme-pci: avoid the deepest sleep state on ZHITAI TiPro5000 SSDs ZHITAI TiPro5000 SSDs has the same APST sleep problem as its cousin, TiPro7000. The quirk for TiPro7000 has been added in commit 6b961bce50e4 ("nvme-pci: avoid the deepest sleep state on ZHITAI TiPro7000 SSDs"), use the same quirk for TiPro5000. The ASPT data from "nvme id-ctrl /dev/nvme1": vid : 0x1e49 ssvid : 0x1e49 sn : ZTA21T0KA2227304LM mn : ZHITAI TiPlus5000 1TB fr : ZTA09139 [...] ps 0 : mp:6.50W operational enlat:0 exlat:0 rrt:0 rrl:0 rwt:0 rwl:0 idle_power:- active_power:- ps 1 : mp:5.80W operational enlat:0 exlat:0 rrt:1 rrl:1 rwt:1 rwl:1 idle_power:- active_power:- ps 2 : mp:3.60W operational enlat:0 exlat:0 rrt:2 rrl:2 rwt:2 rwl:2 idle_power:- active_power:- ps 3 : mp:0.0500W non-operational enlat:5000 exlat:10000 rrt:3 rrl:3 rwt:3 rwl:3 idle_power:- active_power:- ps 4 : mp:0.0025W non-operational enlat:8000 exlat:45000 rrt:4 rrl:4 rwt:4 rwl:4 idle_power:- active_power:- Reported-and-tested-by: Chang Feng Signed-off-by: Xi Ruoyao Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fd2c0231d2e2..bcbef6bc5672 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3521,6 +3521,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1dbe, 0x5236), /* ADATA XPG GAMMIX S70 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e49, 0x0021), /* ZHITAI TiPro5000 NVMe SSD */ + .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x1e49, 0x0041), /* ZHITAI TiPro7000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0xc0a9, 0x540a), /* Crucial P2 */ -- cgit From 72e3b8883a36e80ebfa41015c7b6926ce31ace05 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 29 Sep 2022 10:36:47 +0300 Subject: nvme-multipath: fix possible hang in live ns resize with ANA access When we revalidate paths as part of ns size change (as of commit e7d65803e2bb), it is possible that during the path revalidation, the only paths that is IO capable (i.e. optimized/non-optimized) are the ones that ns resize was not yet informed to the host, which will cause inflight requests to be requeued (as we have available paths but none are IO capable). These requests on the requeue list are waiting for someone to resubmit them at some point. The IO capable paths will eventually notify the ns resize change to the host, but there is nothing that will kick the requeue list to resubmit the queued requests. Fix this by always kicking the requeue list, and if no IO capable path exists, these requests will be queued again. A typical log that indicates that IOs are requeued: -- nvme nvme1: creating 4 I/O queues. nvme nvme1: new ctrl: "testnqn1" nvme nvme2: creating 4 I/O queues. nvme nvme2: mapped 4/0/0 default/read/poll queues. nvme nvme2: new ctrl: NQN "testnqn1", addr 127.0.0.1:8009 nvme nvme1: rescanning namespaces. nvme1n1: detected capacity change from 2097152 to 4194304 block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O nvme nvme2: rescanning namespaces. -- Reported-by: Yogev Cohen Fixes: e7d65803e2bb ("nvme-multipath: revalidate paths during rescan") Signed-off-by: Sagi Grimberg Cc: # v5.15+ Signed-off-by: Christoph Hellwig --- drivers/nvme/host/multipath.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 00f2f81e20fa..0ea7e441e080 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -182,6 +182,7 @@ void nvme_mpath_revalidate_paths(struct nvme_ns *ns) for_each_node(node) rcu_assign_pointer(head->current_path[node], NULL); + kblockd_schedule_work(&head->requeue_work); } static bool nvme_path_is_disabled(struct nvme_ns *ns) -- cgit From e237506238352f3bfa9cf3983cdab873e35651eb Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 12 Oct 2022 13:53:34 +1000 Subject: powerpc/32: fix syscall wrappers with 64-bit arguments of unaligned register-pairs powerpc 32-bit system call (and function) calling convention for 64-bit arguments requires the next available odd-pair (two sequential registers with the first being odd-numbered) from the standard register argument allocation. The first argument register is r3, so a 64-bit argument that appears at an even position in the argument list must skip a register (unless there were preceding 64-bit arguments, which might throw things off). This requires non-standard compat definitions to deal with the holes in the argument register allocation. With pt_regs syscall wrappers which use a standard mapper to map pt_regs GPRs to function arguments, 32-bit kernels hit the same basic problem, the standard definitions don't cope with the unused argument registers. Fix this by having 32-bit kernels share those syscall definitions with compat. Thanks to Jason for spending a lot of time finding and bisecting this and developing a trivial reproducer. The perfect bug report. Reported-by: Jason A. Donenfeld Signed-off-by: Nicholas Piggin Fixes: 7e92e01b72452 ("powerpc: Provide syscall wrapper") Reviewed-by: Arnd Bergmann Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221012035335.866440-1-npiggin@gmail.com --- arch/powerpc/include/asm/syscalls.h | 16 ++++++++++++++ arch/powerpc/kernel/Makefile | 1 + arch/powerpc/kernel/sys_ppc32.c | 38 ++++++++++++++++++++++++-------- arch/powerpc/kernel/syscalls/syscall.tbl | 16 +++++++++----- 4 files changed, 56 insertions(+), 15 deletions(-) diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 9840d572da55..a1142496cd58 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -89,6 +89,22 @@ long compat_sys_rt_sigreturn(void); * responsible for combining parameter pairs. */ +#ifdef CONFIG_PPC32 +long sys_ppc_pread64(unsigned int fd, + char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long sys_ppc_pwrite64(unsigned int fd, + const char __user *ubuf, compat_size_t count, + u32 reg6, u32 pos1, u32 pos2); +long sys_ppc_readahead(int fd, u32 r4, + u32 offset1, u32 offset2, u32 count); +long sys_ppc_truncate64(const char __user *path, u32 reg4, + unsigned long len1, unsigned long len2); +long sys_ppc_ftruncate64(unsigned int fd, u32 reg4, + unsigned long len1, unsigned long len2); +long sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, + size_t len, int advice); +#endif #ifdef CONFIG_COMPAT long compat_sys_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index ee2d76cb3187..9b6146056e48 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -73,6 +73,7 @@ obj-y := cputable.o syscalls.o \ obj-y += ptrace/ obj-$(CONFIG_PPC64) += setup_64.o irq_64.o\ paca.o nvram_64.o note.o +obj-$(CONFIG_PPC32) += sys_ppc32.o obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o obj-$(CONFIG_VDSO32) += vdso32_wrapper.o obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index dcc3c9fd4cfd..1ab4a4d95aba 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -1,13 +1,23 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * sys_ppc32.c: Conversion between 32bit and 64bit native syscalls. + * sys_ppc32.c: 32-bit system calls with complex calling conventions. * * Copyright (C) 2001 IBM * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) * - * These routines maintain argument size conversion between 32bit and 64bit - * environment. + * 32-bit system calls with 64-bit arguments pass those in register pairs. + * This must be specially dealt with on 64-bit kernels. The compat_arg_u64_dual + * in generic compat syscalls is not always usable because the register + * pairing is constrained depending on preceding arguments. + * + * An analogous problem exists on 32-bit kernels with ARCH_HAS_SYSCALL_WRAPPER, + * the defined system call functions take the pt_regs as an argument, and there + * is a mapping macro which maps registers to arguments + * (SC_POWERPC_REGS_TO_ARGS) which also does not deal with these 64-bit + * arguments. + * + * This file contains these system calls. */ #include @@ -47,7 +57,17 @@ #include #include -COMPAT_SYSCALL_DEFINE6(ppc_pread64, +#ifdef CONFIG_PPC32 +#define PPC32_SYSCALL_DEFINE4 SYSCALL_DEFINE4 +#define PPC32_SYSCALL_DEFINE5 SYSCALL_DEFINE5 +#define PPC32_SYSCALL_DEFINE6 SYSCALL_DEFINE6 +#else +#define PPC32_SYSCALL_DEFINE4 COMPAT_SYSCALL_DEFINE4 +#define PPC32_SYSCALL_DEFINE5 COMPAT_SYSCALL_DEFINE5 +#define PPC32_SYSCALL_DEFINE6 COMPAT_SYSCALL_DEFINE6 +#endif + +PPC32_SYSCALL_DEFINE6(ppc_pread64, unsigned int, fd, char __user *, ubuf, compat_size_t, count, u32, reg6, u32, pos1, u32, pos2) @@ -55,7 +75,7 @@ COMPAT_SYSCALL_DEFINE6(ppc_pread64, return ksys_pread64(fd, ubuf, count, merge_64(pos1, pos2)); } -COMPAT_SYSCALL_DEFINE6(ppc_pwrite64, +PPC32_SYSCALL_DEFINE6(ppc_pwrite64, unsigned int, fd, const char __user *, ubuf, compat_size_t, count, u32, reg6, u32, pos1, u32, pos2) @@ -63,28 +83,28 @@ COMPAT_SYSCALL_DEFINE6(ppc_pwrite64, return ksys_pwrite64(fd, ubuf, count, merge_64(pos1, pos2)); } -COMPAT_SYSCALL_DEFINE5(ppc_readahead, +PPC32_SYSCALL_DEFINE5(ppc_readahead, int, fd, u32, r4, u32, offset1, u32, offset2, u32, count) { return ksys_readahead(fd, merge_64(offset1, offset2), count); } -COMPAT_SYSCALL_DEFINE4(ppc_truncate64, +PPC32_SYSCALL_DEFINE4(ppc_truncate64, const char __user *, path, u32, reg4, unsigned long, len1, unsigned long, len2) { return ksys_truncate(path, merge_64(len1, len2)); } -COMPAT_SYSCALL_DEFINE4(ppc_ftruncate64, +PPC32_SYSCALL_DEFINE4(ppc_ftruncate64, unsigned int, fd, u32, reg4, unsigned long, len1, unsigned long, len2) { return ksys_ftruncate(fd, merge_64(len1, len2)); } -COMPAT_SYSCALL_DEFINE6(ppc32_fadvise64, +PPC32_SYSCALL_DEFINE6(ppc32_fadvise64, int, fd, u32, unused, u32, offset1, u32, offset2, size_t, len, int, advice) { diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 2bca64f96164..e9e0df4f9a61 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -228,8 +228,10 @@ 176 64 rt_sigtimedwait sys_rt_sigtimedwait 177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo 178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend -179 common pread64 sys_pread64 compat_sys_ppc_pread64 -180 common pwrite64 sys_pwrite64 compat_sys_ppc_pwrite64 +179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64 +179 64 pread64 sys_pread64 +180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64 +180 64 pwrite64 sys_pwrite64 181 common chown sys_chown 182 common getcwd sys_getcwd 183 common capget sys_capget @@ -242,10 +244,11 @@ 188 common putpmsg sys_ni_syscall 189 nospu vfork sys_vfork 190 common ugetrlimit sys_getrlimit compat_sys_getrlimit -191 common readahead sys_readahead compat_sys_ppc_readahead +191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead +191 64 readahead sys_readahead 192 32 mmap2 sys_mmap2 compat_sys_mmap2 -193 32 truncate64 sys_truncate64 compat_sys_ppc_truncate64 -194 32 ftruncate64 sys_ftruncate64 compat_sys_ppc_ftruncate64 +193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64 +194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64 195 32 stat64 sys_stat64 196 32 lstat64 sys_lstat64 197 32 fstat64 sys_fstat64 @@ -288,7 +291,8 @@ 230 common io_submit sys_io_submit compat_sys_io_submit 231 common io_cancel sys_io_cancel 232 nospu set_tid_address sys_set_tid_address -233 common fadvise64 sys_fadvise64 compat_sys_ppc32_fadvise64 +233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64 +233 64 fadvise64 sys_fadvise64 234 nospu exit_group sys_exit_group 235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie 236 common epoll_create sys_epoll_create -- cgit From 37a3a3278516eae364006d5597f2b9d40580a450 Mon Sep 17 00:00:00 2001 From: ChiaEn Wu Date: Thu, 6 Oct 2022 11:16:13 +0800 Subject: dt-bindings: leds: mt6370: Fix MT6370 LED indicator DT warning Add '$ref' and 'unevaluatedProperties: false' in 'multi-led', and remove unused 'allOf' property. Fixes: 440c57dabb45 ("dt-bindings: leds: mt6370: Add MediaTek MT6370 current sink type LED indicator") Signed-off-by: ChiaEn Wu Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/435f6888ebc20c5abae63eb9cb3a055b60db2ed1.1665050503.git.chiaen_wu@richtek.com Signed-off-by: Rob Herring --- .../devicetree/bindings/leds/mediatek,mt6370-indicator.yaml | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/leds/mediatek,mt6370-indicator.yaml b/Documentation/devicetree/bindings/leds/mediatek,mt6370-indicator.yaml index 204b103ffc2c..16b3abc2af3a 100644 --- a/Documentation/devicetree/bindings/leds/mediatek,mt6370-indicator.yaml +++ b/Documentation/devicetree/bindings/leds/mediatek,mt6370-indicator.yaml @@ -13,9 +13,6 @@ description: | This module is part of the MT6370 MFD device. Add MT6370 LED driver include 4-channel RGB LED support Register/PWM/Breath Mode -allOf: - - $ref: leds-class-multicolor.yaml# - properties: compatible: const: mediatek,mt6370-indicator @@ -29,6 +26,8 @@ properties: patternProperties: "^multi-led@[0-3]$": type: object + $ref: leds-class-multicolor.yaml# + unevaluatedProperties: false properties: reg: -- cgit From 6127dab7a126387744290101514d31b79bb62b8e Mon Sep 17 00:00:00 2001 From: ChiaEn Wu Date: Wed, 12 Oct 2022 15:08:14 +0800 Subject: dt-bindings: mfd: mt6370: fix the interrupt order of the charger in the example Fix the interrupt order of the charger in the binding example. Fixes: 76f52f815f1a ("dt-bindings: mfd: Add MediaTek MT6370") Signed-off-by: ChiaEn Wu Acked-by: Krzysztof Kozlowski Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/fcf4e7e7594070a8698dc0d4b96e031bcaa9b3a3.1665585952.git.chiaen_wu@richtek.com Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/mfd/mediatek,mt6370.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/mfd/mediatek,mt6370.yaml b/Documentation/devicetree/bindings/mfd/mediatek,mt6370.yaml index 250484d59ecd..5644882db2e8 100644 --- a/Documentation/devicetree/bindings/mfd/mediatek,mt6370.yaml +++ b/Documentation/devicetree/bindings/mfd/mediatek,mt6370.yaml @@ -139,8 +139,8 @@ examples: charger { compatible = "mediatek,mt6370-charger"; - interrupts = <48>, <68>, <6>; - interrupt-names = "attach_i", "uvp_d_evt", "mivr"; + interrupts = <68>, <48>, <6>; + interrupt-names = "uvp_d_evt", "attach_i", "mivr"; io-channels = <&mt6370_adc MT6370_CHAN_IBUS>; mt6370_otg_vbus: usb-otg-vbus-regulator { -- cgit From 0811b9e4530d7c46542a8993ce6b725d042c6154 Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Thu, 6 Oct 2022 17:17:40 -0400 Subject: drm/amd/display: Add HUBP surface flip interrupt handler Add the hubp surface flip handler. This fixes some flip timeout issues. Acked-by: Alex Deucher Reviewed-by: Rodrigo Siqueira Signed-off-by: Aurabindo Pillai Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.0.x --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c index f4b901d393eb..ac1c6458dd55 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c @@ -181,6 +181,7 @@ static struct hubp_funcs dcn32_hubp_funcs = { .hubp_init = hubp3_init, .set_unbounded_requesting = hubp31_set_unbounded_requesting, .hubp_soft_reset = hubp31_soft_reset, + .hubp_set_flip_int = hubp1_set_flip_int, .hubp_in_blank = hubp1_in_blank, .hubp_update_force_pstate_disallow = hubp32_update_force_pstate_disallow, .phantom_hubp_post_enable = hubp32_phantom_hubp_post_enable, -- cgit From 06267eb2decaa6baac81bbd882265a8e7782dba4 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Thu, 28 Jul 2022 14:07:15 -0700 Subject: doc: RISC-V: Document that misaligned accesses are supported The RISC-V ISA manual used to mandate that misaligned accesses were supported in user mode, but that requirement was removed in 2018 via riscv-isa-manual commit 61cadb9 ("Provide new description of misaligned load/store behavior compatible with privileged architecture."). Since the Linux uABI was already frozen at that point it's just been demoted to part of the uABI, but that was never written down. Link: https://lore.kernel.org/r/20220728210715.17214-1-palmer@rivosinc.com Signed-off-by: Palmer Dabbelt --- Documentation/riscv/index.rst | 1 + Documentation/riscv/uabi.rst | 6 ++++++ 2 files changed, 7 insertions(+) create mode 100644 Documentation/riscv/uabi.rst diff --git a/Documentation/riscv/index.rst b/Documentation/riscv/index.rst index e23b876ad6eb..2e5b18fbb145 100644 --- a/Documentation/riscv/index.rst +++ b/Documentation/riscv/index.rst @@ -8,6 +8,7 @@ RISC-V architecture boot-image-header vm-layout patch-acceptance + uabi features diff --git a/Documentation/riscv/uabi.rst b/Documentation/riscv/uabi.rst new file mode 100644 index 000000000000..21a82cfb6c4d --- /dev/null +++ b/Documentation/riscv/uabi.rst @@ -0,0 +1,6 @@ +.. SPDX-License-Identifier: GPL-2.0 + +RISC-V Linux User ABI +===================== + +Misaligned accesses are supported in userspace, but they may perform poorly. -- cgit From 0e5d5ae837c8ce04d2ddb874ec5f920118bd9d31 Mon Sep 17 00:00:00 2001 From: D Scott Phillips Date: Mon, 10 Oct 2022 19:21:40 -0700 Subject: arm64: Add AMPERE1 to the Spectre-BHB affected list Per AmpereOne erratum AC03_CPU_12, "Branch history may allow control of speculative execution across software contexts," the AMPERE1 core needs the bhb clearing loop to mitigate Spectre-BHB, with a loop iteration count of 11. Signed-off-by: D Scott Phillips Link: https://lore.kernel.org/r/20221011022140.432370-1-scott@os.amperecomputing.com Reviewed-by: James Morse Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cputype.h | 4 ++++ arch/arm64/kernel/proton-pack.c | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 8aa0d276a636..abc418650fec 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -60,6 +60,7 @@ #define ARM_CPU_IMP_FUJITSU 0x46 #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 +#define ARM_CPU_IMP_AMPERE 0xC0 #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -123,6 +124,8 @@ #define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 +#define AMPERE_CPU_PART_AMPERE1 0xAC3 + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -172,6 +175,7 @@ #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) +#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index a8ea1637b137..bfce41c2a53b 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -868,6 +868,10 @@ u8 spectre_bhb_loop_affected(int scope) MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), {}, }; + static const struct midr_range spectre_bhb_k11_list[] = { + MIDR_ALL_VERSIONS(MIDR_AMPERE1), + {}, + }; static const struct midr_range spectre_bhb_k8_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), @@ -878,6 +882,8 @@ u8 spectre_bhb_loop_affected(int scope) k = 32; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list)) k = 24; + else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k11_list)) + k = 11; else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list)) k = 8; -- cgit From 4f001a21080ff2e2f0e1c3692f5e119aedbb3bc1 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 5 Oct 2022 01:29:03 +0900 Subject: Kconfig.debug: simplify the dependency of DEBUG_INFO_DWARF4/5 Commit c0a5c81ca9be ("Kconfig.debug: drop GCC 5+ version check for DWARF5") could have cleaned up the code a bit more. "CC_IS_CLANG &&" is unneeded. No functional change is intended. Signed-off-by: Masahiro Yamada Reviewed-by: Nathan Chancellor --- lib/Kconfig.debug | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 3761118d1879..72f01edec00e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -264,7 +264,7 @@ config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT config DEBUG_INFO_DWARF4 bool "Generate DWARF Version 4 debuginfo" select DEBUG_INFO - depends on !CC_IS_CLANG || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) + depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502) help Generate DWARF v4 debug info. This requires gcc 4.5+, binutils 2.35.2 if using clang without clang's integrated assembler, and gdb 7.0+. @@ -276,7 +276,7 @@ config DEBUG_INFO_DWARF4 config DEBUG_INFO_DWARF5 bool "Generate DWARF Version 5 debuginfo" select DEBUG_INFO - depends on !CC_IS_CLANG || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) + depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502) help Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc 5.0+ accepts the -gdwarf-5 flag but only had partial support for some -- cgit From bb1435f3f575b5213eaf27434efa3971f51c01de Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 5 Oct 2022 01:29:04 +0900 Subject: Kconfig.debug: add toolchain checks for DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT does not give explicit -gdwarf-* flag. The actual DWARF version is up to the toolchain. The combination of GCC and GAS works fine, and Clang with the integrated assembler is good too. The combination of Clang and GAS is tricky, but at least, the -g flag works for Clang <=13, which defaults to DWARF v4. Clang 14 switched its default to DWARF v5. Now, CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT has the same issue as addressed by commit 98cd6f521f10 ("Kconfig: allow explicit opt in to DWARF v5"). CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y for Clang >= 14 and GAS < 2.35 produces a ton of errors like follows: /tmp/main-c2741c.s: Assembler messages: /tmp/main-c2741c.s:109: Error: junk at end of line, first unrecognized character is `"' /tmp/main-c2741c.s:109: Error: file number less than one Add 'depends on' to check toolchains. Signed-off-by: Masahiro Yamada Reviewed-by: Nathan Chancellor --- lib/Kconfig.debug | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 72f01edec00e..db8d9271cabf 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -253,6 +253,7 @@ config DEBUG_INFO_NONE config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT bool "Rely on the toolchain's implicit default DWARF version" select DEBUG_INFO + depends on !CC_IS_CLANG || AS_IS_LLVM || CLANG_VERSION < 140000 || (AS_IS_GNU && AS_VERSION >= 23502) help The implicit default version of DWARF debug info produced by a toolchain changes over time. -- cgit From fc8c2d8ff20651f887e574767533d1176e3a479c Mon Sep 17 00:00:00 2001 From: Zack Rusin Date: Thu, 6 Oct 2022 10:33:19 -0400 Subject: kbuild: Stop including vmlinux.bz2 in the rpm's vmlinux.bz2 was added to the rpm packages in 2009 in the fc370ecfdb37 ("kbuild: add vmlinux to kernel rpm") but seemingly hasn't been used since. Originally this should have been split up in a seperate debugging package because it massively increases the size of the generated rpm's e.g. kernel rpm built using binrpm-pkg on Fedora 36 default 5.19.8 kernel config and localmodconfig is ~255MB with vmlinux.bz2 and only ~65MB without it. Make the kernel built rpms about 4x smaller by not including the unused vmlinux.bz2 in them. Signed-off-by: Zack Rusin Signed-off-by: Masahiro Yamada --- scripts/package/mkspec | 2 -- 1 file changed, 2 deletions(-) diff --git a/scripts/package/mkspec b/scripts/package/mkspec index c920c1b18e7a..70392fd2fd29 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -97,8 +97,6 @@ $M $MAKE %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} modules_install $MAKE %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install cp System.map %{buildroot}/boot/System.map-$KERNELRELEASE cp .config %{buildroot}/boot/config-$KERNELRELEASE - bzip2 -9 --keep vmlinux - mv vmlinux.bz2 %{buildroot}/boot/vmlinux-$KERNELRELEASE.bz2 $S$M rm -f %{buildroot}/lib/modules/$KERNELRELEASE/build $S$M rm -f %{buildroot}/lib/modules/$KERNELRELEASE/source $S$M mkdir -p %{buildroot}/usr/src/kernels/$KERNELRELEASE -- cgit From d4fa7d772adc02451076b3ad1f990d8b822909fc Mon Sep 17 00:00:00 2001 From: Billy Tsai Date: Mon, 26 Sep 2022 18:51:44 +0800 Subject: i3c: master: Free the old_dyn_addr when reattach. This patch is used to free the old_dyn_addr when the caller want to reattach the device to the different dynamic address. If the old_dyn_addr is 0 the function will treat it as no old_dyn_addr is reserved on the bus. Without the patch, when the driver reattach the i3c device after setnewda the old_dyn_addr will be permanently occupied. Signed-off-by: Billy Tsai Link: https://lore.kernel.org/r/20220926105145.8145-1-billy_tsai@aspeedtech.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 7850287dfe7a..6349ce0ce835 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1379,6 +1379,9 @@ static int i3c_master_reattach_i3c_dev(struct i3c_dev_desc *dev, i3c_bus_set_addr_slot_status(&master->bus, dev->info.dyn_addr, I3C_ADDR_SLOT_I3C_DEV); + if (old_dyn_addr) + i3c_bus_set_addr_slot_status(&master->bus, old_dyn_addr, + I3C_ADDR_SLOT_FREE); } if (master->ops->reattach_i3c_dev) { -- cgit From 90f4a09a15239f4a819b2e90a7a0b92a75060655 Mon Sep 17 00:00:00 2001 From: Billy Tsai Date: Mon, 26 Sep 2022 18:51:45 +0800 Subject: i3c: master: Remove the wrong place of reattach. The reattach should be used when an I3C device has its address changed. But the modified place in this patch doesn't have the address changed of the newdev. This wrong reattach will reserve the same address slot twice and return unexpected -EBUSY when the bus find the duplicate device with diffent dynamic address. Signed-off-by: Billy Tsai Link: https://lore.kernel.org/r/20220926105145.8145-2-billy_tsai@aspeedtech.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 6349ce0ce835..351c81a929a6 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1911,10 +1911,6 @@ int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master, i3c_master_free_i3c_dev(olddev); } - ret = i3c_master_reattach_i3c_dev(newdev, old_dyn_addr); - if (ret) - goto err_detach_dev; - /* * Depending on our previous state, the expected dynamic address might * differ: -- cgit From 0759011157b0d666b02b03b986d3de005d84027e Mon Sep 17 00:00:00 2001 From: Lin Yujun Date: Thu, 15 Sep 2022 14:52:53 +0800 Subject: rtc: stmp3xxx: Add failure handling for stmp3xxx_wdt_register() Use platform_device_put() to free platform device before print error message when platform_device_add() fails to run. Fixes: 1a71fb84fda6 ("rtc: stmp3xxx: add wdt-accessor function") Signed-off-by: Lin Yujun Reviewed-by: Wolfram Sang Link: https://lore.kernel.org/r/20220915065253.43668-1-linyujun809@huawei.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-stmp3xxx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c index 40c0f7ed36e0..aae40d20d086 100644 --- a/drivers/rtc/rtc-stmp3xxx.c +++ b/drivers/rtc/rtc-stmp3xxx.c @@ -107,6 +107,8 @@ static void stmp3xxx_wdt_register(struct platform_device *rtc_pdev) wdt_pdev->dev.parent = &rtc_pdev->dev; wdt_pdev->dev.platform_data = &wdt_pdata; rc = platform_device_add(wdt_pdev); + if (rc) + platform_device_put(wdt_pdev); } if (rc) -- cgit From a35a2ad2b88a66732ac442ad5f86dc49af51673f Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 21 Sep 2022 13:46:16 +0200 Subject: rtc: isl12022: stop using deprecated devm_rtc_device_register() The comments say that devm_rtc_device_register() is deprecated and that one should instead use devm_rtc_allocate_device() and [devm_]rtc_register_device. So do that. Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20220921114624.3250848-2-linux@rasmusvillemoes.dk Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-isl12022.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 79461ded1a48..2dc19061cf5f 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -246,10 +246,13 @@ static int isl12022_probe(struct i2c_client *client) i2c_set_clientdata(client, isl12022); - isl12022->rtc = devm_rtc_device_register(&client->dev, - isl12022_driver.driver.name, - &isl12022_rtc_ops, THIS_MODULE); - return PTR_ERR_OR_ZERO(isl12022->rtc); + isl12022->rtc = devm_rtc_allocate_device(&client->dev); + if (IS_ERR(isl12022->rtc)) + return PTR_ERR(isl12022->rtc); + + isl12022->rtc->ops = &isl12022_rtc_ops; + + return devm_rtc_register_device(isl12022->rtc); } #ifdef CONFIG_OF -- cgit From ca03b7a2c0b098321365f69538823d1bcc860552 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 21 Sep 2022 13:46:17 +0200 Subject: rtc: isl12022: specify range_min and range_max The isl12022 can (only) keep track of times in the range 2000-2099. The data sheet says The calendar registers track date, month, year, and day of the week and are accurate through 2099, with automatic leap year correction. The lower bound of 2000 is obtained by simply observing that its YR register only counts from 00 through 99. Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20220921114624.3250848-3-linux@rasmusvillemoes.dk Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-isl12022.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 2dc19061cf5f..3bc197f5548f 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -251,6 +251,8 @@ static int isl12022_probe(struct i2c_client *client) return PTR_ERR(isl12022->rtc); isl12022->rtc->ops = &isl12022_rtc_ops; + isl12022->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; + isl12022->rtc->range_max = RTC_TIMESTAMP_END_2099; return devm_rtc_register_device(isl12022->rtc); } -- cgit From 43a96b9cf67770d4bb46267e1554d3d8b4cf78ac Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 21 Sep 2022 13:46:18 +0200 Subject: rtc: isl12022: drop a dev_info() This dev_info() seems to be a debug leftover, and it would only get printed once (or, once per battery change). Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20220921114624.3250848-4-linux@rasmusvillemoes.dk Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-isl12022.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 3bc197f5548f..2fc9fbefc6fc 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -173,9 +173,6 @@ static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm) /* Check if WRTC (write rtc enable) is set factory default is * 0 (not set) */ if (!(buf[0] & ISL12022_INT_WRTC)) { - dev_info(&client->dev, - "init write enable and 24 hour format\n"); - /* Set the write enable bit. */ ret = isl12022_write_reg(client, ISL12022_REG_INT, -- cgit From ca35887186b7c53f26c42aee1285ba213adb4365 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 21 Sep 2022 13:46:19 +0200 Subject: rtc: isl12022: simplify some expressions These instances of '&client->dev' might as well be spelled 'dev', since 'client' has been computed from 'dev' via 'client = to_i2c_client(dev)'. Later patches will get rid of that local variable 'client', so remove these unnecessary references so those later patches become easier to read. Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20220921114624.3250848-5-linux@rasmusvillemoes.dk Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-isl12022.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 2fc9fbefc6fc..7efe23fa74df 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -112,13 +112,13 @@ static int isl12022_rtc_read_time(struct device *dev, struct rtc_time *tm) return ret; if (buf[ISL12022_REG_SR] & (ISL12022_SR_LBAT85 | ISL12022_SR_LBAT75)) { - dev_warn(&client->dev, + dev_warn(dev, "voltage dropped below %u%%, " "date and time is not reliable.\n", buf[ISL12022_REG_SR] & ISL12022_SR_LBAT85 ? 85 : 75); } - dev_dbg(&client->dev, + dev_dbg(dev, "%s: raw data is sec=%02x, min=%02x, hr=%02x, " "mday=%02x, mon=%02x, year=%02x, wday=%02x, " "sr=%02x, int=%02x", @@ -141,7 +141,7 @@ static int isl12022_rtc_read_time(struct device *dev, struct rtc_time *tm) tm->tm_mon = bcd2bin(buf[ISL12022_REG_MO] & 0x1F) - 1; tm->tm_year = bcd2bin(buf[ISL12022_REG_YR]) + 100; - dev_dbg(&client->dev, "%s: secs=%d, mins=%d, hours=%d, " + dev_dbg(dev, "%s: secs=%d, mins=%d, hours=%d, " "mday=%d, mon=%d, year=%d, wday=%d\n", __func__, tm->tm_sec, tm->tm_min, tm->tm_hour, @@ -158,7 +158,7 @@ static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm) int ret; uint8_t buf[ISL12022_REG_DW + 1]; - dev_dbg(&client->dev, "%s: secs=%d, mins=%d, hours=%d, " + dev_dbg(dev, "%s: secs=%d, mins=%d, hours=%d, " "mday=%d, mon=%d, year=%d, wday=%d\n", __func__, tm->tm_sec, tm->tm_min, tm->tm_hour, -- cgit From 7093b8a471f48d49891da2108f44fd64742408cb Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 21 Sep 2022 13:46:20 +0200 Subject: rtc: isl12022: use %ptR Simplify the code and make the output format consistent with other RTC drivers by standardizing on using the %ptR printf extension. Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20220921114624.3250848-6-linux@rasmusvillemoes.dk Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-isl12022.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 7efe23fa74df..d396d6076db5 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -141,11 +141,7 @@ static int isl12022_rtc_read_time(struct device *dev, struct rtc_time *tm) tm->tm_mon = bcd2bin(buf[ISL12022_REG_MO] & 0x1F) - 1; tm->tm_year = bcd2bin(buf[ISL12022_REG_YR]) + 100; - dev_dbg(dev, "%s: secs=%d, mins=%d, hours=%d, " - "mday=%d, mon=%d, year=%d, wday=%d\n", - __func__, - tm->tm_sec, tm->tm_min, tm->tm_hour, - tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday); + dev_dbg(dev, "%s: %ptR\n", __func__, tm); return 0; } @@ -158,11 +154,7 @@ static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm) int ret; uint8_t buf[ISL12022_REG_DW + 1]; - dev_dbg(dev, "%s: secs=%d, mins=%d, hours=%d, " - "mday=%d, mon=%d, year=%d, wday=%d\n", - __func__, - tm->tm_sec, tm->tm_min, tm->tm_hour, - tm->tm_mday, tm->tm_mon, tm->tm_year, tm->tm_wday); + dev_dbg(dev, "%s: %ptR\n", __func__, tm); if (!isl12022->write_enabled) { -- cgit From 31b108acc50cddf3d16472ead45c4cd0d1337289 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 21 Sep 2022 13:46:21 +0200 Subject: rtc: isl12022: use dev_set_drvdata() instead of i2c_set_clientdata() As another preparation for removing direct references to the i2c_client in the helper functions, stash a pointer to the private data via dev_set_drvdata() instead of i2c_set_clientdata(). Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20220921114624.3250848-7-linux@rasmusvillemoes.dk Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-isl12022.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index d396d6076db5..df6d91f4e8f3 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -149,7 +149,7 @@ static int isl12022_rtc_read_time(struct device *dev, struct rtc_time *tm) static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm) { struct i2c_client *client = to_i2c_client(dev); - struct isl12022 *isl12022 = i2c_get_clientdata(client); + struct isl12022 *isl12022 = dev_get_drvdata(dev); size_t i; int ret; uint8_t buf[ISL12022_REG_DW + 1]; @@ -232,8 +232,7 @@ static int isl12022_probe(struct i2c_client *client) GFP_KERNEL); if (!isl12022) return -ENOMEM; - - i2c_set_clientdata(client, isl12022); + dev_set_drvdata(&client->dev, isl12022); isl12022->rtc = devm_rtc_allocate_device(&client->dev); if (IS_ERR(isl12022->rtc)) -- cgit From 0a2abbfd8586d396a8581ebf9b96fd5746f08b14 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 21 Sep 2022 13:46:22 +0200 Subject: rtc: isl12022: drop redundant write to HR register There's nothing in the data sheet that says writing to one of the time keeping registers is necessary to start the RTC. It does so at the stop condition of the i2c transfer setting the WRTC bit: Upon initialization or power-up, the WRTC must be set to "1" to enable the RTC. Upon the completion of a valid write (STOP), the RTC starts counting. Moreover, even if such a write to one of the timekeeping registers was necessary, that's exactly what we do anyway just below when we actually write the given struct rtc_time to the device. Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20220921114624.3250848-8-linux@rasmusvillemoes.dk Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-isl12022.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index df6d91f4e8f3..6fb13a5d17f1 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -171,20 +171,6 @@ static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm) buf[0] | ISL12022_INT_WRTC); if (ret) return ret; - - /* Write to any RTC register to start RTC, we use the - * HR register, setting the MIL bit to use the 24 hour - * format. */ - ret = isl12022_read_regs(client, ISL12022_REG_HR, - buf, 1); - if (ret) - return ret; - - ret = isl12022_write_reg(client, - ISL12022_REG_HR, - buf[0] | ISL12022_HR_MIL); - if (ret) - return ret; } isl12022->write_enabled = true; -- cgit From b1a1baa657c738e8bb0107ce304f5e78b9847f37 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 21 Sep 2022 13:46:23 +0200 Subject: rtc: isl12022: switch to using regmap API The regmap abstraction allows us to avoid the private i2c transfer helpers, and also offers some nice utility functions such as the regmap_update_bits family. While at it, simplify the code even more by not keeping track of ->write_enabled: rtc_set_time is not a hot path, so one extra i2c read doesn't hurt (regmap_update_bits elides the write when the bits are already as desired). Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20220921114624.3250848-9-linux@rasmusvillemoes.dk Signed-off-by: Alexandre Belloni --- drivers/rtc/Kconfig | 1 + drivers/rtc/rtc-isl12022.c | 110 +++++++++++---------------------------------- 2 files changed, 26 insertions(+), 85 deletions(-) diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index b8de25118ad0..bb63edb507da 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -423,6 +423,7 @@ config RTC_DRV_ISL1208 config RTC_DRV_ISL12022 tristate "Intersil ISL12022" + select REGMAP_I2C help If you say yes here you get support for the Intersil ISL12022 RTC chip. diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 6fb13a5d17f1..ca677c4265e6 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -16,6 +16,7 @@ #include #include #include +#include /* ISL register offsets */ #define ISL12022_REG_SC 0x00 @@ -42,72 +43,21 @@ static struct i2c_driver isl12022_driver; struct isl12022 { struct rtc_device *rtc; - - bool write_enabled; /* true if write enable is set */ + struct regmap *regmap; }; - -static int isl12022_read_regs(struct i2c_client *client, uint8_t reg, - uint8_t *data, size_t n) -{ - struct i2c_msg msgs[] = { - { - .addr = client->addr, - .flags = 0, - .len = 1, - .buf = data - }, /* setup read ptr */ - { - .addr = client->addr, - .flags = I2C_M_RD, - .len = n, - .buf = data - } - }; - - int ret; - - data[0] = reg; - ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); - if (ret != ARRAY_SIZE(msgs)) { - dev_err(&client->dev, "%s: read error, ret=%d\n", - __func__, ret); - return -EIO; - } - - return 0; -} - - -static int isl12022_write_reg(struct i2c_client *client, - uint8_t reg, uint8_t val) -{ - uint8_t data[2] = { reg, val }; - int err; - - err = i2c_master_send(client, data, sizeof(data)); - if (err != sizeof(data)) { - dev_err(&client->dev, - "%s: err=%d addr=%02x, data=%02x\n", - __func__, err, data[0], data[1]); - return -EIO; - } - - return 0; -} - - /* * In the routines that deal directly with the isl12022 hardware, we use * rtc_time -- month 0-11, hour 0-23, yr = calendar year-epoch. */ static int isl12022_rtc_read_time(struct device *dev, struct rtc_time *tm) { - struct i2c_client *client = to_i2c_client(dev); + struct isl12022 *isl12022 = dev_get_drvdata(dev); + struct regmap *regmap = isl12022->regmap; uint8_t buf[ISL12022_REG_INT + 1]; int ret; - ret = isl12022_read_regs(client, ISL12022_REG_SC, buf, sizeof(buf)); + ret = regmap_bulk_read(regmap, ISL12022_REG_SC, buf, sizeof(buf)); if (ret) return ret; @@ -148,33 +98,18 @@ static int isl12022_rtc_read_time(struct device *dev, struct rtc_time *tm) static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm) { - struct i2c_client *client = to_i2c_client(dev); struct isl12022 *isl12022 = dev_get_drvdata(dev); - size_t i; + struct regmap *regmap = isl12022->regmap; int ret; uint8_t buf[ISL12022_REG_DW + 1]; dev_dbg(dev, "%s: %ptR\n", __func__, tm); - if (!isl12022->write_enabled) { - - ret = isl12022_read_regs(client, ISL12022_REG_INT, buf, 1); - if (ret) - return ret; - - /* Check if WRTC (write rtc enable) is set factory default is - * 0 (not set) */ - if (!(buf[0] & ISL12022_INT_WRTC)) { - /* Set the write enable bit. */ - ret = isl12022_write_reg(client, - ISL12022_REG_INT, - buf[0] | ISL12022_INT_WRTC); - if (ret) - return ret; - } - - isl12022->write_enabled = true; - } + /* Ensure the write enable bit is set. */ + ret = regmap_update_bits(regmap, ISL12022_REG_INT, + ISL12022_INT_WRTC, ISL12022_INT_WRTC); + if (ret) + return ret; /* hours, minutes and seconds */ buf[ISL12022_REG_SC] = bin2bcd(tm->tm_sec); @@ -191,15 +126,8 @@ static int isl12022_rtc_set_time(struct device *dev, struct rtc_time *tm) buf[ISL12022_REG_DW] = tm->tm_wday & 0x07; - /* write register's data */ - for (i = 0; i < ARRAY_SIZE(buf); i++) { - ret = isl12022_write_reg(client, ISL12022_REG_SC + i, - buf[ISL12022_REG_SC + i]); - if (ret) - return -EIO; - } - - return 0; + return regmap_bulk_write(isl12022->regmap, ISL12022_REG_SC, + buf, sizeof(buf)); } static const struct rtc_class_ops isl12022_rtc_ops = { @@ -207,6 +135,12 @@ static const struct rtc_class_ops isl12022_rtc_ops = { .set_time = isl12022_rtc_set_time, }; +static const struct regmap_config regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .use_single_write = true, +}; + static int isl12022_probe(struct i2c_client *client) { struct isl12022 *isl12022; @@ -220,6 +154,12 @@ static int isl12022_probe(struct i2c_client *client) return -ENOMEM; dev_set_drvdata(&client->dev, isl12022); + isl12022->regmap = devm_regmap_init_i2c(client, ®map_config); + if (IS_ERR(isl12022->regmap)) { + dev_err(&client->dev, "regmap allocation failed\n"); + return PTR_ERR(isl12022->regmap); + } + isl12022->rtc = devm_rtc_allocate_device(&client->dev); if (IS_ERR(isl12022->rtc)) return PTR_ERR(isl12022->rtc); -- cgit From d73d66c0e05741b35b7398e647b8c4f2aaea9b09 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 3 Oct 2022 16:37:11 +0100 Subject: rtc: ds1685: Fix spelling of function name in comment block The function name is missing the letter 'd' in the comment block. Fix it. Signed-off-by: Colin Ian King Acked-by: Joshua Kinard Link: https://lore.kernel.org/r/20221003153711.271630-1-colin.i.king@gmail.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1685.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index a24331ba8a5f..5db9c737c022 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -132,7 +132,7 @@ ds1685_rtc_bin2bcd(struct ds1685_priv *rtc, u8 val, u8 bin_mask, u8 bcd_mask) } /** - * s1685_rtc_check_mday - check validity of the day of month. + * ds1685_rtc_check_mday - check validity of the day of month. * @rtc: pointer to the ds1685 rtc structure. * @mday: day of month. * -- cgit From 0091bfc81741b8d3aeb3b7ab8636f911b2de6e80 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 3 Oct 2022 13:59:47 +0100 Subject: io_uring/af_unix: defer registered files gc to io_uring release Instead of putting io_uring's registered files in unix_gc() we want it to be done by io_uring itself. The trick here is to consider io_uring registered files for cycle detection but not actually putting them down. Because io_uring can't register other ring instances, this will remove all refs to the ring file triggering the ->release path and clean up with io_ring_ctx_free(). Cc: stable@vger.kernel.org Fixes: 6b06314c47e1 ("io_uring: add file set registration") Reported-and-tested-by: David Bouman Signed-off-by: Pavel Begunkov Signed-off-by: Thadeu Lima de Souza Cascardo [axboe: add kerneldoc comment to skb, fold in skb leak fix] Signed-off-by: Jens Axboe --- include/linux/skbuff.h | 2 ++ io_uring/rsrc.c | 1 + net/unix/garbage.c | 20 ++++++++++++++++++++ 3 files changed, 23 insertions(+) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9fcf534f2d92..7be5bb4c94b6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -803,6 +803,7 @@ typedef unsigned char *sk_buff_data_t; * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) + * @scm_io_uring: SKB holds io_uring registered files * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required @@ -982,6 +983,7 @@ struct sk_buff { #endif __u8 slow_gro:1; __u8 csum_not_inet:1; + __u8 scm_io_uring:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 6f88ded0e7e5..012fdb04ec23 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -855,6 +855,7 @@ int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file) UNIXCB(skb).fp = fpl; skb->sk = sk; + skb->scm_io_uring = 1; skb->destructor = unix_destruct_scm; refcount_add(skb->truesize, &sk->sk_wmem_alloc); } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index d45d5366115a..dc2763540393 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -204,6 +204,7 @@ void wait_for_unix_gc(void) /* The external entry point: unix_gc() */ void unix_gc(void) { + struct sk_buff *next_skb, *skb; struct unix_sock *u; struct unix_sock *next; struct sk_buff_head hitlist; @@ -297,11 +298,30 @@ void unix_gc(void) spin_unlock(&unix_gc_lock); + /* We need io_uring to clean its registered files, ignore all io_uring + * originated skbs. It's fine as io_uring doesn't keep references to + * other io_uring instances and so killing all other files in the cycle + * will put all io_uring references forcing it to go through normal + * release.path eventually putting registered files. + */ + skb_queue_walk_safe(&hitlist, skb, next_skb) { + if (skb->scm_io_uring) { + __skb_unlink(skb, &hitlist); + skb_queue_tail(&skb->sk->sk_receive_queue, skb); + } + } + /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist); spin_lock(&unix_gc_lock); + /* There could be io_uring registered files, just push them back to + * the inflight list + */ + list_for_each_entry_safe(u, next, &gc_candidates, link) + list_move_tail(&u->link, &gc_inflight_list); + /* All candidates should have been detached by now. */ BUG_ON(!list_empty(&gc_candidates)); -- cgit From 42b6419d0aba47c5d8644cdc0b68502254671de5 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 4 Oct 2022 03:19:08 +0100 Subject: io_uring: correct pinned_vm accounting ->mm_account should be released only after we free all registered buffers, otherwise __io_sqe_buffers_unregister() will see a NULL ->mm_account and skip locked_vm accounting. Cc: Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/6d798f65ed4ab8db3664c4d3397d4af16ca98846.1664849932.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 63f6ce5e5355..ea5cee593bbd 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2585,12 +2585,6 @@ static void io_req_caches_free(struct io_ring_ctx *ctx) static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) { io_sq_thread_finish(ctx); - - if (ctx->mm_account) { - mmdrop(ctx->mm_account); - ctx->mm_account = NULL; - } - io_rsrc_refs_drop(ctx); /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ io_wait_rsrc_data(ctx->buf_data); @@ -2633,6 +2627,10 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); WARN_ON_ONCE(ctx->notif_slots || ctx->nr_notif_slots); + if (ctx->mm_account) { + mmdrop(ctx->mm_account); + ctx->mm_account = NULL; + } io_mem_free(ctx->rings); io_mem_free(ctx->sq_sqes); -- cgit From b7a817752efc850603c4c23ed78da2b990a6a34a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 4 Oct 2022 03:19:25 +0100 Subject: io_uring: remove notif leftovers Notifications were killed but there is a couple of fields and struct declarations left, remove them. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/8df8877d677be5a2b43afd936d600e60105ea960.1664849941.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 5 ----- io_uring/io_uring.c | 1 - 2 files changed, 6 deletions(-) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index aa4d90a53866..f5b687a787a3 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -34,9 +34,6 @@ struct io_file_table { unsigned int alloc_hint; }; -struct io_notif; -struct io_notif_slot; - struct io_hash_bucket { spinlock_t lock; struct hlist_head list; @@ -242,8 +239,6 @@ struct io_ring_ctx { unsigned nr_user_files; unsigned nr_user_bufs; struct io_mapped_ubuf **user_bufs; - struct io_notif_slot *notif_slots; - unsigned nr_notif_slots; struct io_submit_state submit_state; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ea5cee593bbd..b12ec6b5a464 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2625,7 +2625,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) } #endif WARN_ON_ONCE(!list_empty(&ctx->ltimeout_list)); - WARN_ON_ONCE(ctx->notif_slots || ctx->nr_notif_slots); if (ctx->mm_account) { mmdrop(ctx->mm_account); -- cgit From 3fb1bd68817288729179444caf1fd5c5c4d2d65d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 4 Oct 2022 20:29:48 -0600 Subject: io_uring/net: handle -EINPROGRESS correct for IORING_OP_CONNECT We treat EINPROGRESS like EAGAIN, but if we're retrying post getting EINPROGRESS, then we just need to check the socket for errors and terminate the request. This was exposed on a bluetooth connection request which ends up taking a while and hitting EINPROGRESS, and yields a CQE result of -EBADFD because we're retrying a connect on a socket that is now connected. Cc: stable@vger.kernel.org Fixes: 87f80d623c6c ("io_uring: handle connect -EINPROGRESS like -EAGAIN") Link: https://github.com/axboe/liburing/issues/671 Reported-by: Aidan Sun Signed-off-by: Jens Axboe --- io_uring/net.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/io_uring/net.c b/io_uring/net.c index caa6a803cb72..8c7226b5bf41 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -46,6 +46,7 @@ struct io_connect { struct file *file; struct sockaddr __user *addr; int addr_len; + bool in_progress; }; struct io_sr_msg { @@ -1386,6 +1387,7 @@ int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) conn->addr = u64_to_user_ptr(READ_ONCE(sqe->addr)); conn->addr_len = READ_ONCE(sqe->addr2); + conn->in_progress = false; return 0; } @@ -1397,6 +1399,16 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) int ret; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + if (connect->in_progress) { + struct socket *socket; + + ret = -ENOTSOCK; + socket = sock_from_file(req->file); + if (socket) + ret = sock_error(socket->sk); + goto out; + } + if (req_has_async_data(req)) { io = req->async_data; } else { @@ -1413,13 +1425,17 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) ret = __sys_connect_file(req->file, &io->address, connect->addr_len, file_flags); if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { - if (req_has_async_data(req)) - return -EAGAIN; - if (io_alloc_async_data(req)) { - ret = -ENOMEM; - goto out; + if (ret == -EINPROGRESS) { + connect->in_progress = true; + } else { + if (req_has_async_data(req)) + return -EAGAIN; + if (io_alloc_async_data(req)) { + ret = -ENOMEM; + goto out; + } + memcpy(req->async_data, &__io, sizeof(__io)); } - memcpy(req->async_data, &__io, sizeof(__io)); return -EAGAIN; } if (ret == -ERESTARTSYS) -- cgit From fc86f9d3bb4904117eea70347d323fde34a47c79 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 6 Oct 2022 02:06:10 +0100 Subject: io_uring: remove redundant memory barrier in io_req_local_work_add io_cqring_wake() needs a barrier for the waitqueue_active() check. However, in the case of io_req_local_work_add(), we call llist_add() first, which implies an atomic. Hence we can replace smb_mb() with smp_mb__after_atomic(). Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/43983bc8bc507172adda7a0f00cab1aff09fd238.1665018309.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 5 +++-- io_uring/io_uring.h | 11 +++++++++-- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index b12ec6b5a464..12870cd7cb07 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1106,6 +1106,8 @@ static void io_req_local_work_add(struct io_kiocb *req) if (!llist_add(&req->io_task_work.node, &ctx->work_llist)) return; + /* need it for the following io_cqring_wake() */ + smp_mb__after_atomic(); if (unlikely(atomic_read(&req->task->io_uring->in_idle))) { io_move_task_work_from_local(ctx); @@ -1117,8 +1119,7 @@ static void io_req_local_work_add(struct io_kiocb *req) if (ctx->has_evfd) io_eventfd_signal(ctx); - io_cqring_wake(ctx); - + __io_cqring_wake(ctx); } static inline void __io_req_task_work_add(struct io_kiocb *req, bool allow_local) diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 48ce2348c8c1..47d4cad1e9c4 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -203,17 +203,24 @@ static inline void io_commit_cqring(struct io_ring_ctx *ctx) smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); } -static inline void io_cqring_wake(struct io_ring_ctx *ctx) +/* requires smb_mb() prior, see wq_has_sleeper() */ +static inline void __io_cqring_wake(struct io_ring_ctx *ctx) { /* * wake_up_all() may seem excessive, but io_wake_function() and * io_should_wake() handle the termination of the loop and only * wake as many waiters as we need to. */ - if (wq_has_sleeper(&ctx->cq_wait)) + if (waitqueue_active(&ctx->cq_wait)) wake_up_all(&ctx->cq_wait); } +static inline void io_cqring_wake(struct io_ring_ctx *ctx) +{ + smp_mb(); + __io_cqring_wake(ctx); +} + static inline bool io_sqring_full(struct io_ring_ctx *ctx) { struct io_rings *r = ctx->rings; -- cgit From 44f87745d5f24a3cdf0548bf1d84fbb7316ce229 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 6 Oct 2022 21:42:33 +0100 Subject: io_uring: optimise locking for local tw with submit_wait Running local task_work requires taking uring_lock, for submit + wait we can try to run them right after submit while we still hold the lock and save one lock/unlokc pair. The optimisation was implemented in the first local tw patches but got dropped for simplicity. Suggested-by: Dylan Yudaken Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/281fc79d98b5d91fe4778c5137a17a2ab4693e5c.1665088876.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/io_uring.c | 12 ++++++++++-- io_uring/io_uring.h | 7 +++++++ 2 files changed, 17 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 12870cd7cb07..de08d9902b30 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -3227,8 +3227,16 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, mutex_unlock(&ctx->uring_lock); goto out; } - if ((flags & IORING_ENTER_GETEVENTS) && ctx->syscall_iopoll) - goto iopoll_locked; + if (flags & IORING_ENTER_GETEVENTS) { + if (ctx->syscall_iopoll) + goto iopoll_locked; + /* + * Ignore errors, we'll soon call io_cqring_wait() and + * it should handle ownership problems if any. + */ + if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) + (void)io_run_local_work_locked(ctx); + } mutex_unlock(&ctx->uring_lock); } diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 47d4cad1e9c4..ef77d2aa3172 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -275,6 +275,13 @@ static inline int io_run_task_work_ctx(struct io_ring_ctx *ctx) return ret; } +static inline int io_run_local_work_locked(struct io_ring_ctx *ctx) +{ + if (llist_empty(&ctx->work_llist)) + return 0; + return __io_run_local_work(ctx, true); +} + static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked) { if (!*locked) { -- cgit From 11528491c65a493050c682786c6b7cfd9e9b4a8f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 7 Oct 2022 12:26:02 -0600 Subject: io_uring/opdef: remove 'audit_skip' from SENDMSG_ZC The msg variants of sending aren't audited separately, so we should not be setting audit_skip for the zerocopy sendmsg variant either. Fixes: 493108d95f14 ("io_uring/net: zerocopy sendmsg") Reported-by: Paul Moore Reviewed-by: Paul Moore Signed-off-by: Jens Axboe --- io_uring/opdef.c | 1 - 1 file changed, 1 deletion(-) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 2330f6da791e..83dc0f9ad3b2 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -510,7 +510,6 @@ const struct io_op_def io_op_defs[] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, - .audit_skip = 1, .ioprio = 1, .manual_alloc = 1, #if defined(CONFIG_NET) -- cgit From c86416c6ff5ba7f7e5f3ff1dd8a9d1b3d0be827c Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Mon, 10 Oct 2022 16:43:30 -0700 Subject: io_uring: local variable rw shadows outer variable in io_write This fixes the shadowing of the outer variable rw in the function io_write(). No issue is caused by this, but let's silence the shadowing warning anyway. Reported-by: kernel test robot Signed-off-by: Stefan Roesch Link: https://lore.kernel.org/r/20221010234330.244244-1-shr@devkernel.io Signed-off-by: Jens Axboe --- io_uring/rw.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/io_uring/rw.c b/io_uring/rw.c index a25cd44cd415..453e0ae92160 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -916,7 +916,7 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) goto copy_iov; if (ret2 != req->cqe.res && ret2 >= 0 && need_complete_io(req)) { - struct io_async_rw *rw; + struct io_async_rw *io; trace_io_uring_short_write(req->ctx, kiocb->ki_pos - ret2, req->cqe.res, ret2); @@ -929,9 +929,9 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) iov_iter_save_state(&s->iter, &s->iter_state); ret = io_setup_async_rw(req, iovec, s, true); - rw = req->async_data; - if (rw) - rw->bytes_done += ret2; + io = req->async_data; + if (io) + io->bytes_done += ret2; if (kiocb->ki_flags & IOCB_WRITE) kiocb_end_write(req); -- cgit From 00927931cb630bbf8edb6d7f4dadb25139fc5e16 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 11 Oct 2022 01:59:57 +0100 Subject: io_uring: fix fdinfo sqe offsets calculation Only with the big sqe feature they take 128 bytes per entry, but we unconditionally advance by 128B. Fix it by using sq_shift. Fixes: 3b8fdd1dc35e3 ("io_uring/fdinfo: fix sqe dumping for IORING_SETUP_SQE128") Reported-and-tested-by: syzbot+e5198737e8a2d23d958c@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/8b41287cb75d5efb8fcb5cccde845ddbbadd8372.1665449983.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- io_uring/fdinfo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index 4eae088046d0..2e04850a657b 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -94,7 +94,7 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]); if (sq_idx > sq_mask) continue; - sqe = &ctx->sq_sqes[sq_idx << 1]; + sqe = &ctx->sq_sqes[sq_idx << sq_shift]; seq_printf(m, "%5u: opcode:%s, fd:%d, flags:%x, off:%llu, " "addr:0x%llx, rw_flags:0x%x, buf_index:%d " "user_data:%llu", -- cgit From 2ec33a6c3cca9fe2465e82050c81f5ffdc508b36 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Oct 2022 09:06:23 -0600 Subject: io_uring/rw: ensure kiocb_end_write() is always called A previous commit moved the notifications and end-write handling, but it is now missing a few spots where we also want to call both of those. Without that, we can potentially be missing file notifications, and more importantly, have an imbalance in the super_block writers sem accounting. Fixes: b000145e9907 ("io_uring/rw: defer fsnotify calls to task context") Reported-by: Dave Chinner Link: https://lore.kernel.org/all/20221010050319.GC2703033@dread.disaster.area/ Signed-off-by: Jens Axboe --- io_uring/rw.c | 38 +++++++++++++++++++++++++++++--------- 1 file changed, 29 insertions(+), 9 deletions(-) diff --git a/io_uring/rw.c b/io_uring/rw.c index 453e0ae92160..100de2626e47 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -234,11 +234,34 @@ static void kiocb_end_write(struct io_kiocb *req) } } +/* + * Trigger the notifications after having done some IO, and finish the write + * accounting, if any. + */ +static void io_req_io_end(struct io_kiocb *req) +{ + struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); + + WARN_ON(!in_task()); + + if (rw->kiocb.ki_flags & IOCB_WRITE) { + kiocb_end_write(req); + fsnotify_modify(req->file); + } else { + fsnotify_access(req->file); + } +} + static bool __io_complete_rw_common(struct io_kiocb *req, long res) { if (unlikely(res != req->cqe.res)) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { + /* + * Reissue will start accounting again, finish the + * current cycle. + */ + io_req_io_end(req); req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO; return true; } @@ -264,15 +287,7 @@ static inline int io_fixup_rw_res(struct io_kiocb *req, long res) static void io_req_rw_complete(struct io_kiocb *req, bool *locked) { - struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); - - if (rw->kiocb.ki_flags & IOCB_WRITE) { - kiocb_end_write(req); - fsnotify_modify(req->file); - } else { - fsnotify_access(req->file); - } - + io_req_io_end(req); io_req_task_complete(req, locked); } @@ -317,6 +332,11 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret, req->file->f_pos = rw->kiocb.ki_pos; if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) { if (!__io_complete_rw_common(req, ret)) { + /* + * Safe to call io_end from here as we're inline + * from the submission path. + */ + io_req_io_end(req); io_req_set_res(req, final_ret, io_put_kbuf(req, issue_flags)); return IOU_OK; -- cgit From 24fb316155a5f6ba278a8b110c60e67b79900356 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 24 Aug 2022 10:18:25 +0200 Subject: rtc: mpfs: Use devm_clk_get_enabled() helper The devm_clk_get_enabled() helper: - calls devm_clk_get() - calls clk_prepare_enable() and registers what is needed in order to call clk_disable_unprepare() when needed, as a managed resource. This simplifies the code, the error handling paths and avoid the need of a dedicated function used with devm_add_action_or_reset(). That said, mpfs_rtc_init_clk() is the same as devm_clk_get_enabled(), so use this function directly instead. This also fixes an (unlikely) unchecked devm_add_action_or_reset() error. Based on my test with allyesconfig, this reduces the .o size from: text data bss dec hex filename 5330 2208 0 7538 1d72 drivers/rtc/rtc-mpfs.o down to: 5074 2208 0 7282 1c72 drivers/rtc/rtc-mpfs.o Signed-off-by: Christophe JAILLET Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/e55c959f2821a2c367a4c5de529a638b1cc6b8cd.1661329086.git.christophe.jaillet@wanadoo.fr Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mpfs.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) diff --git a/drivers/rtc/rtc-mpfs.c b/drivers/rtc/rtc-mpfs.c index 944ad1036516..2a479d44f198 100644 --- a/drivers/rtc/rtc-mpfs.c +++ b/drivers/rtc/rtc-mpfs.c @@ -193,23 +193,6 @@ static int mpfs_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled) return 0; } -static inline struct clk *mpfs_rtc_init_clk(struct device *dev) -{ - struct clk *clk; - int ret; - - clk = devm_clk_get(dev, "rtc"); - if (IS_ERR(clk)) - return clk; - - ret = clk_prepare_enable(clk); - if (ret) - return ERR_PTR(ret); - - devm_add_action_or_reset(dev, (void (*) (void *))clk_disable_unprepare, clk); - return clk; -} - static irqreturn_t mpfs_rtc_wakeup_irq_handler(int irq, void *dev) { struct mpfs_rtc_dev *rtcdev = dev; @@ -251,7 +234,7 @@ static int mpfs_rtc_probe(struct platform_device *pdev) /* range is capped by alarm max, lower reg is 31:0 & upper is 10:0 */ rtcdev->rtc->range_max = GENMASK_ULL(42, 0); - clk = mpfs_rtc_init_clk(&pdev->dev); + clk = devm_clk_get_enabled(&pdev->dev, "rtc"); if (IS_ERR(clk)) return PTR_ERR(clk); -- cgit From 94e4603d1a262f8d79f6186d0df0379243613b95 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 24 Aug 2022 10:42:29 +0200 Subject: rtc: jz4740: Use devm_clk_get_enabled() helper The devm_clk_get_enabled() helper: - calls devm_clk_get() - calls clk_prepare_enable() and registers what is needed in order to call clk_disable_unprepare() when needed, as a managed resource. This simplifies the code, the error handling paths and avoid the need of a dedicated function used with devm_add_action_or_reset(). As a side effect, some error messages are not logged anymore, so also use dev_err_probe() instead of dev_err() in case of error. At least the error code will be logged (and -EPROBE_DEFER will be filtered) Based on my test with allyesconfig, this reduces the .o size from: text data bss dec hex filename 9025 2488 128 11641 2d79 drivers/rtc/rtc-jz4740.o down to: 8267 2080 128 10475 28eb drivers/rtc/rtc-jz4740.o Signed-off-by: Christophe JAILLET Acked-by: Paul Cercueil Link: https://lore.kernel.org/r/af10570000d7e103d70bbea590ce8df4f8902b67.1661330532.git.christophe.jaillet@wanadoo.fr Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-jz4740.c | 25 +++---------------------- 1 file changed, 3 insertions(+), 22 deletions(-) diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c index 6e51df72fd65..c383719292c7 100644 --- a/drivers/rtc/rtc-jz4740.c +++ b/drivers/rtc/rtc-jz4740.c @@ -257,11 +257,6 @@ static void jz4740_rtc_power_off(void) kernel_halt(); } -static void jz4740_rtc_clk_disable(void *data) -{ - clk_disable_unprepare(data); -} - static const struct of_device_id jz4740_rtc_of_match[] = { { .compatible = "ingenic,jz4740-rtc", .data = (void *)ID_JZ4740 }, { .compatible = "ingenic,jz4760-rtc", .data = (void *)ID_JZ4760 }, @@ -329,23 +324,9 @@ static int jz4740_rtc_probe(struct platform_device *pdev) if (IS_ERR(rtc->base)) return PTR_ERR(rtc->base); - clk = devm_clk_get(dev, "rtc"); - if (IS_ERR(clk)) { - dev_err(dev, "Failed to get RTC clock\n"); - return PTR_ERR(clk); - } - - ret = clk_prepare_enable(clk); - if (ret) { - dev_err(dev, "Failed to enable clock\n"); - return ret; - } - - ret = devm_add_action_or_reset(dev, jz4740_rtc_clk_disable, clk); - if (ret) { - dev_err(dev, "Failed to register devm action\n"); - return ret; - } + clk = devm_clk_get_enabled(dev, "rtc"); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "Failed to get RTC clock\n"); spin_lock_init(&rtc->lock); -- cgit From 8f08553e7e4370cdb8f55f0e3dc4db91ed6a4931 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 24 Aug 2022 10:25:11 +0200 Subject: rtc: k3: Use devm_clk_get_enabled() helper The devm_clk_get_enabled() helper: - calls devm_clk_get() - calls clk_prepare_enable() and registers what is needed in order to call clk_disable_unprepare() when needed, as a managed resource. This simplifies the code, the error handling paths and avoid the need of a dedicated function used with devm_add_action_or_reset(). Based on my test with allyesconfig, this reduces the .o size from: text data bss dec hex filename 12843 4804 64 17711 452f drivers/rtc/rtc-ti-k3.o down to: 12523 4804 64 17391 43ef drivers/rtc/rtc-ti-k3.o Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/601288834ab71c0fddde7eedd8cdb8001254ed7e.1661329498.git.christophe.jaillet@wanadoo.fr Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ti-k3.c | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/drivers/rtc/rtc-ti-k3.c b/drivers/rtc/rtc-ti-k3.c index 68e50c6a72f1..ba23163cc042 100644 --- a/drivers/rtc/rtc-ti-k3.c +++ b/drivers/rtc/rtc-ti-k3.c @@ -515,21 +515,12 @@ static struct nvmem_config ti_k3_rtc_nvmem_config = { static int k3rtc_get_32kclk(struct device *dev, struct ti_k3_rtc *priv) { - int ret; struct clk *clk; - clk = devm_clk_get(dev, "osc32k"); + clk = devm_clk_get_enabled(dev, "osc32k"); if (IS_ERR(clk)) return PTR_ERR(clk); - ret = clk_prepare_enable(clk); - if (ret) - return ret; - - ret = devm_add_action_or_reset(dev, (void (*)(void *))clk_disable_unprepare, clk); - if (ret) - return ret; - priv->rate_32k = clk_get_rate(clk); /* Make sure we are exact 32k clock. Else, try to compensate delay */ @@ -544,24 +535,19 @@ static int k3rtc_get_32kclk(struct device *dev, struct ti_k3_rtc *priv) */ priv->sync_timeout_us = (u32)(DIV_ROUND_UP_ULL(1000000, priv->rate_32k) * 4); - return ret; + return 0; } static int k3rtc_get_vbusclk(struct device *dev, struct ti_k3_rtc *priv) { - int ret; struct clk *clk; /* Note: VBUS isn't a context clock, it is needed for hardware operation */ - clk = devm_clk_get(dev, "vbus"); + clk = devm_clk_get_enabled(dev, "vbus"); if (IS_ERR(clk)) return PTR_ERR(clk); - ret = clk_prepare_enable(clk); - if (ret) - return ret; - - return devm_add_action_or_reset(dev, (void (*)(void *))clk_disable_unprepare, clk); + return 0; } static int ti_k3_rtc_probe(struct platform_device *pdev) -- cgit From acfac37851e01b40c30a7afd0d93ad8db8914f25 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 7 Oct 2022 12:59:20 -0700 Subject: mm/hugetlb.c: make __hugetlb_vma_unlock_write_put() static Reported-by: kernel test robot Cc: Mike Kravetz Signed-off-by: Andrew Morton --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0ad53ad98e74..41d3aa077837 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6804,7 +6804,7 @@ void hugetlb_vma_lock_release(struct kref *kref) kfree(vma_lock); } -void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) +static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) { struct vm_area_struct *vma = vma_lock->vma; -- cgit From 7efc3b7261030da79001c00d92bc3392fd6c664c Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 13 Jul 2022 14:20:09 +0800 Subject: mm/compaction: fix set skip in fast_find_migrateblock When we successfully find a pageblock in fast_find_migrateblock(), the block will be set skip-flag through set_pageblock_skip(). However, when entering isolate_migratepages_block(), the whole pageblock will be skipped due to the branch 'if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages))'. Eventually we will goto isolate_abort and isolate nothing. That makes fast_find_migrateblock useless. In this patch, when we find a suitable pageblock in fast_find_migrateblock, we do noting but let isolate_migratepages_block to set skip flag to the pageblock after scan it. Normally, we would isolate some pages from the fast-find block. I use mmtest/thpscale-madvhugepage test it. Here is the result: baseline patch Amean fault-both-1 1331.66 ( 0.00%) 1261.04 * 5.30%* Amean fault-both-3 1383.95 ( 0.00%) 1191.69 * 13.89%* Amean fault-both-5 1568.13 ( 0.00%) 1445.20 * 7.84%* Amean fault-both-7 1819.62 ( 0.00%) 1555.13 * 14.54%* Amean fault-both-12 1106.96 ( 0.00%) 1149.43 * -3.84%* Amean fault-both-18 2196.93 ( 0.00%) 1875.77 * 14.62%* Amean fault-both-24 2642.69 ( 0.00%) 2671.21 * -1.08%* Amean fault-both-30 2901.89 ( 0.00%) 2857.32 * 1.54%* Amean fault-both-32 3747.00 ( 0.00%) 3479.23 * 7.15%* Link: https://lkml.kernel.org/r/20220713062009.597255-1-zhouchuyi@bytedance.com Fixes: 70b44595eafe9 ("mm, compaction: use free lists to quickly locate a migration source") Signed-off-by: zhouchuyi Cc: Mel Gorman Signed-off-by: Andrew Morton --- mm/compaction.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/compaction.c b/mm/compaction.c index e2a9615f5fde..c4e4453187a2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1851,7 +1851,6 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) pfn = cc->zone->zone_start_pfn; cc->fast_search_fail = 0; found_block = true; - set_pageblock_skip(freepage); break; } } -- cgit From 92b7399695a5cc961c44fc6e4624d3bc3c699ee7 Mon Sep 17 00:00:00 2001 From: Liam Howlett Date: Tue, 11 Oct 2022 20:36:51 +0000 Subject: mmap: fix copy_vma() failure path The anon vma was not unlinked and the file was not closed in the failure path when the machine runs out of memory during the maple tree modification. This caused a memory leak of the anon vma chain and vma since neither would be freed. Link: https://lkml.kernel.org/r/20221011203621.1446507-1-Liam.Howlett@oracle.com Fixes: 524e00b36e8c ("mm: remove rb tree") Signed-off-by: Liam R. Howlett Reported-by: Lukas Bulwahn Tested-by: Lukas Bulwahn Signed-off-by: Andrew Morton --- mm/mmap.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/mm/mmap.c b/mm/mmap.c index 6e447544f07d..fc8581cefef7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3240,6 +3240,11 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, out_vma_link: if (new_vma->vm_ops && new_vma->vm_ops->close) new_vma->vm_ops->close(new_vma); + + if (new_vma->vm_file) + fput(new_vma->vm_file); + + unlink_anon_vmas(new_vma); out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: -- cgit From 7be1c1a3c7b13fb259bb5159662a7b83622013b8 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 11 Oct 2022 20:55:31 +0300 Subject: mm: more vma cache removal Link: https://lkml.kernel.org/r/Y0WuE3Riv4iy5Jx8@localhost.localdomain Fixes: 7964cf8caa4d ("mm: remove vmacache") Signed-off-by: Alexey Dobriyan Acked-by: Liam Howlett Signed-off-by: Andrew Morton --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 88a043f7235e..e0bb85cf8bdd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -861,8 +861,6 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; - /* Per-thread vma caching: */ - #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; #endif -- cgit From 28c5609fb236807910ca347ad3e26c4567998526 Mon Sep 17 00:00:00 2001 From: Liam Howlett Date: Tue, 11 Oct 2022 16:08:37 +0000 Subject: mm/mmap: preallocate maple nodes for brk vma expansion If the brk VMA is the last vma in a maple node and meets the rare criteria that it can be expanded, then preallocation is necessary to avoid a potential fs_reclaim circular lock issue on low resources. At the same time use the actual vma start address (unaligned) when calling vma_adjust_trans_huge(). Link: https://lkml.kernel.org/r/20221011160624.1253454-1-Liam.Howlett@oracle.com Fixes: 2e7ce7d354f2 (mm/mmap: change do_brk_flags() to expand existing VMA and add do_brk_munmap()) Signed-off-by: Liam R. Howlett Reported-by: Yu Zhao Signed-off-by: Andrew Morton --- mm/mmap.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index fc8581cefef7..5855f26639f9 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2942,17 +2942,18 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma, if (vma && (!vma->anon_vma || list_is_singular(&vma->anon_vma_chain)) && ((vma->vm_flags & ~VM_SOFTDIRTY) == flags)) { - mas->index = vma->vm_start; - mas->last = addr + len - 1; - vma_adjust_trans_huge(vma, addr, addr + len, 0); + mas_set_range(mas, vma->vm_start, addr + len - 1); + if (mas_preallocate(mas, vma, GFP_KERNEL)) + return -ENOMEM; + + vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); if (vma->anon_vma) { anon_vma_lock_write(vma->anon_vma); anon_vma_interval_tree_pre_update_vma(vma); } vma->vm_end = addr + len; vma->vm_flags |= VM_SOFTDIRTY; - if (mas_store_gfp(mas, vma, GFP_KERNEL)) - goto mas_expand_failed; + mas_store_prealloc(mas, vma); if (vma->anon_vma) { anon_vma_interval_tree_post_update_vma(vma); @@ -2993,13 +2994,6 @@ mas_store_fail: vma_alloc_fail: vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; - -mas_expand_failed: - if (vma->anon_vma) { - anon_vma_interval_tree_post_update_vma(vma); - anon_vma_unlock_write(vma->anon_vma); - } - return -ENOMEM; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) -- cgit From 515778e2d790652a38a24554fdb7f21420d91efc Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 30 Sep 2022 20:25:55 -0400 Subject: mm/uffd: fix warning without PTE_MARKER_UFFD_WP compiled in When PTE_MARKER_UFFD_WP not configured, it's still possible to reach pte marker code and trigger an warning. Add a few CONFIG_PTE_MARKER_UFFD_WP ifdefs to make sure the code won't be reached when not compiled in. Link: https://lkml.kernel.org/r/YzeR+R6b4bwBlBHh@x1n Fixes: b1f9e876862d ("mm/uffd: enable write protection for shmem & hugetlbfs") Signed-off-by: Peter Xu Reported-by: Cc: Axel Rasmussen Cc: Brian Geffon Cc: Edward Liaw Cc: Liu Shixin Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton --- mm/hugetlb.c | 4 ++++ mm/memory.c | 2 ++ mm/mprotect.c | 2 ++ 3 files changed, 8 insertions(+) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 41d3aa077837..9a910612336d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5096,6 +5096,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { +#ifdef CONFIG_PTE_MARKER_UFFD_WP /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to @@ -5107,6 +5108,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP)); else +#endif huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; @@ -5135,11 +5137,13 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); +#ifdef CONFIG_PTE_MARKER_UFFD_WP /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP)); +#endif hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, vma, true); diff --git a/mm/memory.c b/mm/memory.c index df678fa30cdb..2c7723ea4371 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1393,10 +1393,12 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, struct zap_details *details, pte_t pteval) { +#ifdef CONFIG_PTE_MARKER_UFFD_WP if (zap_drop_file_uffd_wp(details)) return; pte_install_uffd_wp_if_needed(vma, addr, pte, pteval); +#endif } static unsigned long zap_pte_range(struct mmu_gather *tlb, diff --git a/mm/mprotect.c b/mm/mprotect.c index 461dcbd4f21a..668bfaa6ed2a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -267,6 +267,7 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, } else { /* It must be an none page, or what else?.. */ WARN_ON_ONCE(!pte_none(oldpte)); +#ifdef CONFIG_PTE_MARKER_UFFD_WP if (unlikely(uffd_wp && !vma_is_anonymous(vma))) { /* * For file-backed mem, we need to be able to @@ -278,6 +279,7 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, make_pte_marker(PTE_MARKER_UFFD_WP)); pages++; } +#endif } } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); -- cgit From 826249942679a110353e71a1d92764fcf43e7cf7 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 23 Aug 2022 19:33:17 +0100 Subject: dt-bindings: timer: sifive,clint: add legacy riscv compatible While "real" hardware might not use the compatible string "riscv,clint0" it is present in the driver & QEMU uses it for automatically generated virt machine dtbs. To avoid dt-validate problems with QEMU produced dtbs, such as the following, add it to the binding. riscv-virt.dtb: clint@2000000: compatible:0: 'sifive,clint0' is not one of ['sifive,fu540-c000-clint', 'starfive,jh7100-clint', 'canaan,k210-clint'] Reported-by: Rob Herring Link: https://lore.kernel.org/linux-riscv/20220803170552.GA2250266-robh@kernel.org/ Reviewed-by: Rob Herring Signed-off-by: Conor Dooley Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220823183319.3314940-2-mail@conchuod.ie Signed-off-by: Palmer Dabbelt --- .../devicetree/bindings/timer/sifive,clint.yaml | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml index e64f46339079..bbad24165837 100644 --- a/Documentation/devicetree/bindings/timer/sifive,clint.yaml +++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml @@ -22,12 +22,18 @@ description: properties: compatible: - items: - - enum: - - sifive,fu540-c000-clint - - starfive,jh7100-clint - - canaan,k210-clint - - const: sifive,clint0 + oneOf: + - items: + - enum: + - sifive,fu540-c000-clint + - starfive,jh7100-clint + - canaan,k210-clint + - const: sifive,clint0 + - items: + - const: sifive,clint0 + - const: riscv,clint0 + deprecated: true + description: For the QEMU virt machine only description: Should be ",-clint" and "sifive,clint". -- cgit From 6e965c9bd7388762b302dca5852eb25cbe9cc085 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 23 Aug 2022 19:33:18 +0100 Subject: dt-bindings: interrupt-controller: sifive,plic: add legacy riscv compatible While "real" hardware might not use the compatible string "riscv,plic0" it is present in the driver & QEMU uses it for automatically generated virt machine dtbs. To avoid dt-validate problems with QEMU produced dtbs, such as the following, add it to the binding. riscv-virt.dtb: plic@c000000: compatible: 'oneOf' conditional failed, one must be fixed: 'sifive,plic-1.0.0' is not one of ['sifive,fu540-c000-plic', 'starfive,jh7100-plic', 'canaan,k210-plic'] 'sifive,plic-1.0.0' is not one of ['allwinner,sun20i-d1-plic'] 'sifive,plic-1.0.0' was expected 'thead,c900-plic' was expected riscv-virt.dtb: plic@c000000: '#address-cells' is a required property Reported-by: Rob Herring Link: https://lore.kernel.org/linux-riscv/20220803170552.GA2250266-robh@kernel.org/ Reviewed-by: Rob Herring Signed-off-by: Conor Dooley Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20220823183319.3314940-3-mail@conchuod.ie Signed-off-by: Palmer Dabbelt --- .../devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml index 92e0f8c3eff2..99e01f4d0a69 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml @@ -66,6 +66,11 @@ properties: - enum: - allwinner,sun20i-d1-plic - const: thead,c900-plic + - items: + - const: sifive,plic-1.0.0 + - const: riscv,plic0 + deprecated: true + description: For the QEMU virt machine only reg: maxItems: 1 -- cgit From 299824e68bd0fac60f8352c940fd731fde609de1 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 23 Aug 2022 19:33:19 +0100 Subject: dt-bindings: riscv: add new riscv,isa strings for emulators The QEMU virt and spike machines currently export a riscv,isa string of "rv64imafdcsuh", While the RISC-V foundation has been ratifying a bunch of extenstions etc, the kernel has remained relatively static with what hardware is supported - but the same is not true of QEMU. Using the virt machine and running dt-validate on the dumped dtb fails, partly due to the unexpected isa string. Rather than enumerate the many many possbilities, change the pattern to a regex, with the following assumptions: - ima are required - the single letter order is fixed & we don't care about things that can't even do "ima" - the standard multi letter extensions are all in a "_z" format where the first letter of is a valid single letter extension - _s & _h are used for supervisor and hyper visor extensions - convention says that after the first two chars, a standard multi letter extension name could be an english word (ifencei anyone?) so it's not worth restricting the charset - as the above is just convention, don't apply any charset restrictions to reduce future churn - vendor ISA extensions begind with _x and have no charset restrictions - we don't care about an e extension from an OS pov - that attempting to validate the contents of the multiletter extensions with dt-validate beyond the formatting is a futile, massively verbose or unwieldy exercise at best The following limitations also apply: - multi letter extension ordering is not enforced. dt-schema does not appear to allow for named match groups, so the resulting regex would be even more of a headache - ditto for the numbered extensions Finally, add me as a maintainer of the binding so that when it breaks in the future, I can be held responsible! Reported-by: Rob Herring Link: https://lore.kernel.org/linux-riscv/20220803170552.GA2250266-robh@kernel.org/ Reviewed-by: Andrew Jones Acked-by: Guo Ren Signed-off-by: Conor Dooley Acked-by: Heiko Stuebner Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20220823183319.3314940-4-mail@conchuod.ie Signed-off-by: Palmer Dabbelt --- Documentation/devicetree/bindings/riscv/cpus.yaml | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 873dd12f6e89..90a7cabf58fe 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -9,6 +9,7 @@ title: RISC-V bindings for 'cpus' DT nodes maintainers: - Paul Walmsley - Palmer Dabbelt + - Conor Dooley description: | This document uses some terminology common to the RISC-V community @@ -79,9 +80,7 @@ properties: insensitive, letters in the riscv,isa string must be all lowercase to simplify parsing. $ref: "/schemas/types.yaml#/definitions/string" - enum: - - rv64imac - - rv64imafdc + pattern: ^rv(?:64|32)imaf?d?q?c?b?v?k?h?(?:_[hsxz](?:[a-z])+)*$ # RISC-V requires 'timebase-frequency' in /cpus, so disallow it here timebase-frequency: false -- cgit From deb0f6562884b5b4beb883d73e66a7d3a1b96d99 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Fri, 30 Sep 2022 00:38:43 +0000 Subject: mm/mmap: undo ->mmap() when arch_validate_flags() fails Commit c462ac288f2c ("mm: Introduce arch_validate_flags()") added a late check in mmap_region() to let architectures validate vm_flags. The check needs to happen after calling ->mmap() as the flags can potentially be modified during this callback. If arch_validate_flags() check fails we unmap and free the vma. However, the error path fails to undo the ->mmap() call that previously succeeded and depending on the specific ->mmap() implementation this translates to reference increments, memory allocations and other operations what will not be cleaned up. There are several places (mainly device drivers) where this is an issue. However, one specific example is bpf_map_mmap() which keeps count of the mappings in map->writecnt. The count is incremented on ->mmap() and then decremented on vm_ops->close(). When arch_validate_flags() fails this count is off since bpf_map_mmap_close() is never called. One can reproduce this issue in arm64 devices with MTE support. Here the vm_flags are checked to only allow VM_MTE if VM_MTE_ALLOWED has been set previously. From userspace then is enough to pass the PROT_MTE flag to mmap() syscall to trigger the arch_validate_flags() failure. The following program reproduces this issue: #include #include #include #include #include int main(void) { union bpf_attr attr = { .map_type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(int), .value_size = sizeof(long long), .max_entries = 256, .map_flags = BPF_F_MMAPABLE, }; int fd; fd = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr)); mmap(NULL, 4096, PROT_WRITE | PROT_MTE, MAP_SHARED, fd, 0); return 0; } By manually adding some log statements to the vm_ops callbacks we can confirm that when passing PROT_MTE to mmap() the map->writecnt is off upon ->release(): With PROT_MTE flag: root@debian:~# ./bpf-test [ 111.263874] bpf_map_write_active_inc: map=9 writecnt=1 [ 111.288763] bpf_map_release: map=9 writecnt=1 Without PROT_MTE flag: root@debian:~# ./bpf-test [ 157.816912] bpf_map_write_active_inc: map=10 writecnt=1 [ 157.830442] bpf_map_write_active_dec: map=10 writecnt=0 [ 157.832396] bpf_map_release: map=10 writecnt=0 This patch fixes the above issue by calling vm_ops->close() when the arch_validate_flags() check fails, after this we can proceed to unmap and free the vma on the error path. Link: https://lkml.kernel.org/r/20220930003844.1210987-1-cmllamas@google.com Fixes: c462ac288f2c ("mm: Introduce arch_validate_flags()") Signed-off-by: Carlos Llamas Reviewed-by: Catalin Marinas Acked-by: Andrii Nakryiko Reviewed-by: Liam Howlett Cc: Christian Brauner (Microsoft) Cc: Michal Hocko Cc: Suren Baghdasaryan Cc: [5.10+] Signed-off-by: Andrew Morton --- mm/mmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/mmap.c b/mm/mmap.c index 5855f26639f9..bf2122af94e7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2673,7 +2673,7 @@ cannot_expand: if (!arch_validate_flags(vma->vm_flags)) { error = -EINVAL; if (file) - goto unmap_and_free_vma; + goto close_and_free_vma; else goto free_vma; } @@ -2742,6 +2742,9 @@ expanded: validate_mm(mm); return addr; +close_and_free_vma: + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); unmap_and_free_vma: fput(vma->vm_file); vma->vm_file = NULL; -- cgit From 4fa0e3ff217f775cb58d2d6d51820ec519243fb9 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 12 Oct 2022 20:34:19 +0100 Subject: ext4,f2fs: fix readahead of verity data The recent change of page_cache_ra_unbounded() arguments was buggy in the two callers, causing us to readahead the wrong pages. Move the definition of ractl down to after the index is set correctly. This affected performance on configurations that use fs-verity. Link: https://lkml.kernel.org/r/20221012193419.1453558-1-willy@infradead.org Fixes: 73bb49da50cd ("mm/readahead: make page_cache_ra_unbounded take a readahead_control") Signed-off-by: Matthew Wilcox (Oracle) Reported-by: Jintao Yin Signed-off-by: Andrew Morton --- fs/ext4/verity.c | 3 ++- fs/f2fs/verity.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index b051d19b5c8a..94442c690ca7 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -365,13 +365,14 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); struct page *page; index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT; page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c index 7b8f2b41c29b..c0733f867074 100644 --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -262,13 +262,14 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode, pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); struct page *page; index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT; page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) -- cgit From ac801e7e252c5588325e3c983c7d4167fc68c024 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Mon, 5 Sep 2022 14:24:27 +0200 Subject: kmsan: unpoison @tlb in arch_tlb_gather_mmu() This is an optimization to reduce stackdepot pressure. struct mmu_gather contains 7 1-bit fields packed into a 32-bit unsigned int value. The remaining 25 bits remain uninitialized and are never used, but KMSAN updates the origin for them in zap_pXX_range() in mm/memory.c, thus creating very long origin chains. This is technically correct, but consumes too much memory. Unpoisoning the whole structure will prevent creating such chains. Link: https://lkml.kernel.org/r/20220905122452.2258262-20-glider@google.com Signed-off-by: Alexander Potapenko Acked-by: Marco Elver Cc: Alexander Viro Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Konovalov Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Christoph Hellwig Cc: Christoph Lameter Cc: David Rientjes Cc: Dmitry Vyukov Cc: Eric Biggers Cc: Eric Dumazet Cc: Greg Kroah-Hartman Cc: Herbert Xu Cc: Ilya Leoshkevich Cc: Ingo Molnar Cc: Jens Axboe Cc: Joonsoo Kim Cc: Kees Cook Cc: Liu Shixin Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael S. Tsirkin Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Petr Mladek Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vegard Nossum Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/mmu_gather.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index a71924bd38c0..add4244e5790 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -1,6 +1,7 @@ #include #include #include +#include #include #include #include @@ -265,6 +266,15 @@ void tlb_flush_mmu(struct mmu_gather *tlb) static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) { + /* + * struct mmu_gather contains 7 1-bit fields packed into a 32-bit + * unsigned int value. The remaining 25 bits remain uninitialized + * and are never used, but KMSAN updates the origin for them in + * zap_pXX_range() in mm/memory.c, thus creating very long origin + * chains. This is technically correct, but consumes too much memory. + * Unpoisoning the whole structure will prevent creating such chains. + */ + kmsan_unpoison_memory(tlb, sizeof(*tlb)); tlb->mm = mm; tlb->fullmm = fullmm; -- cgit From ea091fa53680030881b56520d731e36d3ff6cdd5 Mon Sep 17 00:00:00 2001 From: Xiaoke Wang Date: Fri, 4 Mar 2022 17:12:15 +0800 Subject: lib/test_meminit: add checks for the allocation functions alloc_pages(), kmalloc() and vmalloc() are all memory allocation functions which can return NULL when some internal memory failures happen. So it is better to check the return of them to catch the failure in time for better test them. Link: https://lkml.kernel.org/r/tencent_D44A49FFB420EDCCBFB9221C8D14DFE12908@qq.com Signed-off-by: Xiaoke Wang Reviewed-by: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Marco Elver Signed-off-by: Andrew Morton --- lib/test_meminit.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/lib/test_meminit.c b/lib/test_meminit.c index c95db11a6906..60e1984c060f 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -67,17 +67,24 @@ static int __init do_alloc_pages_order(int order, int *total_failures) size_t size = PAGE_SIZE << order; page = alloc_pages(GFP_KERNEL, order); + if (!page) + goto err; buf = page_address(page); fill_with_garbage(buf, size); __free_pages(page, order); page = alloc_pages(GFP_KERNEL, order); + if (!page) + goto err; buf = page_address(page); if (count_nonzero_bytes(buf, size)) (*total_failures)++; fill_with_garbage(buf, size); __free_pages(page, order); return 1; +err: + (*total_failures)++; + return 1; } /* Test the page allocator by calling alloc_pages with different orders. */ @@ -100,15 +107,22 @@ static int __init do_kmalloc_size(size_t size, int *total_failures) void *buf; buf = kmalloc(size, GFP_KERNEL); + if (!buf) + goto err; fill_with_garbage(buf, size); kfree(buf); buf = kmalloc(size, GFP_KERNEL); + if (!buf) + goto err; if (count_nonzero_bytes(buf, size)) (*total_failures)++; fill_with_garbage(buf, size); kfree(buf); return 1; +err: + (*total_failures)++; + return 1; } /* Test vmalloc() with given parameters. */ @@ -117,15 +131,22 @@ static int __init do_vmalloc_size(size_t size, int *total_failures) void *buf; buf = vmalloc(size); + if (!buf) + goto err; fill_with_garbage(buf, size); vfree(buf); buf = vmalloc(size); + if (!buf) + goto err; if (count_nonzero_bytes(buf, size)) (*total_failures)++; fill_with_garbage(buf, size); vfree(buf); return 1; +err: + (*total_failures)++; + return 1; } /* Test kmalloc()/vmalloc() by allocating objects of different sizes. */ -- cgit From 652e04464d3944226052c827bdaaf5113b072870 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Tue, 27 Sep 2022 08:19:45 +0800 Subject: mm/damon: move sz_damon_region to damon_sz_region Rename sz_damon_region() to damon_sz_region(), and move it to "include/linux/damon.h", because in many places, we can to use this func. Link: https://lkml.kernel.org/r/20220927001946.85375-1-xhao@linux.alibaba.com Signed-off-by: Xin Hao Suggested-by: SeongJae Park Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/damon.h | 6 ++++++ mm/damon/core.c | 9 ++------- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/include/linux/damon.h b/include/linux/damon.h index ed5470f50bab..620ada094c3b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -484,6 +484,12 @@ static inline struct damon_region *damon_first_region(struct damon_target *t) return list_first_entry(&t->regions_list, struct damon_region, list); } +static inline unsigned long damon_sz_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} + + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) diff --git a/mm/damon/core.c b/mm/damon/core.c index 4de8c7c52979..5b9e0d585aef 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -864,18 +864,13 @@ static void kdamond_apply_schemes(struct damon_ctx *c) } } -static inline unsigned long sz_damon_region(struct damon_region *r) -{ - return r->ar.end - r->ar.start; -} - /* * Merge two adjacent regions into one region */ static void damon_merge_two_regions(struct damon_target *t, struct damon_region *l, struct damon_region *r) { - unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r); + unsigned long sz_l = damon_sz_region(l), sz_r = damon_sz_region(r); l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / (sz_l + sz_r); @@ -904,7 +899,7 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, if (prev && prev->ar.end == r->ar.start && abs(prev->nr_accesses - r->nr_accesses) <= thres && - sz_damon_region(prev) + sz_damon_region(r) <= sz_limit) + damon_sz_region(prev) + damon_sz_region(r) <= sz_limit) damon_merge_two_regions(t, prev, r); else prev = r; -- cgit From ab63f63f3885d492e62da55304b0483a2a9e6a7d Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Tue, 27 Sep 2022 08:19:46 +0800 Subject: mm/damon: use damon_sz_region() in appropriate place In many places we can use damon_sz_region() to instead of "r->ar.end - r->ar.start". Link: https://lkml.kernel.org/r/20220927001946.85375-2-xhao@linux.alibaba.com Signed-off-by: Xin Hao Suggested-by: SeongJae Park Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- mm/damon/core.c | 17 ++++++++--------- mm/damon/vaddr.c | 4 ++-- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/mm/damon/core.c b/mm/damon/core.c index 5b9e0d585aef..515ac4e52a11 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -490,7 +490,7 @@ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) damon_for_each_target(t, ctx) { damon_for_each_region(r, t) - sz += r->ar.end - r->ar.start; + sz += damon_sz_region(r); } if (ctx->attrs.min_nr_regions) @@ -673,7 +673,7 @@ static bool __damos_valid_target(struct damon_region *r, struct damos *s) { unsigned long sz; - sz = r->ar.end - r->ar.start; + sz = damon_sz_region(r); return s->pattern.min_sz_region <= sz && sz <= s->pattern.max_sz_region && s->pattern.min_nr_accesses <= r->nr_accesses && @@ -701,7 +701,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; - unsigned long sz = r->ar.end - r->ar.start; + unsigned long sz = damon_sz_region(r); struct timespec64 begin, end; unsigned long sz_applied = 0; @@ -730,14 +730,14 @@ static void damon_do_apply_schemes(struct damon_ctx *c, sz = ALIGN_DOWN(quota->charge_addr_from - r->ar.start, DAMON_MIN_REGION); if (!sz) { - if (r->ar.end - r->ar.start <= - DAMON_MIN_REGION) + if (damon_sz_region(r) <= + DAMON_MIN_REGION) continue; sz = DAMON_MIN_REGION; } damon_split_region_at(t, r, sz); r = damon_next_region(r); - sz = r->ar.end - r->ar.start; + sz = damon_sz_region(r); } quota->charge_target_from = NULL; quota->charge_addr_from = 0; @@ -842,8 +842,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c) continue; score = c->ops.get_scheme_score( c, t, r, s); - quota->histogram[score] += - r->ar.end - r->ar.start; + quota->histogram[score] += damon_sz_region(r); if (score > max_score) max_score = score; } @@ -957,7 +956,7 @@ static void damon_split_regions_of(struct damon_target *t, int nr_subs) int i; damon_for_each_region_safe(r, next, t) { - sz_region = r->ar.end - r->ar.start; + sz_region = damon_sz_region(r); for (i = 0; i < nr_subs - 1 && sz_region > 2 * DAMON_MIN_REGION; i++) { diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index ea94e0b2c311..15f03df66db6 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -72,7 +72,7 @@ static int damon_va_evenly_split_region(struct damon_target *t, return -EINVAL; orig_end = r->ar.end; - sz_orig = r->ar.end - r->ar.start; + sz_orig = damon_sz_region(r); sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION); if (!sz_piece) @@ -618,7 +618,7 @@ static unsigned long damos_madvise(struct damon_target *target, { struct mm_struct *mm; unsigned long start = PAGE_ALIGN(r->ar.start); - unsigned long len = PAGE_ALIGN(r->ar.end - r->ar.start); + unsigned long len = PAGE_ALIGN(damon_sz_region(r)); unsigned long applied; mm = damon_get_mm(target); -- cgit From 16ce101db85db694a91380aa4c89b25530871d33 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:15 +1000 Subject: mm/memory.c: fix race when faulting a device private page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Fix several device private page reference counting issues", v2 This series aims to fix a number of page reference counting issues in drivers dealing with device private ZONE_DEVICE pages. These result in use-after-free type bugs, either from accessing a struct page which no longer exists because it has been removed or accessing fields within the struct page which are no longer valid because the page has been freed. During normal usage it is unlikely these will cause any problems. However without these fixes it is possible to crash the kernel from userspace. These crashes can be triggered either by unloading the kernel module or unbinding the device from the driver prior to a userspace task exiting. In modules such as Nouveau it is also possible to trigger some of these issues by explicitly closing the device file-descriptor prior to the task exiting and then accessing device private memory. This involves some minor changes to both PowerPC and AMD GPU code. Unfortunately I lack hardware to test either of those so any help there would be appreciated. The changes mimic what is done in for both Nouveau and hmm-tests though so I doubt they will cause problems. This patch (of 8): When the CPU tries to access a device private page the migrate_to_ram() callback associated with the pgmap for the page is called. However no reference is taken on the faulting page. Therefore a concurrent migration of the device private page can free the page and possibly the underlying pgmap. This results in a race which can crash the kernel due to the migrate_to_ram() function pointer becoming invalid. It also means drivers can't reliably read the zone_device_data field because the page may have been freed with memunmap_pages(). Close the race by getting a reference on the page while holding the ptl to ensure it has not been freed. Unfortunately the elevated reference count will cause the migration required to handle the fault to fail. To avoid this failure pass the faulting page into the migrate_vma functions so that if an elevated reference count is found it can be checked to see if it's expected or not. [mpe@ellerman.id.au: fix build] Link: https://lkml.kernel.org/r/87fsgbf3gh.fsf@mpe.ellerman.id.au Link: https://lkml.kernel.org/r/cover.60659b549d8509ddecafad4f498ee7f03bb23c69.1664366292.git-series.apopple@nvidia.com Link: https://lkml.kernel.org/r/d3e813178a59e565e8d78d9b9a4e2562f6494f90.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Acked-by: Felix Kuehling Cc: Jason Gunthorpe Cc: John Hubbard Cc: Ralph Campbell Cc: Michael Ellerman Cc: Lyude Paul Cc: Alex Deucher Cc: Alex Sierra Cc: Ben Skeggs Cc: Christian König Cc: Dan Williams Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Matthew Wilcox Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/powerpc/kvm/book3s_hv_uvmem.c | 19 ++++++++++-------- drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 17 +++++++++------- drivers/gpu/drm/amd/amdkfd/kfd_migrate.h | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 11 +++++++---- include/linux/migrate.h | 8 ++++++++ lib/test_hmm.c | 7 ++++--- mm/memory.c | 16 ++++++++++++++- mm/migrate.c | 34 +++++++++++++++++++------------- mm/migrate_device.c | 18 ++++++++++++----- 9 files changed, 89 insertions(+), 43 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 598006301620..965c9e9e500b 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -508,10 +508,10 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) static int __kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long page_shift, - struct kvm *kvm, unsigned long gpa) + struct kvm *kvm, unsigned long gpa, struct page *fault_page) { unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma mig; + struct migrate_vma mig = { 0 }; struct page *dpage, *spage; struct kvmppc_uvmem_page_pvt *pvt; unsigned long pfn; @@ -525,6 +525,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma, mig.dst = &dst_pfn; mig.pgmap_owner = &kvmppc_uvmem_pgmap; mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; + mig.fault_page = fault_page; /* The requested page is already paged-out, nothing to do */ if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL)) @@ -580,12 +581,14 @@ out_finalize: static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long page_shift, - struct kvm *kvm, unsigned long gpa) + struct kvm *kvm, unsigned long gpa, + struct page *fault_page) { int ret; mutex_lock(&kvm->arch.uvmem_lock); - ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa); + ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa, + fault_page); mutex_unlock(&kvm->arch.uvmem_lock); return ret; @@ -634,7 +637,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, pvt->remove_gfn = true; if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE, - PAGE_SHIFT, kvm, pvt->gpa)) + PAGE_SHIFT, kvm, pvt->gpa, NULL)) pr_err("Can't page out gpa:0x%lx addr:0x%lx\n", pvt->gpa, addr); } else { @@ -736,7 +739,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, bool pagein) { unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma mig; + struct migrate_vma mig = { 0 }; struct page *spage; unsigned long pfn; struct page *dpage; @@ -994,7 +997,7 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf) if (kvmppc_svm_page_out(vmf->vma, vmf->address, vmf->address + PAGE_SIZE, PAGE_SHIFT, - pvt->kvm, pvt->gpa)) + pvt->kvm, pvt->gpa, vmf->page)) return VM_FAULT_SIGBUS; else return 0; @@ -1065,7 +1068,7 @@ kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa, if (!vma || vma->vm_start > start || vma->vm_end < end) goto out; - if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa)) + if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa, NULL)) ret = H_SUCCESS; out: mmap_read_unlock(kvm->mm); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index b059a77b6081..776448bd9fe4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -409,7 +409,7 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, uint64_t npages = (end - start) >> PAGE_SHIFT; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; - struct migrate_vma migrate; + struct migrate_vma migrate = { 0 }; unsigned long cpages = 0; dma_addr_t *scratch; void *buf; @@ -668,7 +668,7 @@ out_oom: static long svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, uint64_t end, - uint32_t trigger) + uint32_t trigger, struct page *fault_page) { struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms); uint64_t npages = (end - start) >> PAGE_SHIFT; @@ -676,7 +676,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, unsigned long cpages = 0; struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; - struct migrate_vma migrate; + struct migrate_vma migrate = { 0 }; dma_addr_t *scratch; void *buf; int r = -ENOMEM; @@ -699,6 +699,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, migrate.src = buf; migrate.dst = migrate.src + npages; + migrate.fault_page = fault_page; scratch = (dma_addr_t *)(migrate.dst + npages); kfd_smi_event_migration_start(adev->kfd.dev, p->lead_thread->pid, @@ -766,7 +767,7 @@ out: * 0 - OK, otherwise error code */ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, - uint32_t trigger) + uint32_t trigger, struct page *fault_page) { struct amdgpu_device *adev; struct vm_area_struct *vma; @@ -807,7 +808,8 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, } next = min(vma->vm_end, end); - r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger); + r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger, + fault_page); if (r < 0) { pr_debug("failed %ld to migrate prange %p\n", r, prange); break; @@ -851,7 +853,7 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc, pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc); do { - r = svm_migrate_vram_to_ram(prange, mm, trigger); + r = svm_migrate_vram_to_ram(prange, mm, trigger, NULL); if (r) return r; } while (prange->actual_loc && --retries); @@ -938,7 +940,8 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf) goto out_unlock_prange; } - r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU); + r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU, + vmf->page); if (r) pr_debug("failed %d migrate 0x%p [0x%lx 0x%lx] to ram\n", r, prange, prange->start, prange->last); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h index b3f0754b32fa..a5d7e6d22264 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.h @@ -43,7 +43,7 @@ enum MIGRATION_COPY_DIR { int svm_migrate_to_vram(struct svm_range *prange, uint32_t best_loc, struct mm_struct *mm, uint32_t trigger); int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm, - uint32_t trigger); + uint32_t trigger, struct page *fault_page); unsigned long svm_migrate_addr_to_pfn(struct amdgpu_device *adev, unsigned long addr); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 11074cc8c333..9139e5a0b2a0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -2913,13 +2913,15 @@ retry_write_locked: */ if (prange->actual_loc) r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + NULL); else r = 0; } } else { r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU); + KFD_MIGRATE_TRIGGER_PAGEFAULT_GPU, + NULL); } if (r) { pr_debug("failed %d to migrate svms %p [0x%lx 0x%lx]\n", @@ -3242,7 +3244,8 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, return 0; if (!best_loc) { - r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PREFETCH); + r = svm_migrate_vram_to_ram(prange, mm, + KFD_MIGRATE_TRIGGER_PREFETCH, NULL); *migrated = !r; return r; } @@ -3303,7 +3306,7 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work) mutex_lock(&prange->migrate_mutex); do { r = svm_migrate_vram_to_ram(prange, mm, - KFD_MIGRATE_TRIGGER_TTM_EVICTION); + KFD_MIGRATE_TRIGGER_TTM_EVICTION, NULL); } while (!r && prange->actual_loc && --retries); if (!r && prange->actual_loc) diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 704a04f5a074..52090d1f9230 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -62,6 +62,8 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free, @@ -197,6 +199,12 @@ struct migrate_vma { */ void *pgmap_owner; unsigned long flags; + + /* + * Set to vmf->page if this is being called to migrate a page as part of + * a migrate_to_ram() callback. + */ + struct page *fault_page; }; int migrate_vma_setup(struct migrate_vma *args); diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 6a33f6b1b465..e566166b5571 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -907,7 +907,7 @@ static int dmirror_migrate_to_system(struct dmirror *dmirror, struct vm_area_struct *vma; unsigned long src_pfns[64] = { 0 }; unsigned long dst_pfns[64] = { 0 }; - struct migrate_vma args; + struct migrate_vma args = { 0 }; unsigned long next; int ret; @@ -968,7 +968,7 @@ static int dmirror_migrate_to_device(struct dmirror *dmirror, unsigned long src_pfns[64] = { 0 }; unsigned long dst_pfns[64] = { 0 }; struct dmirror_bounce bounce; - struct migrate_vma args; + struct migrate_vma args = { 0 }; unsigned long next; int ret; @@ -1334,7 +1334,7 @@ static void dmirror_devmem_free(struct page *page) static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) { - struct migrate_vma args; + struct migrate_vma args = { 0 }; unsigned long src_pfns = 0; unsigned long dst_pfns = 0; struct page *rpage; @@ -1357,6 +1357,7 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf) args.dst = &dst_pfns; args.pgmap_owner = dmirror->mdevice; args.flags = dmirror_select_device(dmirror); + args.fault_page = vmf->page; if (migrate_vma_setup(&args)) return VM_FAULT_SIGBUS; diff --git a/mm/memory.c b/mm/memory.c index 2c7723ea4371..4ad6077164cd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3750,7 +3750,21 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) ret = remove_device_exclusive_entry(vmf); } else if (is_device_private_entry(entry)) { vmf->page = pfn_swap_entry_to_page(entry); - ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, + vmf->address, &vmf->ptl); + if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { + spin_unlock(vmf->ptl); + goto out; + } + + /* + * Get a page reference while we know the page can't be + * freed. + */ + get_page(vmf->page); + pte_unmap_unlock(vmf->pte, vmf->ptl); + vmf->page->pgmap->ops->migrate_to_ram(vmf); + put_page(vmf->page); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else if (is_swapin_error_entry(entry)) { diff --git a/mm/migrate.c b/mm/migrate.c index c228afba0963..1379e1912772 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -625,6 +625,25 @@ EXPORT_SYMBOL(folio_migrate_copy); * Migration functions ***********************************************************/ +int migrate_folio_extra(struct address_space *mapping, struct folio *dst, + struct folio *src, enum migrate_mode mode, int extra_count) +{ + int rc; + + BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */ + + rc = folio_migrate_mapping(mapping, dst, src, extra_count); + + if (rc != MIGRATEPAGE_SUCCESS) + return rc; + + if (mode != MIGRATE_SYNC_NO_COPY) + folio_migrate_copy(dst, src); + else + folio_migrate_flags(dst, src); + return MIGRATEPAGE_SUCCESS; +} + /** * migrate_folio() - Simple folio migration. * @mapping: The address_space containing the folio. @@ -640,20 +659,7 @@ EXPORT_SYMBOL(folio_migrate_copy); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { - int rc; - - BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */ - - rc = folio_migrate_mapping(mapping, dst, src, 0); - - if (rc != MIGRATEPAGE_SUCCESS) - return rc; - - if (mode != MIGRATE_SYNC_NO_COPY) - folio_migrate_copy(dst, src); - else - folio_migrate_flags(dst, src); - return MIGRATEPAGE_SUCCESS; + return migrate_folio_extra(mapping, dst, src, mode, 0); } EXPORT_SYMBOL(migrate_folio); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 5ab6ab9d2ed8..8dee38ffcda2 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -325,14 +325,14 @@ static void migrate_vma_collect(struct migrate_vma *migrate) * folio_migrate_mapping(), except that here we allow migration of a * ZONE_DEVICE page. */ -static bool migrate_vma_check_page(struct page *page) +static bool migrate_vma_check_page(struct page *page, struct page *fault_page) { /* * One extra ref because caller holds an extra reference, either from * isolate_lru_page() for a regular page, or migrate_vma_collect() for * a device page. */ - int extra = 1; + int extra = 1 + (page == fault_page); /* * FIXME support THP (transparent huge page), it is bit more complex to @@ -405,7 +405,8 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) if (folio_mapped(folio)) try_to_migrate(folio, 0); - if (page_mapped(page) || !migrate_vma_check_page(page)) { + if (page_mapped(page) || + !migrate_vma_check_page(page, migrate->fault_page)) { if (!is_zone_device_page(page)) { get_page(page); putback_lru_page(page); @@ -517,6 +518,8 @@ int migrate_vma_setup(struct migrate_vma *args) return -EINVAL; if (!args->src || !args->dst) return -EINVAL; + if (args->fault_page && !is_device_private_page(args->fault_page)) + return -EINVAL; memset(args->src, 0, sizeof(*args->src) * nr_pages); args->cpages = 0; @@ -747,8 +750,13 @@ void migrate_vma_pages(struct migrate_vma *migrate) continue; } - r = migrate_folio(mapping, page_folio(newpage), - page_folio(page), MIGRATE_SYNC_NO_COPY); + if (migrate->fault_page == page) + r = migrate_folio_extra(mapping, page_folio(newpage), + page_folio(page), + MIGRATE_SYNC_NO_COPY, 1); + else + r = migrate_folio(mapping, page_folio(newpage), + page_folio(page), MIGRATE_SYNC_NO_COPY); if (r != MIGRATEPAGE_SUCCESS) migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; } -- cgit From ef233450898f8893dafa193a9f3211fa077a3d05 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:16 +1000 Subject: mm: free device private pages have zero refcount MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since 27674ef6c73f ("mm: remove the extra ZONE_DEVICE struct page refcount") device private pages have no longer had an extra reference count when the page is in use. However before handing them back to the owning device driver we add an extra reference count such that free pages have a reference count of one. This makes it difficult to tell if a page is free or not because both free and in use pages will have a non-zero refcount. Instead we should return pages to the drivers page allocator with a zero reference count. Kernel code can then safely use kernel functions such as get_page_unless_zero(). Link: https://lkml.kernel.org/r/cf70cf6f8c0bdb8aaebdbfb0d790aea4c683c3c6.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Acked-by: Felix Kuehling Cc: Jason Gunthorpe Cc: Michael Ellerman Cc: Alex Deucher Cc: Christian König Cc: Ben Skeggs Cc: Lyude Paul Cc: Ralph Campbell Cc: Alex Sierra Cc: John Hubbard Cc: Dan Williams Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Matthew Wilcox Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- arch/powerpc/kvm/book3s_hv_uvmem.c | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 2 +- drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +- include/linux/memremap.h | 1 + lib/test_hmm.c | 2 +- mm/memremap.c | 9 +++++++++ mm/page_alloc.c | 8 ++++++++ 7 files changed, 22 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 965c9e9e500b..e2f11f9c3f2a 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -718,7 +718,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) dpage = pfn_to_page(uvmem_pfn); dpage->zone_device_data = pvt; - lock_page(dpage); + zone_device_page_init(dpage); return dpage; out_clear: spin_lock(&kvmppc_uvmem_bitmap_lock); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 776448bd9fe4..97a684568ae0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -223,7 +223,7 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn) page = pfn_to_page(pfn); svm_range_bo_ref(prange->svm_bo); page->zone_device_data = prange->svm_bo; - lock_page(page); + zone_device_page_init(page); } static void diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 16356611b5b9..b092988266a6 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -326,7 +326,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm) return NULL; } - lock_page(page); + zone_device_page_init(page); return page; } diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c3b4cc84877b..7fcaf3180a5b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -187,6 +187,7 @@ static inline bool folio_is_device_coherent(const struct folio *folio) } #ifdef CONFIG_ZONE_DEVICE +void zone_device_page_init(struct page *page); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); diff --git a/lib/test_hmm.c b/lib/test_hmm.c index e566166b5571..bc2b94991165 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -627,8 +627,8 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice) goto error; } + zone_device_page_init(dpage); dpage->zone_device_data = rpage; - lock_page(dpage); return dpage; error: diff --git a/mm/memremap.c b/mm/memremap.c index 25029a474d30..1c2c038f3410 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -505,8 +505,17 @@ void free_zone_device_page(struct page *page) /* * Reset the page count to 1 to prepare for handing out the page again. */ + if (page->pgmap->type != MEMORY_DEVICE_PRIVATE && + page->pgmap->type != MEMORY_DEVICE_COHERENT) + set_page_count(page, 1); +} + +void zone_device_page_init(struct page *page) +{ set_page_count(page, 1); + lock_page(page); } +EXPORT_SYMBOL_GPL(zone_device_page_init); #ifdef CONFIG_FS_DAX bool __put_devmap_managed_page_refs(struct page *page, int refs) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 12b6184cbbed..059f6946832f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6819,6 +6819,14 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, set_pageblock_migratetype(page, MIGRATE_MOVABLE); cond_resched(); } + + /* + * ZONE_DEVICE pages are released directly to the driver page allocator + * which will set the page count to 1 when allocating the page. + */ + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_COHERENT) + set_page_count(page, 0); } /* -- cgit From 0dc45ca1ce18900572282c4f054bbe78351cb6a7 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:17 +1000 Subject: mm/memremap.c: take a pgmap reference on page allocation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ZONE_DEVICE pages have a struct dev_pagemap which is allocated by a driver. When the struct page is first allocated by the kernel in memremap_pages() a reference is taken on the associated pagemap to ensure it is not freed prior to the pages being freed. Prior to 27674ef6c73f ("mm: remove the extra ZONE_DEVICE struct page refcount") pages were considered free and returned to the driver when the reference count dropped to one. However the pagemap reference was not dropped until the page reference count hit zero. This would occur as part of the final put_page() in memunmap_pages() which would wait for all pages to be freed prior to returning. When the extra refcount was removed the pagemap reference was no longer being dropped in put_page(). Instead memunmap_pages() was changed to explicitly drop the pagemap references. This means that memunmap_pages() can complete even though pages are still mapped by the kernel which can lead to kernel crashes, particularly if a driver frees the pagemap. To fix this drivers should take a pagemap reference when allocating the page. This reference can then be returned when the page is freed. Link: https://lkml.kernel.org/r/12d155ec727935ebfbb4d639a03ab374917ea51b.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Fixes: 27674ef6c73f ("mm: remove the extra ZONE_DEVICE struct page refcount") Cc: Jason Gunthorpe Cc: Felix Kuehling Cc: Alex Deucher Cc: Christian König Cc: Ben Skeggs Cc: Lyude Paul Cc: Ralph Campbell Cc: Alex Sierra Cc: John Hubbard Cc: Dan Williams Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- mm/memremap.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/mm/memremap.c b/mm/memremap.c index 1c2c038f3410..421bec3a29ee 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -138,8 +138,11 @@ void memunmap_pages(struct dev_pagemap *pgmap) int i; percpu_ref_kill(&pgmap->ref); - for (i = 0; i < pgmap->nr_range; i++) - percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i)); + if (pgmap->type != MEMORY_DEVICE_PRIVATE && + pgmap->type != MEMORY_DEVICE_COHERENT) + for (i = 0; i < pgmap->nr_range; i++) + percpu_ref_put_many(&pgmap->ref, pfn_len(pgmap, i)); + wait_for_completion(&pgmap->done); for (i = 0; i < pgmap->nr_range; i++) @@ -264,7 +267,9 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], PHYS_PFN(range->start), PHYS_PFN(range_len(range)), pgmap); - percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id)); + if (pgmap->type != MEMORY_DEVICE_PRIVATE && + pgmap->type != MEMORY_DEVICE_COHERENT) + percpu_ref_get_many(&pgmap->ref, pfn_len(pgmap, range_id)); return 0; err_add_memory: @@ -502,16 +507,24 @@ void free_zone_device_page(struct page *page) page->mapping = NULL; page->pgmap->ops->page_free(page); - /* - * Reset the page count to 1 to prepare for handing out the page again. - */ if (page->pgmap->type != MEMORY_DEVICE_PRIVATE && page->pgmap->type != MEMORY_DEVICE_COHERENT) + /* + * Reset the page count to 1 to prepare for handing out the page + * again. + */ set_page_count(page, 1); + else + put_dev_pagemap(page->pgmap); } void zone_device_page_init(struct page *page) { + /* + * Drivers shouldn't be allocating pages after calling + * memunmap_pages(). + */ + WARN_ON_ONCE(!percpu_ref_tryget_live(&page->pgmap->ref)); set_page_count(page, 1); lock_page(page); } -- cgit From 241f68859656836ae3e85179cc224cc4c5e4e6a7 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:18 +1000 Subject: mm/migrate_device.c: refactor migrate_vma and migrate_deivce_coherent_page() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit migrate_device_coherent_page() reuses the existing migrate_vma family of functions to migrate a specific page without providing a valid mapping or vma. This looks a bit odd because it means we are calling migrate_vma_*() without setting a valid vma, however it was considered acceptable at the time because the details were internal to migrate_device.c and there was only a single user. One of the reasons the details could be kept internal was that this was strictly for migrating device coherent memory. Such memory can be copied directly by the CPU without intervention from a driver. However this isn't true for device private memory, and a future change requires similar functionality for device private memory. So refactor the code into something more sensible for migrating device memory without a vma. Link: https://lkml.kernel.org/r/c7b2ff84e9b33d022cf4a40f87d051f281a16d8f.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Cc: "Huang, Ying" Cc: Zi Yan Cc: Matthew Wilcox Cc: Yang Shi Cc: David Hildenbrand Cc: Ralph Campbell Cc: John Hubbard Cc: Alex Deucher Cc: Alex Sierra Cc: Ben Skeggs Cc: Christian König Cc: Dan Williams Cc: Felix Kuehling Cc: Jason Gunthorpe Cc: Lyude Paul Cc: Michael Ellerman Signed-off-by: Andrew Morton --- mm/migrate_device.c | 150 +++++++++++++++++++++++++++++----------------------- 1 file changed, 85 insertions(+), 65 deletions(-) diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 8dee38ffcda2..7707c1d898f5 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -357,26 +357,20 @@ static bool migrate_vma_check_page(struct page *page, struct page *fault_page) } /* - * migrate_vma_unmap() - replace page mapping with special migration pte entry - * @migrate: migrate struct containing all migration information - * - * Isolate pages from the LRU and replace mappings (CPU page table pte) with a - * special migration pte entry and check if it has been pinned. Pinned pages are - * restored because we cannot migrate them. - * - * This is the last step before we call the device driver callback to allocate - * destination memory and copy contents of original page over to new page. + * Unmaps pages for migration. Returns number of unmapped pages. */ -static void migrate_vma_unmap(struct migrate_vma *migrate) +static unsigned long migrate_device_unmap(unsigned long *src_pfns, + unsigned long npages, + struct page *fault_page) { - const unsigned long npages = migrate->npages; unsigned long i, restore = 0; bool allow_drain = true; + unsigned long unmapped = 0; lru_add_drain(); for (i = 0; i < npages; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); struct folio *folio; if (!page) @@ -391,8 +385,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) } if (isolate_lru_page(page)) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; restore++; continue; } @@ -406,34 +399,54 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) try_to_migrate(folio, 0); if (page_mapped(page) || - !migrate_vma_check_page(page, migrate->fault_page)) { + !migrate_vma_check_page(page, fault_page)) { if (!is_zone_device_page(page)) { get_page(page); putback_lru_page(page); } - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; restore++; continue; } + + unmapped++; } for (i = 0; i < npages && restore; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); struct folio *folio; - if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE)) + if (!page || (src_pfns[i] & MIGRATE_PFN_MIGRATE)) continue; folio = page_folio(page); remove_migration_ptes(folio, folio, false); - migrate->src[i] = 0; + src_pfns[i] = 0; folio_unlock(folio); folio_put(folio); restore--; } + + return unmapped; +} + +/* + * migrate_vma_unmap() - replace page mapping with special migration pte entry + * @migrate: migrate struct containing all migration information + * + * Isolate pages from the LRU and replace mappings (CPU page table pte) with a + * special migration pte entry and check if it has been pinned. Pinned pages are + * restored because we cannot migrate them. + * + * This is the last step before we call the device driver callback to allocate + * destination memory and copy contents of original page over to new page. + */ +static void migrate_vma_unmap(struct migrate_vma *migrate) +{ + migrate->cpages = migrate_device_unmap(migrate->src, migrate->npages, + migrate->fault_page); } /** @@ -680,41 +693,36 @@ abort: *src &= ~MIGRATE_PFN_MIGRATE; } -/** - * migrate_vma_pages() - migrate meta-data from src page to dst page - * @migrate: migrate struct containing all migration information - * - * This migrates struct page meta-data from source struct page to destination - * struct page. This effectively finishes the migration from source page to the - * destination page. - */ -void migrate_vma_pages(struct migrate_vma *migrate) +static void migrate_device_pages(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages, + struct migrate_vma *migrate) { - const unsigned long npages = migrate->npages; - const unsigned long start = migrate->start; struct mmu_notifier_range range; - unsigned long addr, i; + unsigned long i; bool notified = false; - for (i = 0, addr = start; i < npages; addr += PAGE_SIZE, i++) { - struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); - struct page *page = migrate_pfn_to_page(migrate->src[i]); + for (i = 0; i < npages; i++) { + struct page *newpage = migrate_pfn_to_page(dst_pfns[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); struct address_space *mapping; int r; if (!newpage) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; continue; } if (!page) { + unsigned long addr; + /* * The only time there is no vma is when called from * migrate_device_coherent_page(). However this isn't * called if the page could not be unmapped. */ - VM_BUG_ON(!migrate->vma); - if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) + VM_BUG_ON(!migrate); + addr = migrate->start + i*PAGE_SIZE; + if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE)) continue; if (!notified) { notified = true; @@ -726,7 +734,7 @@ void migrate_vma_pages(struct migrate_vma *migrate) mmu_notifier_invalidate_range_start(&range); } migrate_vma_insert_page(migrate, addr, newpage, - &migrate->src[i]); + &src_pfns[i]); continue; } @@ -739,18 +747,18 @@ void migrate_vma_pages(struct migrate_vma *migrate) * device private or coherent memory. */ if (mapping) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; continue; } } else if (is_zone_device_page(newpage)) { /* * Other types of ZONE_DEVICE page are not supported. */ - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; continue; } - if (migrate->fault_page == page) + if (migrate && migrate->fault_page == page) r = migrate_folio_extra(mapping, page_folio(newpage), page_folio(page), MIGRATE_SYNC_NO_COPY, 1); @@ -758,7 +766,7 @@ void migrate_vma_pages(struct migrate_vma *migrate) r = migrate_folio(mapping, page_folio(newpage), page_folio(page), MIGRATE_SYNC_NO_COPY); if (r != MIGRATEPAGE_SUCCESS) - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + src_pfns[i] &= ~MIGRATE_PFN_MIGRATE; } /* @@ -769,28 +777,30 @@ void migrate_vma_pages(struct migrate_vma *migrate) if (notified) mmu_notifier_invalidate_range_only_end(&range); } -EXPORT_SYMBOL(migrate_vma_pages); /** - * migrate_vma_finalize() - restore CPU page table entry + * migrate_vma_pages() - migrate meta-data from src page to dst page * @migrate: migrate struct containing all migration information * - * This replaces the special migration pte entry with either a mapping to the - * new page if migration was successful for that page, or to the original page - * otherwise. - * - * This also unlocks the pages and puts them back on the lru, or drops the extra - * refcount, for device pages. + * This migrates struct page meta-data from source struct page to destination + * struct page. This effectively finishes the migration from source page to the + * destination page. */ -void migrate_vma_finalize(struct migrate_vma *migrate) +void migrate_vma_pages(struct migrate_vma *migrate) +{ + migrate_device_pages(migrate->src, migrate->dst, migrate->npages, migrate); +} +EXPORT_SYMBOL(migrate_vma_pages); + +static void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages) { - const unsigned long npages = migrate->npages; unsigned long i; for (i = 0; i < npages; i++) { struct folio *dst, *src; - struct page *newpage = migrate_pfn_to_page(migrate->dst[i]); - struct page *page = migrate_pfn_to_page(migrate->src[i]); + struct page *newpage = migrate_pfn_to_page(dst_pfns[i]); + struct page *page = migrate_pfn_to_page(src_pfns[i]); if (!page) { if (newpage) { @@ -800,7 +810,7 @@ void migrate_vma_finalize(struct migrate_vma *migrate) continue; } - if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE) || !newpage) { + if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE) || !newpage) { if (newpage) { unlock_page(newpage); put_page(newpage); @@ -827,6 +837,22 @@ void migrate_vma_finalize(struct migrate_vma *migrate) } } } + +/** + * migrate_vma_finalize() - restore CPU page table entry + * @migrate: migrate struct containing all migration information + * + * This replaces the special migration pte entry with either a mapping to the + * new page if migration was successful for that page, or to the original page + * otherwise. + * + * This also unlocks the pages and puts them back on the lru, or drops the extra + * refcount, for device pages. + */ +void migrate_vma_finalize(struct migrate_vma *migrate) +{ + migrate_device_finalize(migrate->src, migrate->dst, migrate->npages); +} EXPORT_SYMBOL(migrate_vma_finalize); /* @@ -837,25 +863,19 @@ EXPORT_SYMBOL(migrate_vma_finalize); int migrate_device_coherent_page(struct page *page) { unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma args; struct page *dpage; WARN_ON_ONCE(PageCompound(page)); lock_page(page); src_pfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; - args.src = &src_pfn; - args.dst = &dst_pfn; - args.cpages = 1; - args.npages = 1; - args.vma = NULL; /* * We don't have a VMA and don't need to walk the page tables to find * the source page. So call migrate_vma_unmap() directly to unmap the * page as migrate_vma_setup() will fail if args.vma == NULL. */ - migrate_vma_unmap(&args); + migrate_device_unmap(&src_pfn, 1, NULL); if (!(src_pfn & MIGRATE_PFN_MIGRATE)) return -EBUSY; @@ -865,10 +885,10 @@ int migrate_device_coherent_page(struct page *page) dst_pfn = migrate_pfn(page_to_pfn(dpage)); } - migrate_vma_pages(&args); + migrate_device_pages(&src_pfn, &dst_pfn, 1, NULL); if (src_pfn & MIGRATE_PFN_MIGRATE) copy_highpage(dpage, page); - migrate_vma_finalize(&args); + migrate_device_finalize(&src_pfn, &dst_pfn, 1); if (src_pfn & MIGRATE_PFN_MIGRATE) return 0; -- cgit From e778406b40dbb1342a1888cd751ca9d2982a12e2 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:19 +1000 Subject: mm/migrate_device.c: add migrate_device_range() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Device drivers can use the migrate_vma family of functions to migrate existing private anonymous mappings to device private pages. These pages are backed by memory on the device with drivers being responsible for copying data to and from device memory. Device private pages are freed via the pgmap->page_free() callback when they are unmapped and their refcount drops to zero. Alternatively they may be freed indirectly via migration back to CPU memory in response to a pgmap->migrate_to_ram() callback called whenever the CPU accesses an address mapped to a device private page. In other words drivers cannot control the lifetime of data allocated on the devices and must wait until these pages are freed from userspace. This causes issues when memory needs to reclaimed on the device, either because the device is going away due to a ->release() callback or because another user needs to use the memory. Drivers could use the existing migrate_vma functions to migrate data off the device. However this would require them to track the mappings of each page which is both complicated and not always possible. Instead drivers need to be able to migrate device pages directly so they can free up device memory. To allow that this patch introduces the migrate_device family of functions which are functionally similar to migrate_vma but which skips the initial lookup based on mapping. Link: https://lkml.kernel.org/r/868116aab70b0c8ee467d62498bb2cf0ef907295.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Cc: "Huang, Ying" Cc: Zi Yan Cc: Matthew Wilcox Cc: Yang Shi Cc: David Hildenbrand Cc: Ralph Campbell Cc: John Hubbard Cc: Alex Deucher Cc: Alex Sierra Cc: Ben Skeggs Cc: Christian König Cc: Dan Williams Cc: Felix Kuehling Cc: Jason Gunthorpe Cc: Lyude Paul Cc: Michael Ellerman Signed-off-by: Andrew Morton --- include/linux/migrate.h | 7 ++++ mm/migrate_device.c | 89 +++++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 89 insertions(+), 7 deletions(-) diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 52090d1f9230..3ef77f52a4f0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -210,6 +210,13 @@ struct migrate_vma { int migrate_vma_setup(struct migrate_vma *args); void migrate_vma_pages(struct migrate_vma *migrate); void migrate_vma_finalize(struct migrate_vma *migrate); +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages); +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages); +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages); + #endif /* CONFIG_MIGRATION */ #endif /* _LINUX_MIGRATE_H */ diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 7707c1d898f5..6fa682eef7a0 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -693,7 +693,7 @@ abort: *src &= ~MIGRATE_PFN_MIGRATE; } -static void migrate_device_pages(unsigned long *src_pfns, +static void __migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, unsigned long npages, struct migrate_vma *migrate) { @@ -715,6 +715,9 @@ static void migrate_device_pages(unsigned long *src_pfns, if (!page) { unsigned long addr; + if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE)) + continue; + /* * The only time there is no vma is when called from * migrate_device_coherent_page(). However this isn't @@ -722,8 +725,6 @@ static void migrate_device_pages(unsigned long *src_pfns, */ VM_BUG_ON(!migrate); addr = migrate->start + i*PAGE_SIZE; - if (!(src_pfns[i] & MIGRATE_PFN_MIGRATE)) - continue; if (!notified) { notified = true; @@ -778,6 +779,22 @@ static void migrate_device_pages(unsigned long *src_pfns, mmu_notifier_invalidate_range_only_end(&range); } +/** + * migrate_device_pages() - migrate meta-data from src page to dst page + * @src_pfns: src_pfns returned from migrate_device_range() + * @dst_pfns: array of pfns allocated by the driver to migrate memory to + * @npages: number of pages in the range + * + * Equivalent to migrate_vma_pages(). This is called to migrate struct page + * meta-data from source struct page to destination. + */ +void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns, + unsigned long npages) +{ + __migrate_device_pages(src_pfns, dst_pfns, npages, NULL); +} +EXPORT_SYMBOL(migrate_device_pages); + /** * migrate_vma_pages() - migrate meta-data from src page to dst page * @migrate: migrate struct containing all migration information @@ -788,12 +805,22 @@ static void migrate_device_pages(unsigned long *src_pfns, */ void migrate_vma_pages(struct migrate_vma *migrate) { - migrate_device_pages(migrate->src, migrate->dst, migrate->npages, migrate); + __migrate_device_pages(migrate->src, migrate->dst, migrate->npages, migrate); } EXPORT_SYMBOL(migrate_vma_pages); -static void migrate_device_finalize(unsigned long *src_pfns, - unsigned long *dst_pfns, unsigned long npages) +/* + * migrate_device_finalize() - complete page migration + * @src_pfns: src_pfns returned from migrate_device_range() + * @dst_pfns: array of pfns allocated by the driver to migrate memory to + * @npages: number of pages in the range + * + * Completes migration of the page by removing special migration entries. + * Drivers must ensure copying of page data is complete and visible to the CPU + * before calling this. + */ +void migrate_device_finalize(unsigned long *src_pfns, + unsigned long *dst_pfns, unsigned long npages) { unsigned long i; @@ -837,6 +864,7 @@ static void migrate_device_finalize(unsigned long *src_pfns, } } } +EXPORT_SYMBOL(migrate_device_finalize); /** * migrate_vma_finalize() - restore CPU page table entry @@ -855,6 +883,53 @@ void migrate_vma_finalize(struct migrate_vma *migrate) } EXPORT_SYMBOL(migrate_vma_finalize); +/** + * migrate_device_range() - migrate device private pfns to normal memory. + * @src_pfns: array large enough to hold migrating source device private pfns. + * @start: starting pfn in the range to migrate. + * @npages: number of pages to migrate. + * + * migrate_vma_setup() is similar in concept to migrate_vma_setup() except that + * instead of looking up pages based on virtual address mappings a range of + * device pfns that should be migrated to system memory is used instead. + * + * This is useful when a driver needs to free device memory but doesn't know the + * virtual mappings of every page that may be in device memory. For example this + * is often the case when a driver is being unloaded or unbound from a device. + * + * Like migrate_vma_setup() this function will take a reference and lock any + * migrating pages that aren't free before unmapping them. Drivers may then + * allocate destination pages and start copying data from the device to CPU + * memory before calling migrate_device_pages(). + */ +int migrate_device_range(unsigned long *src_pfns, unsigned long start, + unsigned long npages) +{ + unsigned long i, pfn; + + for (pfn = start, i = 0; i < npages; pfn++, i++) { + struct page *page = pfn_to_page(pfn); + + if (!get_page_unless_zero(page)) { + src_pfns[i] = 0; + continue; + } + + if (!trylock_page(page)) { + src_pfns[i] = 0; + put_page(page); + continue; + } + + src_pfns[i] = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE; + } + + migrate_device_unmap(src_pfns, npages, NULL); + + return 0; +} +EXPORT_SYMBOL(migrate_device_range); + /* * Migrate a device coherent page back to normal memory. The caller should have * a reference on page which will be copied to the new page if migration is @@ -885,7 +960,7 @@ int migrate_device_coherent_page(struct page *page) dst_pfn = migrate_pfn(page_to_pfn(dpage)); } - migrate_device_pages(&src_pfn, &dst_pfn, 1, NULL); + migrate_device_pages(&src_pfn, &dst_pfn, 1); if (src_pfn & MIGRATE_PFN_MIGRATE) copy_highpage(dpage, page); migrate_device_finalize(&src_pfn, &dst_pfn, 1); -- cgit From d9b719394a1147614351961ac454589111c76e76 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:20 +1000 Subject: nouveau/dmem: refactor nouveau_dmem_fault_copy_one() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit nouveau_dmem_fault_copy_one() is used during handling of CPU faults via the migrate_to_ram() callback and is used to copy data from GPU to CPU memory. It is currently specific to fault handling, however a future patch implementing eviction of data during teardown needs similar functionality. Refactor out the core functionality so that it is not specific to fault handling. Link: https://lkml.kernel.org/r/20573d7b4e641a78fde9935f948e64e71c9e709e.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Reviewed-by: Lyude Paul Cc: Ben Skeggs Cc: Ralph Campbell Cc: John Hubbard Cc: Alex Deucher Cc: Alex Sierra Cc: Christian König Cc: Dan Williams Cc: David Hildenbrand Cc: Felix Kuehling Cc: "Huang, Ying" Cc: Jason Gunthorpe Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 58 ++++++++++++++++------------------ 1 file changed, 28 insertions(+), 30 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index b092988266a6..65f51fb6a70c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -139,44 +139,24 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence) } } -static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, - struct vm_fault *vmf, struct migrate_vma *args, - dma_addr_t *dma_addr) +static int nouveau_dmem_copy_one(struct nouveau_drm *drm, struct page *spage, + struct page *dpage, dma_addr_t *dma_addr) { struct device *dev = drm->dev->dev; - struct page *dpage, *spage; - struct nouveau_svmm *svmm; - - spage = migrate_pfn_to_page(args->src[0]); - if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE)) - return 0; - dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); - if (!dpage) - return VM_FAULT_SIGBUS; lock_page(dpage); *dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, *dma_addr)) - goto error_free_page; + return -EIO; - svmm = spage->zone_device_data; - mutex_lock(&svmm->mutex); - nouveau_svmm_invalidate(svmm, args->start, args->end); if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr, - NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) - goto error_dma_unmap; - mutex_unlock(&svmm->mutex); + NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) { + dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); + return -EIO; + } - args->dst[0] = migrate_pfn(page_to_pfn(dpage)); return 0; - -error_dma_unmap: - mutex_unlock(&svmm->mutex); - dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); -error_free_page: - __free_page(dpage); - return VM_FAULT_SIGBUS; } static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) @@ -184,9 +164,11 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) struct nouveau_drm *drm = page_to_drm(vmf->page); struct nouveau_dmem *dmem = drm->dmem; struct nouveau_fence *fence; + struct nouveau_svmm *svmm; + struct page *spage, *dpage; unsigned long src = 0, dst = 0; dma_addr_t dma_addr = 0; - vm_fault_t ret; + vm_fault_t ret = 0; struct migrate_vma args = { .vma = vmf->vma, .start = vmf->address, @@ -207,9 +189,25 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) if (!args.cpages) return 0; - ret = nouveau_dmem_fault_copy_one(drm, vmf, &args, &dma_addr); - if (ret || dst == 0) + spage = migrate_pfn_to_page(src); + if (!spage || !(src & MIGRATE_PFN_MIGRATE)) + goto done; + + dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); + if (!dpage) + goto done; + + dst = migrate_pfn(page_to_pfn(dpage)); + + svmm = spage->zone_device_data; + mutex_lock(&svmm->mutex); + nouveau_svmm_invalidate(svmm, args.start, args.end); + ret = nouveau_dmem_copy_one(drm, spage, dpage, &dma_addr); + mutex_unlock(&svmm->mutex); + if (ret) { + ret = VM_FAULT_SIGBUS; goto done; + } nouveau_fence_new(dmem->migrate.chan, false, &fence); migrate_vma_pages(&args); -- cgit From 249881232e1471d28b68f9a3829acc14d150cf5d Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:21 +1000 Subject: nouveau/dmem: evict device private memory during release MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the module is unloaded or a GPU is unbound from the module it is possible for device private pages to still be mapped in currently running processes. This can lead to a hangs and RCU stall warnings when unbinding the device as memunmap_pages() will wait in an uninterruptible state until all device pages have been freed which may never happen. Fix this by migrating device mappings back to normal CPU memory prior to freeing the GPU memory chunks and associated device private pages. Link: https://lkml.kernel.org/r/66277601fb8fda9af408b33da9887192bf895bda.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Cc: Lyude Paul Cc: Ben Skeggs Cc: Ralph Campbell Cc: John Hubbard Cc: Alex Deucher Cc: Alex Sierra Cc: Christian König Cc: Dan Williams Cc: David Hildenbrand Cc: Felix Kuehling Cc: "Huang, Ying" Cc: Jason Gunthorpe Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 48 ++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 65f51fb6a70c..5fe209107246 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -367,6 +367,52 @@ nouveau_dmem_suspend(struct nouveau_drm *drm) mutex_unlock(&drm->dmem->mutex); } +/* + * Evict all pages mapping a chunk. + */ +static void +nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) +{ + unsigned long i, npages = range_len(&chunk->pagemap.range) >> PAGE_SHIFT; + unsigned long *src_pfns, *dst_pfns; + dma_addr_t *dma_addrs; + struct nouveau_fence *fence; + + src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); + dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL); + + migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, + npages); + + for (i = 0; i < npages; i++) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) { + struct page *dpage; + + /* + * _GFP_NOFAIL because the GPU is going away and there + * is nothing sensible we can do if we can't copy the + * data back. + */ + dpage = alloc_page(GFP_HIGHUSER | __GFP_NOFAIL); + dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)); + nouveau_dmem_copy_one(chunk->drm, + migrate_pfn_to_page(src_pfns[i]), dpage, + &dma_addrs[i]); + } + } + + nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence); + migrate_device_pages(src_pfns, dst_pfns, npages); + nouveau_dmem_fence_done(&fence); + migrate_device_finalize(src_pfns, dst_pfns, npages); + kfree(src_pfns); + kfree(dst_pfns); + for (i = 0; i < npages; i++) + dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL); + kfree(dma_addrs); +} + void nouveau_dmem_fini(struct nouveau_drm *drm) { @@ -378,8 +424,10 @@ nouveau_dmem_fini(struct nouveau_drm *drm) mutex_lock(&drm->dmem->mutex); list_for_each_entry_safe(chunk, tmp, &drm->dmem->chunks, list) { + nouveau_dmem_evict_chunk(chunk); nouveau_bo_unpin(chunk->bo); nouveau_bo_ref(NULL, &chunk->bo); + WARN_ON(chunk->callocated); list_del(&chunk->list); memunmap_pages(&chunk->pagemap); release_mem_region(chunk->pagemap.range.start, -- cgit From ad4c365221b0f92f9c24a203119f2bade30c970e Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 28 Sep 2022 22:01:22 +1000 Subject: hmm-tests: add test for migrate_device_range() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Link: https://lkml.kernel.org/r/a73cf109de0224cfd118d22be58ddebac3ae2897.1664366292.git-series.apopple@nvidia.com Signed-off-by: Alistair Popple Cc: Jason Gunthorpe Cc: Ralph Campbell Cc: John Hubbard Cc: Alex Sierra Cc: Felix Kuehling Cc: Alex Deucher Cc: Ben Skeggs Cc: Christian König Cc: Dan Williams Cc: David Hildenbrand Cc: "Huang, Ying" Cc: Lyude Paul Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- lib/test_hmm.c | 120 +++++++++++++++++++++++++++------ lib/test_hmm_uapi.h | 1 + tools/testing/selftests/vm/hmm-tests.c | 49 ++++++++++++++ 3 files changed, 149 insertions(+), 21 deletions(-) diff --git a/lib/test_hmm.c b/lib/test_hmm.c index bc2b94991165..67e6f83fe0f8 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -100,6 +100,7 @@ struct dmirror { struct dmirror_chunk { struct dev_pagemap pagemap; struct dmirror_device *mdevice; + bool remove; }; /* @@ -192,11 +193,15 @@ static int dmirror_fops_release(struct inode *inode, struct file *filp) return 0; } +static struct dmirror_chunk *dmirror_page_to_chunk(struct page *page) +{ + return container_of(page->pgmap, struct dmirror_chunk, pagemap); +} + static struct dmirror_device *dmirror_page_to_device(struct page *page) { - return container_of(page->pgmap, struct dmirror_chunk, - pagemap)->mdevice; + return dmirror_page_to_chunk(page)->mdevice; } static int dmirror_do_fault(struct dmirror *dmirror, struct hmm_range *range) @@ -1218,6 +1223,85 @@ static int dmirror_snapshot(struct dmirror *dmirror, return ret; } +static void dmirror_device_evict_chunk(struct dmirror_chunk *chunk) +{ + unsigned long start_pfn = chunk->pagemap.range.start >> PAGE_SHIFT; + unsigned long end_pfn = chunk->pagemap.range.end >> PAGE_SHIFT; + unsigned long npages = end_pfn - start_pfn + 1; + unsigned long i; + unsigned long *src_pfns; + unsigned long *dst_pfns; + + src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); + dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + + migrate_device_range(src_pfns, start_pfn, npages); + for (i = 0; i < npages; i++) { + struct page *dpage, *spage; + + spage = migrate_pfn_to_page(src_pfns[i]); + if (!spage || !(src_pfns[i] & MIGRATE_PFN_MIGRATE)) + continue; + + if (WARN_ON(!is_device_private_page(spage) && + !is_device_coherent_page(spage))) + continue; + spage = BACKING_PAGE(spage); + dpage = alloc_page(GFP_HIGHUSER_MOVABLE | __GFP_NOFAIL); + lock_page(dpage); + copy_highpage(dpage, spage); + dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)); + if (src_pfns[i] & MIGRATE_PFN_WRITE) + dst_pfns[i] |= MIGRATE_PFN_WRITE; + } + migrate_device_pages(src_pfns, dst_pfns, npages); + migrate_device_finalize(src_pfns, dst_pfns, npages); + kfree(src_pfns); + kfree(dst_pfns); +} + +/* Removes free pages from the free list so they can't be re-allocated */ +static void dmirror_remove_free_pages(struct dmirror_chunk *devmem) +{ + struct dmirror_device *mdevice = devmem->mdevice; + struct page *page; + + for (page = mdevice->free_pages; page; page = page->zone_device_data) + if (dmirror_page_to_chunk(page) == devmem) + mdevice->free_pages = page->zone_device_data; +} + +static void dmirror_device_remove_chunks(struct dmirror_device *mdevice) +{ + unsigned int i; + + mutex_lock(&mdevice->devmem_lock); + if (mdevice->devmem_chunks) { + for (i = 0; i < mdevice->devmem_count; i++) { + struct dmirror_chunk *devmem = + mdevice->devmem_chunks[i]; + + spin_lock(&mdevice->lock); + devmem->remove = true; + dmirror_remove_free_pages(devmem); + spin_unlock(&mdevice->lock); + + dmirror_device_evict_chunk(devmem); + memunmap_pages(&devmem->pagemap); + if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE) + release_mem_region(devmem->pagemap.range.start, + range_len(&devmem->pagemap.range)); + kfree(devmem); + } + mdevice->devmem_count = 0; + mdevice->devmem_capacity = 0; + mdevice->free_pages = NULL; + kfree(mdevice->devmem_chunks); + mdevice->devmem_chunks = NULL; + } + mutex_unlock(&mdevice->devmem_lock); +} + static long dmirror_fops_unlocked_ioctl(struct file *filp, unsigned int command, unsigned long arg) @@ -1272,6 +1356,11 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp, ret = dmirror_snapshot(dmirror, &cmd); break; + case HMM_DMIRROR_RELEASE: + dmirror_device_remove_chunks(dmirror->mdevice); + ret = 0; + break; + default: return -EINVAL; } @@ -1326,9 +1415,13 @@ static void dmirror_devmem_free(struct page *page) mdevice = dmirror_page_to_device(page); spin_lock(&mdevice->lock); - mdevice->cfree++; - page->zone_device_data = mdevice->free_pages; - mdevice->free_pages = page; + + /* Return page to our allocator if not freeing the chunk */ + if (!dmirror_page_to_chunk(page)->remove) { + mdevice->cfree++; + page->zone_device_data = mdevice->free_pages; + mdevice->free_pages = page; + } spin_unlock(&mdevice->lock); } @@ -1408,22 +1501,7 @@ static int dmirror_device_init(struct dmirror_device *mdevice, int id) static void dmirror_device_remove(struct dmirror_device *mdevice) { - unsigned int i; - - if (mdevice->devmem_chunks) { - for (i = 0; i < mdevice->devmem_count; i++) { - struct dmirror_chunk *devmem = - mdevice->devmem_chunks[i]; - - memunmap_pages(&devmem->pagemap); - if (devmem->pagemap.type == MEMORY_DEVICE_PRIVATE) - release_mem_region(devmem->pagemap.range.start, - range_len(&devmem->pagemap.range)); - kfree(devmem); - } - kfree(mdevice->devmem_chunks); - } - + dmirror_device_remove_chunks(mdevice); cdev_device_del(&mdevice->cdevice, &mdevice->device); } diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h index e31d58c9034a..8c818a2cf4f6 100644 --- a/lib/test_hmm_uapi.h +++ b/lib/test_hmm_uapi.h @@ -36,6 +36,7 @@ struct hmm_dmirror_cmd { #define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x04, struct hmm_dmirror_cmd) #define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd) #define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x06, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_RELEASE _IOWR('H', 0x07, struct hmm_dmirror_cmd) /* * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT. diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index f2c2c970eeb2..28232adec883 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -1054,6 +1054,55 @@ TEST_F(hmm, migrate_fault) hmm_buffer_free(buffer); } +TEST_F(hmm, migrate_release) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + + npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + /* Release device memory. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_RELEASE, buffer, npages); + ASSERT_EQ(ret, 0); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i) + ASSERT_EQ(ptr[i], i); + + hmm_buffer_free(buffer); +} + /* * Migrate anonymous shared memory to device private memory. */ -- cgit From d6e5040bd8e53371fafd7e0c7c63b090b3a675db Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Mon, 26 Sep 2022 20:08:47 +0200 Subject: kasan: fix array-bounds warnings in tests GCC's -Warray-bounds option detects out-of-bounds accesses to statically-sized allocations in krealloc out-of-bounds tests. Use OPTIMIZER_HIDE_VAR to suppress the warning. Also change kmalloc_memmove_invalid_size to use OPTIMIZER_HIDE_VAR instead of a volatile variable. Link: https://lkml.kernel.org/r/e94399242d32e00bba6fd0d9ec4c897f188128e8.1664215688.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reported-by: kernel test robot Reviewed-by: Kees Cook Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Marco Elver Signed-off-by: Andrew Morton --- mm/kasan/kasan_test.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index f25692def781..57e4c72aa8bd 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -295,6 +295,9 @@ static void krealloc_more_oob_helper(struct kunit *test, ptr2 = krealloc(ptr1, size2, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); + /* Suppress -Warray-bounds warnings. */ + OPTIMIZER_HIDE_VAR(ptr2); + /* All offsets up to size2 must be accessible. */ ptr2[size1 - 1] = 'x'; ptr2[size1] = 'x'; @@ -327,6 +330,9 @@ static void krealloc_less_oob_helper(struct kunit *test, ptr2 = krealloc(ptr1, size2, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr2); + /* Suppress -Warray-bounds warnings. */ + OPTIMIZER_HIDE_VAR(ptr2); + /* Must be accessible for all modes. */ ptr2[size2 - 1] = 'x'; @@ -540,13 +546,14 @@ static void kmalloc_memmove_invalid_size(struct kunit *test) { char *ptr; size_t size = 64; - volatile size_t invalid_size = size; + size_t invalid_size = size; ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset((char *)ptr, 0, 64); OPTIMIZER_HIDE_VAR(ptr); + OPTIMIZER_HIDE_VAR(invalid_size); KUNIT_EXPECT_KASAN_FAIL(test, memmove((char *)ptr, (char *)ptr + 4, invalid_size)); kfree(ptr); -- cgit From bce8cb3c04dc01d21b6b17baf1cb6c277e7e6848 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Thu, 29 Sep 2022 19:23:17 +0800 Subject: mm: use update_mmu_tlb() on the second thread As message in commit 7df676974359 ("mm/memory.c: Update local TLB if PTE entry exists") said, we should update local TLB only on the second thread. So in the do_anonymous_page() here, we should use update_mmu_tlb() instead of update_mmu_cache() on the second thread. As David pointed out, this is a performance improvement, not a correctness fix. Link: https://lkml.kernel.org/r/20220929112318.32393-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Reviewed-by: Muchun Song Acked-by: David Hildenbrand Cc: Bibo Mao Cc: Chris Zankel Cc: Huacai Chen Cc: Max Filippov Signed-off-by: Andrew Morton --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index 4ad6077164cd..f88c351aecd4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4134,7 +4134,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { - update_mmu_cache(vma, vmf->address, vmf->pte); + update_mmu_tlb(vma, vmf->address, vmf->pte); goto release; } -- cgit From 14c2ac36811b82479b1138383b2c9ff1ab6ba47d Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Thu, 29 Sep 2022 19:23:18 +0800 Subject: LoongArch: update local TLB if PTE entry exists Currently, the implementation of update_mmu_tlb() is empty if __HAVE_ARCH_UPDATE_MMU_TLB is not defined. Then if two threads concurrently fault at the same page, the second thread that did not win the race will give up and do nothing. In the LoongArch architecture, this second thread will trigger another fault, and only updates its local TLB. Instead of triggering another fault, it's better to implement update_mmu_tlb() to directly update the local TLB of the second thread. Just do it. Link: https://lkml.kernel.org/r/20220929112318.32393-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Suggested-by: Bibo Mao Acked-by: Huacai Chen Cc: Chris Zankel Cc: David Hildenbrand Cc: Max Filippov Cc: Muchun Song Signed-off-by: Andrew Morton --- arch/loongarch/include/asm/pgtable.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 8ea57e2f0e04..946704bee599 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -412,6 +412,9 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, __update_tlb(vma, address, ptep); } +#define __HAVE_ARCH_UPDATE_MMU_TLB +#define update_mmu_tlb update_mmu_cache + static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { -- cgit From 94541bc3fbde45bbd40e7989995246b22732679a Mon Sep 17 00:00:00 2001 From: Brian Geffon Date: Mon, 3 Oct 2022 10:48:32 -0400 Subject: zram: always expose rw_page Currently zram will adjust its fops to a version which does not contain rw_page when a backing device has been assigned. This is done to prevent upper layers from assuming a synchronous operation when a page may have been written back. This forces every operation through bio which has overhead associated with bio_alloc/frees. The code can be simplified to always expose an rw_page method and only in the rare event that a page is written back we instead will return -EOPNOTSUPP forcing the upper layer to fallback to bio. Link: https://lkml.kernel.org/r/20221003144832.2906610-1-bgeffon@google.com Signed-off-by: Brian Geffon Reviewed-by: Sergey Senozhatsky Cc: Minchan Kim Cc: Nitin Gupta Cc: Rom Lemarchand Cc: Suleiman Souhlal Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 26 +++----------------------- 1 file changed, 3 insertions(+), 23 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 43eeef2b9fbe..2ba5c98319e5 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -52,9 +52,6 @@ static unsigned int num_devices = 1; static size_t huge_class_size; static const struct block_device_operations zram_devops; -#ifdef CONFIG_ZRAM_WRITEBACK -static const struct block_device_operations zram_wb_devops; -#endif static void zram_free_page(struct zram *zram, size_t index); static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, @@ -546,17 +543,6 @@ static ssize_t backing_dev_store(struct device *dev, zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; - /* - * With writeback feature, zram does asynchronous IO so it's no longer - * synchronous device so let's remove synchronous io flag. Othewise, - * upper layer(e.g., swap) could wait IO completion rather than - * (submit and return), which will cause system sluggish. - * Furthermore, when the IO function returns(e.g., swap_readpage), - * upper layer expects IO was done so it could deallocate the page - * freely but in fact, IO is going on so finally could cause - * use-after-free when the IO is really done. - */ - zram->disk->fops = &zram_wb_devops; up_write(&zram->init_lock); pr_info("setup backing device %s\n", file_name); @@ -1270,6 +1256,9 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, struct bio_vec bvec; zram_slot_unlock(zram, index); + /* A null bio means rw_page was used, we must fallback to bio */ + if (!bio) + return -EOPNOTSUPP; bvec.bv_page = page; bvec.bv_len = PAGE_SIZE; @@ -1856,15 +1845,6 @@ static const struct block_device_operations zram_devops = { .owner = THIS_MODULE }; -#ifdef CONFIG_ZRAM_WRITEBACK -static const struct block_device_operations zram_wb_devops = { - .open = zram_open, - .submit_bio = zram_submit_bio, - .swap_slot_free_notify = zram_slot_free_notify, - .owner = THIS_MODULE -}; -#endif - static DEVICE_ATTR_WO(compact); static DEVICE_ATTR_RW(disksize); static DEVICE_ATTR_RO(initstate); -- cgit From 2ea7ff1e39cbe3753d3c649beb70f2cf861dca75 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Tue, 4 Oct 2022 15:33:58 -0400 Subject: mm/hugetlb: fix race condition of uffd missing/minor handling Patch series "mm/hugetlb: Fix selftest failures with write check", v3. Currently akpm mm-unstable fails with uffd hugetlb private mapping test randomly on a write check. The initial bisection of that points to the recent pmd unshare series, but it turns out there's no direction relationship with the series but only some timing change caused the race to start trigger. The race should be fixed in patch 1. Patch 2 is a trivial cleanup on the similar race with hugetlb migrations, patch 3 comment on the write check so when anyone read it again it'll be clear why it's there. This patch (of 3): After the recent rework patchset of hugetlb locking on pmd sharing, kselftest for userfaultfd sometimes fails on hugetlb private tests with unexpected write fault checks. It turns out there's nothing wrong within the locking series regarding this matter, but it could have changed the timing of threads so it can trigger an old bug. The real bug is when we call hugetlb_no_page() we're not with the pgtable lock. It means we're reading the pte values lockless. It's perfectly fine in most cases because before we do normal page allocations we'll take the lock and check pte_same() again. However before that, there are actually two paths on userfaultfd missing/minor handling that may directly move on with the fault process without checking the pte values. It means for these two paths we may be generating an uffd message based on an unstable pte, while an unstable pte can legally be anything as long as the modifier holds the pgtable lock. One example, which is also what happened in the failing kselftest and caused the test failure, is that for private mappings wr-protection changes can happen on one page. While hugetlb_change_protection() generally requires pte being cleared before being changed, then there can be a race condition like: thread 1 thread 2 -------- -------- UFFDIO_WRITEPROTECT hugetlb_fault hugetlb_change_protection pgtable_lock() huge_ptep_modify_prot_start pte==NULL hugetlb_no_page generate uffd missing event even if page existed!! huge_ptep_modify_prot_commit pgtable_unlock() Fix this by rechecking the pte after pgtable lock for both userfaultfd missing & minor fault paths. This bug should have been around starting from uffd hugetlb introduced, so attaching a Fixes to the commit. Also attach another Fixes to the minor support commit for easier tracking. Note that userfaultfd is actually fine with false positives (e.g. caused by pte changed), but not wrong logical events (e.g. caused by reading a pte during changing). The latter can confuse the userspace, so the strictness is very much preferred. E.g., MISSING event should never happen on the page after UFFDIO_COPY has correctly installed the page and returned. Link: https://lkml.kernel.org/r/20221004193400.110155-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20221004193400.110155-2-peterx@redhat.com Fixes: 1a1aad8a9b7b ("userfaultfd: hugetlbfs: add userfaultfd hugetlb hook") Fixes: 7677f7fd8be7 ("userfaultfd: add minor fault registration mode") Signed-off-by: Peter Xu Co-developed-by: Mike Kravetz Reviewed-by: Mike Kravetz Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Nadav Amit Cc: David Hildenbrand Cc: Mike Rapoport Signed-off-by: Andrew Morton --- mm/hugetlb.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 52 insertions(+), 7 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9a910612336d..bf9d8d04bf4f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5535,6 +5535,23 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, return handle_userfault(&vmf, reason); } +/* + * Recheck pte with pgtable lock. Returns true if pte didn't change, or + * false if pte changed or is changing. + */ +static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, + pte_t *ptep, pte_t old_pte) +{ + spinlock_t *ptl; + bool same; + + ptl = huge_pte_lock(h, mm, ptep); + same = pte_same(huge_ptep_get(ptep), old_pte); + spin_unlock(ptl); + + return same; +} + static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, @@ -5575,10 +5592,33 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (idx >= size) goto out; /* Check for page in userfault range */ - if (userfaultfd_missing(vma)) - return hugetlb_handle_userfault(vma, mapping, idx, - flags, haddr, address, - VM_UFFD_MISSING); + if (userfaultfd_missing(vma)) { + /* + * Since hugetlb_no_page() was examining pte + * without pgtable lock, we need to re-test under + * lock because the pte may not be stable and could + * have changed from under us. Try to detect + * either changed or during-changing ptes and retry + * properly when needed. + * + * Note that userfaultfd is actually fine with + * false positives (e.g. caused by pte changed), + * but not wrong logical events (e.g. caused by + * reading a pte during changing). The latter can + * confuse the userspace, so the strictness is very + * much preferred. E.g., MISSING event should + * never happen on the page after UFFDIO_COPY has + * correctly installed the page and returned. + */ + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MISSING); + } page = alloc_huge_page(vma, haddr, 0); if (IS_ERR(page)) { @@ -5644,9 +5684,14 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, if (userfaultfd_minor(vma)) { unlock_page(page); put_page(page); - return hugetlb_handle_userfault(vma, mapping, idx, - flags, haddr, address, - VM_UFFD_MINOR); + /* See comment in userfaultfd_missing() block above */ + if (!hugetlb_pte_stable(h, mm, ptep, old_pte)) { + ret = 0; + goto out; + } + return hugetlb_handle_userfault(vma, mapping, idx, flags, + haddr, address, + VM_UFFD_MINOR); } } -- cgit From f9bf6c03eca1077cae8de0e6d86427656fa42a9b Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Tue, 4 Oct 2022 15:33:59 -0400 Subject: mm/hugetlb: use hugetlb_pte_stable in migration race check After hugetlb_pte_stable() introduced, we can also rewrite the migration race condition against page allocation to use the new helper too. Link: https://lkml.kernel.org/r/20221004193400.110155-3-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Reviewed-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- mm/hugetlb.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bf9d8d04bf4f..9b26055f3119 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5634,11 +5634,10 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * here. Before returning error, get ptl and make * sure there really is no pte entry. */ - ptl = huge_pte_lock(h, mm, ptep); - ret = 0; - if (huge_pte_none(huge_ptep_get(ptep))) + if (hugetlb_pte_stable(h, mm, ptep, old_pte)) ret = vmf_error(PTR_ERR(page)); - spin_unlock(ptl); + else + ret = 0; goto out; } clear_huge_page(page, address, pages_per_huge_page(h)); -- cgit From 26c92d37d3dc484157bdb4eb7d29991c017b168b Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Tue, 4 Oct 2022 15:34:00 -0400 Subject: mm/selftest: uffd: explain the write missing fault check It's not obvious why we had a write check for each of the missing messages, especially when it should be a locking op. Add a rich comment for that, and also try to explain its good side and limitations, so that if someone hit it again for either a bug or a different glibc impl there'll be some clue to start with. Link: https://lkml.kernel.org/r/20221004193400.110155-4-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Reviewed-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Mike Rapoport Cc: Nadav Amit Signed-off-by: Andrew Morton --- tools/testing/selftests/vm/userfaultfd.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 74babdbc02e5..297f250c1d95 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -774,7 +774,27 @@ static void uffd_handle_page_fault(struct uffd_msg *msg, continue_range(uffd, msg->arg.pagefault.address, page_size); stats->minor_faults++; } else { - /* Missing page faults */ + /* + * Missing page faults. + * + * Here we force a write check for each of the missing mode + * faults. It's guaranteed because the only threads that + * will trigger uffd faults are the locking threads, and + * their first instruction to touch the missing page will + * always be pthread_mutex_lock(). + * + * Note that here we relied on an NPTL glibc impl detail to + * always read the lock type at the entry of the lock op + * (pthread_mutex_t.__data.__type, offset 0x10) before + * doing any locking operations to guarantee that. It's + * actually not good to rely on this impl detail because + * logically a pthread-compatible lib can implement the + * locks without types and we can fail when linking with + * them. However since we used to find bugs with this + * strict check we still keep it around. Hopefully this + * could be a good hint when it fails again. If one day + * it'll break on some other impl of glibc we'll revisit. + */ if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) err("unexpected write fault"); -- cgit From 15cd90049d595e592d8860ee15a3f23491d54d17 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Thu, 6 Oct 2022 10:15:40 +0000 Subject: mm/page_alloc: fix incorrect PGFREE and PGALLOC for high-order page PGFREE and PGALLOC represent the number of freed and allocated pages. So the page order must be considered. Link: https://lkml.kernel.org/r/20221006101540.40686-1-laoar.shao@gmail.com Fixes: 44042b449872 ("mm/page_alloc: allow high-order pages to be stored on the per-cpu lists") Signed-off-by: Yafang Shao Acked-by: Mel Gorman Reviewed-by: Miaohe Lin Signed-off-by: Andrew Morton --- mm/page_alloc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 059f6946832f..8e9b7f08a32c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3446,7 +3446,7 @@ static void free_unref_page_commit(struct zone *zone, struct per_cpu_pages *pcp, int pindex; bool free_high; - __count_vm_event(PGFREE); + __count_vm_events(PGFREE, 1 << order); pindex = order_to_pindex(migratetype, order); list_add(&page->pcp_list, &pcp->lists[pindex]); pcp->count += 1 << order; @@ -3803,7 +3803,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, pcp_spin_unlock_irqrestore(pcp, flags); pcp_trylock_finish(UP_flags); if (page) { - __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); zone_statistics(preferred_zone, zone, 1); } return page; -- cgit From ef6e06b2ef87077104d1145a0fd452ff8dbbc4b7 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 5 Oct 2022 21:05:55 -0700 Subject: highmem: fix kmap_to_page() for kmap_local_page() addresses kmap_to_page() is used to get the page for a virtual address which may be kmap'ed. Unfortunately, kmap_local_page() stores mappings in a thread local array separate from kmap(). These mappings were not checked by the call. Check the kmap_local_page() mappings and return the page if found. Because it is intended to remove kmap_to_page() add a warn on once to the kmap checks to flag potential issues early. NOTE Due to 32bit x86 use of kmap local in iomap atmoic, KMAP_LOCAL does not require HIGHMEM to be set. Therefore the support calls required a new KMAP_LOCAL section to fix 0day build errors. [akpm@linux-foundation.org: fix warning] Link: https://lkml.kernel.org/r/20221006040555.1502679-1-ira.weiny@intel.com Signed-off-by: Ira Weiny Reported-by: Al Viro Reported-by: kernel test robot Cc: "Fabio M. De Francesco" Cc: Thomas Gleixner Cc: Christoph Hellwig Signed-off-by: Andrew Morton --- mm/highmem.c | 43 +++++++++++++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 12 deletions(-) diff --git a/mm/highmem.c b/mm/highmem.c index c707d7202d5f..db251e77f98f 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -30,6 +30,17 @@ #include #include +#ifdef CONFIG_KMAP_LOCAL +static inline int kmap_local_calc_idx(int idx) +{ + return idx + KM_MAX_IDX * smp_processor_id(); +} + +#ifndef arch_kmap_local_map_idx +#define arch_kmap_local_map_idx(idx, pfn) kmap_local_calc_idx(idx) +#endif +#endif /* CONFIG_KMAP_LOCAL */ + /* * Virtual_count is not a pure "count". * 0 means that it is not mapped, and has not been mapped @@ -142,12 +153,29 @@ pte_t *pkmap_page_table; struct page *__kmap_to_page(void *vaddr) { + unsigned long base = (unsigned long) vaddr & PAGE_MASK; + struct kmap_ctrl *kctrl = ¤t->kmap_ctrl; unsigned long addr = (unsigned long)vaddr; + int i; + + /* kmap() mappings */ + if (WARN_ON_ONCE(addr >= PKMAP_ADDR(0) && + addr < PKMAP_ADDR(LAST_PKMAP))) + return pte_page(pkmap_page_table[PKMAP_NR(addr)]); - if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) { - int i = PKMAP_NR(addr); + /* kmap_local_page() mappings */ + if (WARN_ON_ONCE(base >= __fix_to_virt(FIX_KMAP_END) && + base < __fix_to_virt(FIX_KMAP_BEGIN))) { + for (i = 0; i < kctrl->idx; i++) { + unsigned long base_addr; + int idx; - return pte_page(pkmap_page_table[i]); + idx = arch_kmap_local_map_idx(i, pte_pfn(pteval)); + base_addr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + + if (base_addr == base) + return pte_page(kctrl->pteval[i]); + } } return virt_to_page(vaddr); @@ -462,10 +490,6 @@ static inline void kmap_local_idx_pop(void) # define arch_kmap_local_post_unmap(vaddr) do { } while (0) #endif -#ifndef arch_kmap_local_map_idx -#define arch_kmap_local_map_idx(idx, pfn) kmap_local_calc_idx(idx) -#endif - #ifndef arch_kmap_local_unmap_idx #define arch_kmap_local_unmap_idx(idx, vaddr) kmap_local_calc_idx(idx) #endif @@ -494,11 +518,6 @@ static inline bool kmap_high_unmap_local(unsigned long vaddr) return false; } -static inline int kmap_local_calc_idx(int idx) -{ - return idx + KM_MAX_IDX * smp_processor_id(); -} - static pte_t *__kmap_pte; static pte_t *kmap_get_pte(unsigned long vaddr, int idx) -- cgit From f2913d006fcdb61719635e093d1b5dd0dafecac7 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Tue, 20 Sep 2022 13:00:37 -0700 Subject: RISC-V: Avoid dereferening NULL regs in die() I don't think we can actually die() without a regs pointer, but the compiler was warning about a NULL check after a dereference. It seems prudent to just avoid the possibly-NULL dereference, given that when die()ing the system is already toast so who knows how we got there. Reported-by: kernel test robot Reported-by: Dan Carpenter Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220920200037.6727-1-palmer@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/traps.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 635e6ec26938..f3e96d60a2ff 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -33,6 +33,7 @@ void die(struct pt_regs *regs, const char *str) { static int die_counter; int ret; + long cause; oops_enter(); @@ -42,11 +43,13 @@ void die(struct pt_regs *regs, const char *str) pr_emerg("%s [#%d]\n", str, ++die_counter); print_modules(); - show_regs(regs); + if (regs) + show_regs(regs); - ret = notify_die(DIE_OOPS, str, regs, 0, regs->cause, SIGSEGV); + cause = regs ? regs->cause : -1; + ret = notify_die(DIE_OOPS, str, regs, 0, cause, SIGSEGV); - if (regs && kexec_should_crash(current)) + if (kexec_should_crash(current)) crash_kexec(regs); bust_spinlocks(0); -- cgit From a4cb3651a174366cc85a677da9e3681fbe97fdae Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 13 Oct 2022 16:44:18 +1000 Subject: powerpc/64s/interrupt: Fix lost interrupts when returning to soft-masked context It's possible for an interrupt returning to an irqs-disabled context to lose a pending soft-masked irq because it branches to part of the exit code for irqs-enabled contexts, which is meant to clear only the PACA_IRQS_HARD_DIS flag from PACAIRQHAPPENED by zeroing the byte. This just looks like a simple thinko from a recent commit (if there was no hard mask pending, there would be no reason to clear it anyway). This also adds comment to the code that actually does need to clear the flag. Fixes: e485f6c751e0a ("powerpc/64/interrupt: Fix return to masked context after hard-mask irq becomes pending") Reported-by: Sachin Sant Reported-by: Guenter Roeck Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221013064418.1311104-1-npiggin@gmail.com --- arch/powerpc/kernel/interrupt_64.S | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 904a5608cbe3..978a173eb339 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -538,7 +538,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) beq .Lfast_kernel_interrupt_return_\srr\() // EE already disabled lbz r11,PACAIRQHAPPENED(r13) andi. r10,r11,PACA_IRQ_MUST_HARD_MASK - beq 1f // No HARD_MASK pending + beq .Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending /* Must clear MSR_EE from _MSR */ #ifdef CONFIG_PPC_BOOK3S @@ -555,12 +555,23 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) b .Lfast_kernel_interrupt_return_\srr\() .Linterrupt_return_\srr\()_soft_enabled: + /* + * In the soft-enabled case, need to double-check that we have no + * pending interrupts that might have come in before we reached the + * restart section of code, and restart the exit so those can be + * handled. + * + * If there are none, it is be possible that the interrupt still + * has PACA_IRQ_HARD_DIS set, which needs to be cleared for the + * interrupted context. This clear will not clobber a new pending + * interrupt coming in, because we're in the restart section, so + * such would return to the restart location. + */ #ifdef CONFIG_PPC_BOOK3S lbz r11,PACAIRQHAPPENED(r13) andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l bne- interrupt_return_\srr\()_kernel_restart #endif -1: li r11,0 stb r11,PACAIRQHAPPENED(r13) // clear the possible HARD_DIS -- cgit From 90d5ce82e143b42b2fdfb95401a89f86b71cedb7 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 13 Oct 2022 17:31:31 +1000 Subject: powerpc/pseries: Fix CONFIG_DTL=n build The recently moved dtl code must be compiled-in if CONFIG_VIRT_CPU_ACCOUNTING_NATIVE=y even if CONFIG_DTL=n. Fixes: 6ba5aa541aaa0 ("powerpc/pseries: Move dtl scanning and steal time accounting to pseries platform") Reported-by: Guenter Roeck Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20221013073131.1485742-1-npiggin@gmail.com --- arch/powerpc/platforms/pseries/Makefile | 3 +- arch/powerpc/platforms/pseries/dtl.c | 151 +++++++++++++++++--------------- 2 files changed, 80 insertions(+), 74 deletions(-) diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 14e143b946a3..92310202bdd7 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -7,7 +7,7 @@ obj-y := lpar.o hvCall.o nvram.o reconfig.o \ setup.o iommu.o event_sources.o ras.o \ firmware.o power.o dlpar.o mobility.o rng.o \ pci.o pci_dlpar.o eeh_pseries.o msi.o \ - papr_platform_attributes.o + papr_platform_attributes.o dtl.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KEXEC_CORE) += kexec.o obj-$(CONFIG_PSERIES_ENERGY) += pseries_energy.o @@ -19,7 +19,6 @@ obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o obj-$(CONFIG_HVCS) += hvcserver.o obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o obj-$(CONFIG_CMM) += cmm.o -obj-$(CONFIG_DTL) += dtl.o obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o obj-$(CONFIG_LPARCFG) += lparcfg.o obj-$(CONFIG_IBMVIO) += vio.o diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 1b1977bc78e7..3f1cdccebc9c 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -18,6 +18,7 @@ #include #include +#ifdef CONFIG_DTL struct dtl { struct dtl_entry *buf; int cpu; @@ -57,78 +58,6 @@ static DEFINE_PER_CPU(struct dtl_ring, dtl_rings); static atomic_t dtl_count; -/* - * Scan the dispatch trace log and count up the stolen time. - * Should be called with interrupts disabled. - */ -static notrace u64 scan_dispatch_log(u64 stop_tb) -{ - u64 i = local_paca->dtl_ridx; - struct dtl_entry *dtl = local_paca->dtl_curr; - struct dtl_entry *dtl_end = local_paca->dispatch_log_end; - struct lppaca *vpa = local_paca->lppaca_ptr; - u64 tb_delta; - u64 stolen = 0; - u64 dtb; - - if (!dtl) - return 0; - - if (i == be64_to_cpu(vpa->dtl_idx)) - return 0; - while (i < be64_to_cpu(vpa->dtl_idx)) { - dtb = be64_to_cpu(dtl->timebase); - tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + - be32_to_cpu(dtl->ready_to_enqueue_time); - barrier(); - if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { - /* buffer has overflowed */ - i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; - dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); - continue; - } - if (dtb > stop_tb) - break; - if (dtl_consumer) - dtl_consumer(dtl, i); - stolen += tb_delta; - ++i; - ++dtl; - if (dtl == dtl_end) - dtl = local_paca->dispatch_log; - } - local_paca->dtl_ridx = i; - local_paca->dtl_curr = dtl; - return stolen; -} - -/* - * Accumulate stolen time by scanning the dispatch trace log. - * Called on entry from user mode. - */ -void notrace pseries_accumulate_stolen_time(void) -{ - u64 sst, ust; - struct cpu_accounting_data *acct = &local_paca->accounting; - - sst = scan_dispatch_log(acct->starttime_user); - ust = scan_dispatch_log(acct->starttime); - acct->stime -= sst; - acct->utime -= ust; - acct->steal_time += ust + sst; -} - -u64 pseries_calculate_stolen_time(u64 stop_tb) -{ - if (!firmware_has_feature(FW_FEATURE_SPLPAR)) - return 0; - - if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) - return scan_dispatch_log(stop_tb); - - return 0; -} - /* * The cpu accounting code controls the DTL ring buffer, and we get * given entries as they are processed. @@ -436,3 +365,81 @@ static int dtl_init(void) return 0; } machine_arch_initcall(pseries, dtl_init); +#endif /* CONFIG_DTL */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +/* + * Scan the dispatch trace log and count up the stolen time. + * Should be called with interrupts disabled. + */ +static notrace u64 scan_dispatch_log(u64 stop_tb) +{ + u64 i = local_paca->dtl_ridx; + struct dtl_entry *dtl = local_paca->dtl_curr; + struct dtl_entry *dtl_end = local_paca->dispatch_log_end; + struct lppaca *vpa = local_paca->lppaca_ptr; + u64 tb_delta; + u64 stolen = 0; + u64 dtb; + + if (!dtl) + return 0; + + if (i == be64_to_cpu(vpa->dtl_idx)) + return 0; + while (i < be64_to_cpu(vpa->dtl_idx)) { + dtb = be64_to_cpu(dtl->timebase); + tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) + + be32_to_cpu(dtl->ready_to_enqueue_time); + barrier(); + if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { + /* buffer has overflowed */ + i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG; + dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); + continue; + } + if (dtb > stop_tb) + break; +#ifdef CONFIG_DTL + if (dtl_consumer) + dtl_consumer(dtl, i); +#endif + stolen += tb_delta; + ++i; + ++dtl; + if (dtl == dtl_end) + dtl = local_paca->dispatch_log; + } + local_paca->dtl_ridx = i; + local_paca->dtl_curr = dtl; + return stolen; +} + +/* + * Accumulate stolen time by scanning the dispatch trace log. + * Called on entry from user mode. + */ +void notrace pseries_accumulate_stolen_time(void) +{ + u64 sst, ust; + struct cpu_accounting_data *acct = &local_paca->accounting; + + sst = scan_dispatch_log(acct->starttime_user); + ust = scan_dispatch_log(acct->starttime); + acct->stime -= sst; + acct->utime -= ust; + acct->steal_time += ust + sst; +} + +u64 pseries_calculate_stolen_time(u64 stop_tb) +{ + if (!firmware_has_feature(FW_FEATURE_SPLPAR)) + return 0; + + if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) + return scan_dispatch_log(stop_tb); + + return 0; +} + +#endif -- cgit From 2f6f19c7aaad5005dc75298a413eb0243c5d312d Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Wed, 12 Oct 2022 09:12:07 +1000 Subject: cifs: fix regression in very old smb1 mounts BZ: 215375 Fixes: 76a3c92ec9e0 ("cifs: remove support for NTLM and weaker authentication algorithms") Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/connect.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 40900aace416..e158257da1cd 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3922,12 +3922,11 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses, pSMB->AndXCommand = 0xFF; pSMB->Flags = cpu_to_le16(TCON_EXTENDED_SECINFO); bcc_ptr = &pSMB->Password[0]; - if (tcon->pipe || (ses->server->sec_mode & SECMODE_USER)) { - pSMB->PasswordLength = cpu_to_le16(1); /* minimum */ - *bcc_ptr = 0; /* password is null byte */ - bcc_ptr++; /* skip password */ - /* already aligned so no need to do it below */ - } + + pSMB->PasswordLength = cpu_to_le16(1); /* minimum */ + *bcc_ptr = 0; /* password is null byte */ + bcc_ptr++; /* skip password */ + /* already aligned so no need to do it below */ if (ses->server->sign) smb_buffer->Flags2 |= SMBFLG2_SECURITY_SIGNATURE; -- cgit From 977bb6530807a9a8e7f29d7dfba5737135b50df6 Mon Sep 17 00:00:00 2001 From: Steve French Date: Tue, 11 Oct 2022 23:26:33 -0500 Subject: smb3: clarify multichannel warning When server does not return network interfaces, clarify the message to indicate that "multichannel not available" not just that "empty network interface returned by server ..." Suggested-by: Tom Talpey Reviewed-by: Bharath SM Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 5187250c5f66..32d5387a9dde 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -550,7 +550,8 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, /* avoid spamming logs every 10 minutes, so log only in mount */ if ((ses->chan_max > 1) && in_mount) cifs_dbg(VFS, - "empty network interface list returned by server %s\n", + "multichannel not available\n" + "Empty network interface list returned by server %s\n", ses->server->hostname); rc = -EINVAL; goto out; -- cgit From 76894f3e2f71177747b8b4763fb180e800279585 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Mon, 3 Oct 2022 18:43:50 -0300 Subject: cifs: improve symlink handling for smb2+ When creating inode for symlink, the client used to send below requests to fill it in: * create+query_info+close (STATUS_STOPPED_ON_SYMLINK) * create(+reparse_flag)+query_info+close (set file attrs) * create+ioctl(get_reparse)+close (query reparse tag) and then for every access to the symlink dentry, the ->link() method would send another: * create+ioctl(get_reparse)+close (parse symlink) So, in order to improve: (i) Get rid of unnecessary roundtrips and then resolve symlinks as follows: * create+query_info+close (STATUS_STOPPED_ON_SYMLINK + parse symlink + get reparse tag) * create(+reparse_flag)+query_info+close (set file attrs) (ii) Set the resolved symlink target directly in inode->i_link and use simple_get_link() for ->link() to simply return it. Signed-off-by: Paulo Alcantara (SUSE) Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/cifsfs.c | 9 ++- fs/cifs/cifsglob.h | 46 ++++++++++---- fs/cifs/cifsproto.h | 13 ++-- fs/cifs/dir.c | 30 ++++------ fs/cifs/file.c | 41 +++++++------ fs/cifs/inode.c | 170 +++++++++++++++++++++++++++++++--------------------- fs/cifs/link.c | 107 +-------------------------------- fs/cifs/readdir.c | 2 + fs/cifs/smb1ops.c | 56 ++++++++++------- fs/cifs/smb2file.c | 127 ++++++++++++++++++++++++++++++++------- fs/cifs/smb2inode.c | 169 ++++++++++++++++++++++++++------------------------- fs/cifs/smb2ops.c | 109 +++++++-------------------------- fs/cifs/smb2pdu.h | 3 + fs/cifs/smb2proto.h | 22 +++---- 14 files changed, 451 insertions(+), 453 deletions(-) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8042d7280dec..c6ac19223ddc 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -396,6 +396,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode->epoch = 0; spin_lock_init(&cifs_inode->open_file_lock); generate_random_uuid(cifs_inode->lease_key); + cifs_inode->symlink_target = NULL; /* * Can not set i_flags here - they get immediately overwritten to zero @@ -412,7 +413,11 @@ cifs_alloc_inode(struct super_block *sb) static void cifs_free_inode(struct inode *inode) { - kmem_cache_free(cifs_inode_cachep, CIFS_I(inode)); + struct cifsInodeInfo *cinode = CIFS_I(inode); + + if (S_ISLNK(inode->i_mode)) + kfree(cinode->symlink_target); + kmem_cache_free(cifs_inode_cachep, cinode); } static void @@ -1139,7 +1144,7 @@ const struct inode_operations cifs_file_inode_ops = { }; const struct inode_operations cifs_symlink_inode_ops = { - .get_link = cifs_get_link, + .get_link = simple_get_link, .permission = cifs_permission, .listxattr = cifs_listxattr, }; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 52ddf4163b98..9c0253835f1c 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -185,6 +185,19 @@ struct cifs_cred { struct cifs_ace *aces; }; +struct cifs_open_info_data { + char *symlink_target; + union { + struct smb2_file_all_info fi; + struct smb311_posix_qinfo posix_fi; + }; +}; + +static inline void cifs_free_open_info(struct cifs_open_info_data *data) +{ + kfree(data->symlink_target); +} + /* ***************************************************************** * Except the CIFS PDUs themselves all the @@ -307,20 +320,20 @@ struct smb_version_operations { int (*is_path_accessible)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, const char *); /* query path data from the server */ - int (*query_path_info)(const unsigned int, struct cifs_tcon *, - struct cifs_sb_info *, const char *, - FILE_ALL_INFO *, bool *, bool *); + int (*query_path_info)(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse); /* query file data from the server */ - int (*query_file_info)(const unsigned int, struct cifs_tcon *, - struct cifs_fid *, FILE_ALL_INFO *); + int (*query_file_info)(const unsigned int xid, struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, struct cifs_open_info_data *data); /* query reparse tag from srv to determine which type of special file */ int (*query_reparse_tag)(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *path, __u32 *reparse_tag); /* get server index number */ - int (*get_srv_inum)(const unsigned int, struct cifs_tcon *, - struct cifs_sb_info *, const char *, - u64 *uniqueid, FILE_ALL_INFO *); + int (*get_srv_inum)(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, u64 *uniqueid, + struct cifs_open_info_data *data); /* set size by path */ int (*set_path_size)(const unsigned int, struct cifs_tcon *, const char *, __u64, struct cifs_sb_info *, bool); @@ -369,8 +382,8 @@ struct smb_version_operations { struct cifs_sb_info *, const char *, char **, bool); /* open a file for non-posix mounts */ - int (*open)(const unsigned int, struct cifs_open_parms *, - __u32 *, FILE_ALL_INFO *); + int (*open)(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, + void *buf); /* set fid protocol-specific info */ void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32); /* close a file */ @@ -1123,6 +1136,7 @@ struct cifs_fattr { struct timespec64 cf_mtime; struct timespec64 cf_ctime; u32 cf_cifstag; + char *cf_symlink_target; }; /* @@ -1385,6 +1399,7 @@ struct cifsFileInfo { struct work_struct put; /* work for the final part of _put */ struct delayed_work deferred; bool deferred_close_scheduled; /* Flag to indicate close is scheduled */ + char *symlink_target; }; struct cifs_io_parms { @@ -1543,6 +1558,7 @@ struct cifsInodeInfo { struct list_head deferred_closes; /* list of deferred closes */ spinlock_t deferred_lock; /* protection on deferred list */ bool lease_granted; /* Flag to indicate whether lease or oplock is granted. */ + char *symlink_target; }; static inline struct cifsInodeInfo * @@ -2111,4 +2127,14 @@ static inline size_t ntlmssp_workstation_name_size(const struct cifs_ses *ses) return sizeof(ses->workstation_name); } +static inline void move_cifs_info_to_smb2(struct smb2_file_all_info *dst, const FILE_ALL_INFO *src) +{ + memcpy(dst, src, (size_t)((u8 *)&src->AccessFlags - (u8 *)src)); + dst->AccessFlags = src->AccessFlags; + dst->CurrentByteOffset = src->CurrentByteOffset; + dst->Mode = src->Mode; + dst->AlignmentRequirement = src->AlignmentRequirement; + dst->FileNameLength = src->FileNameLength; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 84ec71bdfacd..83e83d8beabb 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -182,10 +182,9 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile, extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile); extern void cifs_down_write(struct rw_semaphore *sem); -extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, - struct file *file, - struct tcon_link *tlink, - __u32 oplock); +struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, + struct tcon_link *tlink, __u32 oplock, + const char *symlink_target); extern int cifs_posix_open(const char *full_path, struct inode **inode, struct super_block *sb, int mode, unsigned int f_flags, __u32 *oplock, __u16 *netfid, @@ -200,9 +199,9 @@ extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr); extern struct inode *cifs_iget(struct super_block *sb, struct cifs_fattr *fattr); -extern int cifs_get_inode_info(struct inode **inode, const char *full_path, - FILE_ALL_INFO *data, struct super_block *sb, - int xid, const struct cifs_fid *fid); +int cifs_get_inode_info(struct inode **inode, const char *full_path, + struct cifs_open_info_data *data, struct super_block *sb, int xid, + const struct cifs_fid *fid); extern int smb311_posix_get_inode_info(struct inode **pinode, const char *search_path, struct super_block *sb, unsigned int xid); extern int cifs_get_inode_info_unix(struct inode **pinode, diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index f58869306309..cbd46ac59cd2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -165,10 +165,9 @@ check_name(struct dentry *direntry, struct cifs_tcon *tcon) /* Inode operations in similar order to how they appear in Linux file fs.h */ -static int -cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, - struct tcon_link *tlink, unsigned oflags, umode_t mode, - __u32 *oplock, struct cifs_fid *fid) +static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, + struct tcon_link *tlink, unsigned int oflags, umode_t mode, __u32 *oplock, + struct cifs_fid *fid, struct cifs_open_info_data *buf) { int rc = -ENOENT; int create_options = CREATE_NOT_DIR; @@ -177,7 +176,6 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, struct cifs_tcon *tcon = tlink_tcon(tlink); const char *full_path; void *page = alloc_dentry_path(); - FILE_ALL_INFO *buf = NULL; struct inode *newinode = NULL; int disposition; struct TCP_Server_Info *server = tcon->ses->server; @@ -290,12 +288,6 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid, goto out; } - buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (buf == NULL) { - rc = -ENOMEM; - goto out; - } - /* * if we're not using unix extensions, see if we need to set * ATTR_READONLY on the create call @@ -364,8 +356,7 @@ cifs_create_get_file_info: { #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* TODO: Add support for calling POSIX query info here, but passing in fid */ - rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb, - xid, fid); + rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb, xid, fid); if (newinode) { if (server->ops->set_lease_key) server->ops->set_lease_key(newinode, fid); @@ -402,7 +393,6 @@ cifs_create_set_dentry: d_add(direntry, newinode); out: - kfree(buf); free_dentry_path(page); return rc; @@ -427,6 +417,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, struct cifs_pending_open open; __u32 oplock; struct cifsFileInfo *file_info; + struct cifs_open_info_data buf = {}; if (unlikely(cifs_forced_shutdown(CIFS_SB(inode->i_sb)))) return -EIO; @@ -484,8 +475,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, cifs_add_pending_open(&fid, tlink, &open); rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, - &oplock, &fid); - + &oplock, &fid, &buf); if (rc) { cifs_del_pending_open(&open); goto out; @@ -510,7 +500,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, file->f_op = &cifs_file_direct_ops; } - file_info = cifs_new_fileinfo(&fid, file, tlink, oplock); + file_info = cifs_new_fileinfo(&fid, file, tlink, oplock, buf.symlink_target); if (file_info == NULL) { if (server->ops->close) server->ops->close(xid, tcon, &fid); @@ -526,6 +516,7 @@ out: cifs_put_tlink(tlink); out_free_xid: free_xid(xid); + cifs_free_open_info(&buf); return rc; } @@ -547,6 +538,7 @@ int cifs_create(struct user_namespace *mnt_userns, struct inode *inode, struct TCP_Server_Info *server; struct cifs_fid fid; __u32 oplock; + struct cifs_open_info_data buf = {}; cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %pd and dentry = 0x%p\n", inode, direntry, direntry); @@ -565,11 +557,11 @@ int cifs_create(struct user_namespace *mnt_userns, struct inode *inode, if (server->ops->new_lease_key) server->ops->new_lease_key(&fid); - rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, - &oplock, &fid); + rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode, &oplock, &fid, &buf); if (!rc && server->ops->close) server->ops->close(xid, tcon, &fid); + cifs_free_open_info(&buf); cifs_put_tlink(tlink); out_free_xid: free_xid(xid); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 7d756721e1a6..dcec1690312b 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -209,16 +209,14 @@ posix_open_ret: } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ -static int -cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, - struct cifs_tcon *tcon, unsigned int f_flags, __u32 *oplock, - struct cifs_fid *fid, unsigned int xid) +static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, + struct cifs_tcon *tcon, unsigned int f_flags, __u32 *oplock, + struct cifs_fid *fid, unsigned int xid, struct cifs_open_info_data *buf) { int rc; int desired_access; int disposition; int create_options = CREATE_NOT_DIR; - FILE_ALL_INFO *buf; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; @@ -255,10 +253,6 @@ cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *ci /* BB pass O_SYNC flag through on file attributes .. BB */ - buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (!buf) - return -ENOMEM; - /* O_SYNC also has bit for O_DSYNC so following check picks up either */ if (f_flags & O_SYNC) create_options |= CREATE_WRITE_THROUGH; @@ -276,9 +270,8 @@ cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *ci oparms.reconnect = false; rc = server->ops->open(xid, &oparms, oplock, buf); - if (rc) - goto out; + return rc; /* TODO: Add support for calling posix query info but with passing in fid */ if (tcon->unix_ext) @@ -294,8 +287,6 @@ cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *ci rc = -EOPENSTALE; } -out: - kfree(buf); return rc; } @@ -325,9 +316,9 @@ cifs_down_write(struct rw_semaphore *sem) static void cifsFileInfo_put_work(struct work_struct *work); -struct cifsFileInfo * -cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, - struct tcon_link *tlink, __u32 oplock) +struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, + struct tcon_link *tlink, __u32 oplock, + const char *symlink_target) { struct dentry *dentry = file_dentry(file); struct inode *inode = d_inode(dentry); @@ -347,6 +338,15 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, return NULL; } + if (symlink_target) { + cfile->symlink_target = kstrdup(symlink_target, GFP_KERNEL); + if (!cfile->symlink_target) { + kfree(fdlocks); + kfree(cfile); + return NULL; + } + } + INIT_LIST_HEAD(&fdlocks->locks); fdlocks->cfile = cfile; cfile->llist = fdlocks; @@ -440,6 +440,7 @@ static void cifsFileInfo_put_final(struct cifsFileInfo *cifs_file) cifs_put_tlink(cifs_file->tlink); dput(cifs_file->dentry); cifs_sb_deactive(sb); + kfree(cifs_file->symlink_target); kfree(cifs_file); } @@ -572,6 +573,7 @@ int cifs_open(struct inode *inode, struct file *file) bool posix_open_ok = false; struct cifs_fid fid; struct cifs_pending_open open; + struct cifs_open_info_data data = {}; xid = get_xid(); @@ -662,15 +664,15 @@ int cifs_open(struct inode *inode, struct file *file) if (server->ops->get_lease_key) server->ops->get_lease_key(inode, &fid); - rc = cifs_nt_open(full_path, inode, cifs_sb, tcon, - file->f_flags, &oplock, &fid, xid); + rc = cifs_nt_open(full_path, inode, cifs_sb, tcon, file->f_flags, &oplock, &fid, + xid, &data); if (rc) { cifs_del_pending_open(&open); goto out; } } - cfile = cifs_new_fileinfo(&fid, file, tlink, oplock); + cfile = cifs_new_fileinfo(&fid, file, tlink, oplock, data.symlink_target); if (cfile == NULL) { if (server->ops->close) server->ops->close(xid, tcon, &fid); @@ -712,6 +714,7 @@ out: free_dentry_path(page); free_xid(xid); cifs_put_tlink(tlink); + cifs_free_open_info(&data); return rc; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index ad10c61ab5c9..be6dafcb25e3 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -210,6 +210,17 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) */ inode->i_blocks = (512 - 1 + fattr->cf_bytes) >> 9; } + + if (S_ISLNK(fattr->cf_mode)) { + kfree(cifs_i->symlink_target); + cifs_i->symlink_target = fattr->cf_symlink_target; + fattr->cf_symlink_target = NULL; + + if (unlikely(!cifs_i->symlink_target)) + inode->i_link = ERR_PTR(-EOPNOTSUPP); + else + inode->i_link = cifs_i->symlink_target; + } spin_unlock(&inode->i_lock); if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL) @@ -347,13 +358,20 @@ cifs_get_file_info_unix(struct file *filp) int rc; unsigned int xid; FILE_UNIX_BASIC_INFO find_data; - struct cifs_fattr fattr; + struct cifs_fattr fattr = {}; struct inode *inode = file_inode(filp); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsFileInfo *cfile = filp->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); xid = get_xid(); + + if (cfile->symlink_target) { + fattr.cf_symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!fattr.cf_symlink_target) + return -ENOMEM; + } + rc = CIFSSMBUnixQFileInfo(xid, tcon, cfile->fid.netfid, &find_data); if (!rc) { cifs_unix_basic_to_fattr(&fattr, &find_data, cifs_sb); @@ -378,6 +396,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, FILE_UNIX_BASIC_INFO find_data; struct cifs_fattr fattr; struct cifs_tcon *tcon; + struct TCP_Server_Info *server; struct tcon_link *tlink; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); @@ -387,10 +406,12 @@ int cifs_get_inode_info_unix(struct inode **pinode, if (IS_ERR(tlink)) return PTR_ERR(tlink); tcon = tlink_tcon(tlink); + server = tcon->ses->server; /* could have done a find first instead but this returns more info */ rc = CIFSSMBUnixQPathInfo(xid, tcon, full_path, &find_data, cifs_sb->local_nls, cifs_remap(cifs_sb)); + cifs_dbg(FYI, "%s: query path info: rc = %d\n", __func__, rc); cifs_put_tlink(tlink); if (!rc) { @@ -410,6 +431,17 @@ int cifs_get_inode_info_unix(struct inode **pinode, cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc); } + if (S_ISLNK(fattr.cf_mode) && !fattr.cf_symlink_target) { + if (!server->ops->query_symlink) + return -EOPNOTSUPP; + rc = server->ops->query_symlink(xid, tcon, cifs_sb, full_path, + &fattr.cf_symlink_target, false); + if (rc) { + cifs_dbg(FYI, "%s: query_symlink: %d\n", __func__, rc); + goto cgiiu_exit; + } + } + if (*pinode == NULL) { /* get new inode */ cifs_fill_uniqueid(sb, &fattr); @@ -432,6 +464,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, } cgiiu_exit: + kfree(fattr.cf_symlink_target); return rc; } #else @@ -601,10 +634,10 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path, } /* Fill a cifs_fattr struct with info from POSIX info struct */ -static void -smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct smb311_posix_qinfo *info, - struct super_block *sb, bool adjust_tz, bool symlink) +static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct cifs_open_info_data *data, + struct super_block *sb, bool adjust_tz, bool symlink) { + struct smb311_posix_qinfo *info = &data->posix_fi; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); @@ -639,6 +672,8 @@ smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct smb311_posix_qinfo * if (symlink) { fattr->cf_mode |= S_IFLNK; fattr->cf_dtype = DT_LNK; + fattr->cf_symlink_target = data->symlink_target; + data->symlink_target = NULL; } else if (fattr->cf_cifsattrs & ATTR_DIRECTORY) { fattr->cf_mode |= S_IFDIR; fattr->cf_dtype = DT_DIR; @@ -655,13 +690,11 @@ smb311_posix_info_to_fattr(struct cifs_fattr *fattr, struct smb311_posix_qinfo * fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink); } - -/* Fill a cifs_fattr struct with info from FILE_ALL_INFO */ -static void -cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, - struct super_block *sb, bool adjust_tz, - bool symlink, u32 reparse_tag) +static void cifs_open_info_to_fattr(struct cifs_fattr *fattr, struct cifs_open_info_data *data, + struct super_block *sb, bool adjust_tz, bool symlink, + u32 reparse_tag) { + struct smb2_file_all_info *info = &data->fi; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); @@ -703,7 +736,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, } else if (reparse_tag == IO_REPARSE_TAG_LX_BLK) { fattr->cf_mode |= S_IFBLK | cifs_sb->ctx->file_mode; fattr->cf_dtype = DT_BLK; - } else if (symlink) { /* TODO add more reparse tag checks */ + } else if (symlink || reparse_tag == IO_REPARSE_TAG_SYMLINK || + reparse_tag == IO_REPARSE_TAG_NFS) { fattr->cf_mode = S_IFLNK; fattr->cf_dtype = DT_LNK; } else if (fattr->cf_cifsattrs & ATTR_DIRECTORY) { @@ -735,6 +769,11 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info, } } + if (S_ISLNK(fattr->cf_mode)) { + fattr->cf_symlink_target = data->symlink_target; + data->symlink_target = NULL; + } + fattr->cf_uid = cifs_sb->ctx->linux_uid; fattr->cf_gid = cifs_sb->ctx->linux_gid; } @@ -744,23 +783,28 @@ cifs_get_file_info(struct file *filp) { int rc; unsigned int xid; - FILE_ALL_INFO find_data; + struct cifs_open_info_data data = {}; struct cifs_fattr fattr; struct inode *inode = file_inode(filp); struct cifsFileInfo *cfile = filp->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; + bool symlink = false; + u32 tag = 0; if (!server->ops->query_file_info) return -ENOSYS; xid = get_xid(); - rc = server->ops->query_file_info(xid, tcon, &cfile->fid, &find_data); + rc = server->ops->query_file_info(xid, tcon, cfile, &data); switch (rc) { case 0: /* TODO: add support to query reparse tag */ - cifs_all_info_to_fattr(&fattr, &find_data, inode->i_sb, false, - false, 0 /* no reparse tag */); + if (data.symlink_target) { + symlink = true; + tag = IO_REPARSE_TAG_SYMLINK; + } + cifs_open_info_to_fattr(&fattr, &data, inode->i_sb, false, symlink, tag); break; case -EREMOTE: cifs_create_dfs_fattr(&fattr, inode->i_sb); @@ -789,6 +833,7 @@ cifs_get_file_info(struct file *filp) /* if filetype is different, return error */ rc = cifs_fattr_to_inode(inode, &fattr); cgfi_exit: + cifs_free_open_info(&data); free_xid(xid); return rc; } @@ -860,14 +905,9 @@ cifs_backup_query_path_info(int xid, } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ -static void -cifs_set_fattr_ino(int xid, - struct cifs_tcon *tcon, - struct super_block *sb, - struct inode **inode, - const char *full_path, - FILE_ALL_INFO *data, - struct cifs_fattr *fattr) +static void cifs_set_fattr_ino(int xid, struct cifs_tcon *tcon, struct super_block *sb, + struct inode **inode, const char *full_path, + struct cifs_open_info_data *data, struct cifs_fattr *fattr) { struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct TCP_Server_Info *server = tcon->ses->server; @@ -885,11 +925,8 @@ cifs_set_fattr_ino(int xid, * If we have an inode pass a NULL tcon to ensure we don't * make a round trip to the server. This only works for SMB2+. */ - rc = server->ops->get_srv_inum(xid, - *inode ? NULL : tcon, - cifs_sb, full_path, - &fattr->cf_uniqueid, - data); + rc = server->ops->get_srv_inum(xid, *inode ? NULL : tcon, cifs_sb, full_path, + &fattr->cf_uniqueid, data); if (rc) { /* * If that fails reuse existing ino or generate one @@ -923,14 +960,10 @@ static inline bool is_inode_cache_good(struct inode *ino) return ino && CIFS_CACHE_READ(CIFS_I(ino)) && CIFS_I(ino)->time != 0; } -int -cifs_get_inode_info(struct inode **inode, - const char *full_path, - FILE_ALL_INFO *in_data, - struct super_block *sb, int xid, - const struct cifs_fid *fid) +int cifs_get_inode_info(struct inode **inode, const char *full_path, + struct cifs_open_info_data *data, struct super_block *sb, int xid, + const struct cifs_fid *fid) { - struct cifs_tcon *tcon; struct TCP_Server_Info *server; struct tcon_link *tlink; @@ -938,8 +971,7 @@ cifs_get_inode_info(struct inode **inode, bool adjust_tz = false; struct cifs_fattr fattr = {0}; bool is_reparse_point = false; - FILE_ALL_INFO *data = in_data; - FILE_ALL_INFO *tmp_data = NULL; + struct cifs_open_info_data tmp_data = {}; void *smb1_backup_rsp_buf = NULL; int rc = 0; int tmprc = 0; @@ -960,21 +992,15 @@ cifs_get_inode_info(struct inode **inode, cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); goto out; } - tmp_data = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (!tmp_data) { - rc = -ENOMEM; - goto out; - } - rc = server->ops->query_path_info(xid, tcon, cifs_sb, - full_path, tmp_data, - &adjust_tz, &is_reparse_point); + rc = server->ops->query_path_info(xid, tcon, cifs_sb, full_path, &tmp_data, + &adjust_tz, &is_reparse_point); #ifdef CONFIG_CIFS_DFS_UPCALL if (rc == -ENOENT && is_tcon_dfs(tcon)) rc = cifs_dfs_query_info_nonascii_quirk(xid, tcon, cifs_sb, full_path); #endif - data = tmp_data; + data = &tmp_data; } /* @@ -988,14 +1014,24 @@ cifs_get_inode_info(struct inode **inode, * since we have to check if its reparse tag matches a known * special file type e.g. symlink or fifo or char etc. */ - if ((le32_to_cpu(data->Attributes) & ATTR_REPARSE) && - server->ops->query_reparse_tag) { - rc = server->ops->query_reparse_tag(xid, tcon, cifs_sb, - full_path, &reparse_tag); - cifs_dbg(FYI, "reparse tag 0x%x\n", reparse_tag); + if (is_reparse_point && data->symlink_target) { + reparse_tag = IO_REPARSE_TAG_SYMLINK; + } else if ((le32_to_cpu(data->fi.Attributes) & ATTR_REPARSE) && + server->ops->query_reparse_tag) { + tmprc = server->ops->query_reparse_tag(xid, tcon, cifs_sb, full_path, + &reparse_tag); + if (tmprc) + cifs_dbg(FYI, "%s: query_reparse_tag: rc = %d\n", __func__, tmprc); + if (server->ops->query_symlink) { + tmprc = server->ops->query_symlink(xid, tcon, cifs_sb, full_path, + &data->symlink_target, + is_reparse_point); + if (tmprc) + cifs_dbg(FYI, "%s: query_symlink: rc = %d\n", __func__, + tmprc); + } } - cifs_all_info_to_fattr(&fattr, data, sb, adjust_tz, - is_reparse_point, reparse_tag); + cifs_open_info_to_fattr(&fattr, data, sb, adjust_tz, is_reparse_point, reparse_tag); break; case -EREMOTE: /* DFS link, no metadata available on this server */ @@ -1014,18 +1050,20 @@ cifs_get_inode_info(struct inode **inode, */ if (backup_cred(cifs_sb) && is_smb1_server(server)) { /* for easier reading */ + FILE_ALL_INFO *fi; FILE_DIRECTORY_INFO *fdi; SEARCH_ID_FULL_DIR_INFO *si; rc = cifs_backup_query_path_info(xid, tcon, sb, full_path, &smb1_backup_rsp_buf, - &data); + &fi); if (rc) goto out; - fdi = (FILE_DIRECTORY_INFO *)data; - si = (SEARCH_ID_FULL_DIR_INFO *)data; + move_cifs_info_to_smb2(&data->fi, fi); + fdi = (FILE_DIRECTORY_INFO *)fi; + si = (SEARCH_ID_FULL_DIR_INFO *)fi; cifs_dir_info_to_fattr(&fattr, fdi, cifs_sb); fattr.cf_uniqueid = le64_to_cpu(si->UniqueId); @@ -1123,7 +1161,8 @@ handle_mnt_opt: out: cifs_buf_release(smb1_backup_rsp_buf); cifs_put_tlink(tlink); - kfree(tmp_data); + cifs_free_open_info(&tmp_data); + kfree(fattr.cf_symlink_target); return rc; } @@ -1138,7 +1177,7 @@ smb311_posix_get_inode_info(struct inode **inode, bool adjust_tz = false; struct cifs_fattr fattr = {0}; bool symlink = false; - struct smb311_posix_qinfo *data = NULL; + struct cifs_open_info_data data = {}; int rc = 0; int tmprc = 0; @@ -1155,15 +1194,9 @@ smb311_posix_get_inode_info(struct inode **inode, cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); goto out; } - data = kmalloc(sizeof(struct smb311_posix_qinfo), GFP_KERNEL); - if (!data) { - rc = -ENOMEM; - goto out; - } - rc = smb311_posix_query_path_info(xid, tcon, cifs_sb, - full_path, data, - &adjust_tz, &symlink); + rc = smb311_posix_query_path_info(xid, tcon, cifs_sb, full_path, &data, &adjust_tz, + &symlink); /* * 2. Convert it to internal cifs metadata (fattr) @@ -1171,7 +1204,7 @@ smb311_posix_get_inode_info(struct inode **inode, switch (rc) { case 0: - smb311_posix_info_to_fattr(&fattr, data, sb, adjust_tz, symlink); + smb311_posix_info_to_fattr(&fattr, &data, sb, adjust_tz, symlink); break; case -EREMOTE: /* DFS link, no metadata available on this server */ @@ -1228,7 +1261,8 @@ smb311_posix_get_inode_info(struct inode **inode, } out: cifs_put_tlink(tlink); - kfree(data); + cifs_free_open_info(&data); + kfree(fattr.cf_symlink_target); return rc; } diff --git a/fs/cifs/link.c b/fs/cifs/link.c index cd29c296cec6..bd374feeccaa 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -201,40 +201,6 @@ out: return rc; } -static int -query_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const unsigned char *path, - char **symlinkinfo) -{ - int rc; - u8 *buf = NULL; - unsigned int link_len = 0; - unsigned int bytes_read = 0; - - buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - if (tcon->ses->server->ops->query_mf_symlink) - rc = tcon->ses->server->ops->query_mf_symlink(xid, tcon, - cifs_sb, path, buf, &bytes_read); - else - rc = -ENOSYS; - - if (rc) - goto out; - - if (bytes_read == 0) { /* not a symlink */ - rc = -EINVAL; - goto out; - } - - rc = parse_mf_symlink(buf, bytes_read, &link_len, symlinkinfo); -out: - kfree(buf); - return rc; -} - int check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, @@ -244,6 +210,7 @@ check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, u8 *buf = NULL; unsigned int link_len = 0; unsigned int bytes_read = 0; + char *symlink = NULL; if (!couldbe_mf_symlink(fattr)) /* it's not a symlink */ @@ -265,7 +232,7 @@ check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, if (bytes_read == 0) /* not a symlink */ goto out; - rc = parse_mf_symlink(buf, bytes_read, &link_len, NULL); + rc = parse_mf_symlink(buf, bytes_read, &link_len, &symlink); if (rc == -EINVAL) { /* it's not a symlink */ rc = 0; @@ -280,6 +247,7 @@ check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, fattr->cf_mode &= ~S_IFMT; fattr->cf_mode |= S_IFLNK | S_IRWXU | S_IRWXG | S_IRWXO; fattr->cf_dtype = DT_LNK; + fattr->cf_symlink_target = symlink; out: kfree(buf); return rc; @@ -599,75 +567,6 @@ cifs_hl_exit: return rc; } -const char * -cifs_get_link(struct dentry *direntry, struct inode *inode, - struct delayed_call *done) -{ - int rc = -ENOMEM; - unsigned int xid; - const char *full_path; - void *page; - char *target_path = NULL; - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - struct tcon_link *tlink = NULL; - struct cifs_tcon *tcon; - struct TCP_Server_Info *server; - - if (!direntry) - return ERR_PTR(-ECHILD); - - xid = get_xid(); - - tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) { - free_xid(xid); - return ERR_CAST(tlink); - } - tcon = tlink_tcon(tlink); - server = tcon->ses->server; - - page = alloc_dentry_path(); - full_path = build_path_from_dentry(direntry, page); - if (IS_ERR(full_path)) { - free_xid(xid); - cifs_put_tlink(tlink); - free_dentry_path(page); - return ERR_CAST(full_path); - } - - cifs_dbg(FYI, "Full path: %s inode = 0x%p\n", full_path, inode); - - rc = -EACCES; - /* - * First try Minshall+French Symlinks, if configured - * and fallback to UNIX Extensions Symlinks. - */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) - rc = query_mf_symlink(xid, tcon, cifs_sb, full_path, - &target_path); - - if (rc != 0 && server->ops->query_symlink) { - struct cifsInodeInfo *cifsi = CIFS_I(inode); - bool reparse_point = false; - - if (cifsi->cifsAttrs & ATTR_REPARSE) - reparse_point = true; - - rc = server->ops->query_symlink(xid, tcon, cifs_sb, full_path, - &target_path, reparse_point); - } - - free_dentry_path(page); - free_xid(xid); - cifs_put_tlink(tlink); - if (rc != 0) { - kfree(target_path); - return ERR_PTR(rc); - } - set_delayed_call(done, kfree_link, target_path); - return target_path; -} - int cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode, struct dentry *direntry, const char *symname) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 1bb4624e768b..2d75ba5aaa8a 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -1011,6 +1011,8 @@ static int cifs_filldir(char *find_entry, struct file *file, cifs_unix_basic_to_fattr(&fattr, &((FILE_UNIX_INFO *)find_entry)->basic, cifs_sb); + if (S_ISLNK(fattr.cf_mode)) + fattr.cf_flags |= CIFS_FATTR_NEED_REVAL; break; case SMB_FIND_FILE_INFO_STANDARD: cifs_std_info_to_fattr(&fattr, diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index f36b2d2d40ca..50480751e521 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -542,31 +542,32 @@ cifs_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, return rc; } -static int -cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - FILE_ALL_INFO *data, bool *adjustTZ, bool *symlink) +static int cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjustTZ, bool *symlink) { int rc; + FILE_ALL_INFO fi = {}; *symlink = false; /* could do find first instead but this returns more info */ - rc = CIFSSMBQPathInfo(xid, tcon, full_path, data, 0 /* not legacy */, - cifs_sb->local_nls, cifs_remap(cifs_sb)); + rc = CIFSSMBQPathInfo(xid, tcon, full_path, &fi, 0 /* not legacy */, cifs_sb->local_nls, + cifs_remap(cifs_sb)); /* * BB optimize code so we do not make the above call when server claims * no NT SMB support and the above call failed at least once - set flag * in tcon or mount. */ if ((rc == -EOPNOTSUPP) || (rc == -EINVAL)) { - rc = SMBQueryInformation(xid, tcon, full_path, data, - cifs_sb->local_nls, + rc = SMBQueryInformation(xid, tcon, full_path, &fi, cifs_sb->local_nls, cifs_remap(cifs_sb)); + if (!rc) + move_cifs_info_to_smb2(&data->fi, &fi); *adjustTZ = true; } - if (!rc && (le32_to_cpu(data->Attributes) & ATTR_REPARSE)) { + if (!rc && (le32_to_cpu(fi.Attributes) & ATTR_REPARSE)) { int tmprc; int oplock = 0; struct cifs_fid fid; @@ -592,10 +593,9 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, return rc; } -static int -cifs_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - u64 *uniqueid, FILE_ALL_INFO *data) +static int cifs_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + u64 *uniqueid, struct cifs_open_info_data *unused) { /* * We can not use the IndexNumber field by default from Windows or @@ -613,11 +613,22 @@ cifs_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, cifs_remap(cifs_sb)); } -static int -cifs_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_fid *fid, FILE_ALL_INFO *data) +static int cifs_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, struct cifs_open_info_data *data) { - return CIFSSMBQFileInfo(xid, tcon, fid->netfid, data); + int rc; + FILE_ALL_INFO fi = {}; + + if (cfile->symlink_target) { + data->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!data->symlink_target) + return -ENOMEM; + } + + rc = CIFSSMBQFileInfo(xid, tcon, cfile->fid.netfid, &fi); + if (!rc) + move_cifs_info_to_smb2(&data->fi, &fi); + return rc; } static void @@ -702,19 +713,20 @@ cifs_mkdir_setinfo(struct inode *inode, const char *full_path, cifsInode->cifsAttrs = dosattrs; } -static int -cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms, - __u32 *oplock, FILE_ALL_INFO *buf) +static int cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, + void *buf) { + FILE_ALL_INFO *fi = buf; + if (!(oparms->tcon->ses->capabilities & CAP_NT_SMBS)) return SMBLegacyOpen(xid, oparms->tcon, oparms->path, oparms->disposition, oparms->desired_access, oparms->create_options, - &oparms->fid->netfid, oplock, buf, + &oparms->fid->netfid, oplock, fi, oparms->cifs_sb->local_nls, cifs_remap(oparms->cifs_sb)); - return CIFS_open(xid, oparms, oplock, buf); + return CIFS_open(xid, oparms, oplock, fi); } static void diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 9dfd2dd612c2..4992b43616a7 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -20,40 +20,125 @@ #include "cifs_unicode.h" #include "fscache.h" #include "smb2proto.h" +#include "smb2status.h" -int -smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, - __u32 *oplock, FILE_ALL_INFO *buf) +static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) +{ + struct smb2_err_rsp *err = iov->iov_base; + struct smb2_symlink_err_rsp *sym = ERR_PTR(-EINVAL); + u32 len; + + if (err->ErrorContextCount) { + struct smb2_error_context_rsp *p, *end; + + len = (u32)err->ErrorContextCount * (offsetof(struct smb2_error_context_rsp, + ErrorContextData) + + sizeof(struct smb2_symlink_err_rsp)); + if (le32_to_cpu(err->ByteCount) < len || iov->iov_len < len + sizeof(*err)) + return ERR_PTR(-EINVAL); + + p = (struct smb2_error_context_rsp *)err->ErrorData; + end = (struct smb2_error_context_rsp *)((u8 *)err + iov->iov_len); + do { + if (le32_to_cpu(p->ErrorId) == SMB2_ERROR_ID_DEFAULT) { + sym = (struct smb2_symlink_err_rsp *)&p->ErrorContextData; + break; + } + cifs_dbg(FYI, "%s: skipping unhandled error context: 0x%x\n", + __func__, le32_to_cpu(p->ErrorId)); + + len = ALIGN(le32_to_cpu(p->ErrorDataLength), 8); + p = (struct smb2_error_context_rsp *)((u8 *)&p->ErrorContextData + len); + } while (p < end); + } else if (le32_to_cpu(err->ByteCount) >= sizeof(*sym) && + iov->iov_len >= SMB2_SYMLINK_STRUCT_SIZE) { + sym = (struct smb2_symlink_err_rsp *)err->ErrorData; + } + + if (!IS_ERR(sym) && (le32_to_cpu(sym->SymLinkErrorTag) != SYMLINK_ERROR_TAG || + le32_to_cpu(sym->ReparseTag) != IO_REPARSE_TAG_SYMLINK)) + sym = ERR_PTR(-EINVAL); + + return sym; +} + +int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec *iov, char **path) +{ + struct smb2_symlink_err_rsp *sym; + unsigned int sub_offs, sub_len; + unsigned int print_offs, print_len; + char *s; + + if (!cifs_sb || !iov || !iov->iov_base || !iov->iov_len || !path) + return -EINVAL; + + sym = symlink_data(iov); + if (IS_ERR(sym)) + return PTR_ERR(sym); + + sub_len = le16_to_cpu(sym->SubstituteNameLength); + sub_offs = le16_to_cpu(sym->SubstituteNameOffset); + print_len = le16_to_cpu(sym->PrintNameLength); + print_offs = le16_to_cpu(sym->PrintNameOffset); + + if (iov->iov_len < SMB2_SYMLINK_STRUCT_SIZE + sub_offs + sub_len || + iov->iov_len < SMB2_SYMLINK_STRUCT_SIZE + print_offs + print_len) + return -EINVAL; + + s = cifs_strndup_from_utf16((char *)sym->PathBuffer + sub_offs, sub_len, true, + cifs_sb->local_nls); + if (!s) + return -ENOMEM; + convert_delimiter(s, '/'); + cifs_dbg(FYI, "%s: symlink target: %s\n", __func__, s); + + *path = s; + return 0; +} + +int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, void *buf) { int rc; __le16 *smb2_path; - struct smb2_file_all_info *smb2_data = NULL; __u8 smb2_oplock; + struct cifs_open_info_data *data = buf; + struct smb2_file_all_info file_info = {}; + struct smb2_file_all_info *smb2_data = data ? &file_info : NULL; + struct kvec err_iov = {}; + int err_buftype = CIFS_NO_BUFFER; struct cifs_fid *fid = oparms->fid; struct network_resiliency_req nr_ioctl_req; smb2_path = cifs_convert_path_to_utf16(oparms->path, oparms->cifs_sb); - if (smb2_path == NULL) { - rc = -ENOMEM; - goto out; - } - - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, - GFP_KERNEL); - if (smb2_data == NULL) { - rc = -ENOMEM; - goto out; - } + if (smb2_path == NULL) + return -ENOMEM; oparms->desired_access |= FILE_READ_ATTRIBUTES; smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH; - rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, - NULL, NULL); + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL, &err_iov, + &err_buftype); + if (rc && data) { + struct smb2_hdr *hdr = err_iov.iov_base; + + if (unlikely(!err_iov.iov_base || err_buftype == CIFS_NO_BUFFER)) + rc = -ENOMEM; + else if (hdr->Status == STATUS_STOPPED_ON_SYMLINK && oparms->cifs_sb) { + rc = smb2_parse_symlink_response(oparms->cifs_sb, &err_iov, + &data->symlink_target); + if (!rc) { + memset(smb2_data, 0, sizeof(*smb2_data)); + oparms->create_options |= OPEN_REPARSE_POINT; + rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, + NULL, NULL, NULL); + oparms->create_options &= ~OPEN_REPARSE_POINT; + } + } + } + if (rc) goto out; - if (oparms->tcon->use_resilient) { /* default timeout is 0, servers pick default (120 seconds) */ nr_ioctl_req.Timeout = @@ -73,7 +158,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, rc = 0; } - if (buf) { + if (smb2_data) { /* if open response does not have IndexNumber field - get it */ if (smb2_data->IndexNumber == 0) { rc = SMB2_get_srv_num(xid, oparms->tcon, @@ -89,12 +174,12 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, rc = 0; } } - move_smb2_info_to_cifs(buf, smb2_data); + memcpy(&data->fi, smb2_data, sizeof(data->fi)); } *oplock = smb2_oplock; out: - kfree(smb2_data); + free_rsp_buf(err_buftype, err_iov.iov_base); kfree(smb2_path); return rc; } diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index bb3e3d5a0cda..adf71b328f32 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -24,6 +24,7 @@ #include "smb2pdu.h" #include "smb2proto.h" #include "cached_dir.h" +#include "smb2status.h" static void free_set_inf_compound(struct smb_rqst *rqst) @@ -50,13 +51,15 @@ struct cop_vars { /* * note: If cfile is passed, the reference to it is dropped here. * So make sure that you do not reuse cfile after return from this func. + * + * If passing @err_iov and @err_buftype, ensure to make them both large enough (>= 3) to hold all + * error responses. Caller is also responsible for freeing them up. */ -static int -smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - __u32 desired_access, __u32 create_disposition, - __u32 create_options, umode_t mode, void *ptr, int command, - struct cifsFileInfo *cfile) +static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + __u32 desired_access, __u32 create_disposition, __u32 create_options, + umode_t mode, void *ptr, int command, struct cifsFileInfo *cfile, + struct kvec *err_iov, int *err_buftype) { struct cop_vars *vars = NULL; struct kvec *rsp_iov; @@ -70,6 +73,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, int num_rqst = 0; int resp_buftype[3]; struct smb2_query_info_rsp *qi_rsp = NULL; + struct cifs_open_info_data *idata; int flags = 0; __u8 delete_pending[8] = {1, 0, 0, 0, 0, 0, 0, 0}; unsigned int size[2]; @@ -385,14 +389,19 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, switch (command) { case SMB2_OP_QUERY_INFO: + idata = ptr; + if (rc == 0 && cfile && cfile->symlink_target) { + idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!idata->symlink_target) + rc = -ENOMEM; + } if (rc == 0) { qi_rsp = (struct smb2_query_info_rsp *) rsp_iov[1].iov_base; rc = smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), le32_to_cpu(qi_rsp->OutputBufferLength), - &rsp_iov[1], sizeof(struct smb2_file_all_info), - ptr); + &rsp_iov[1], sizeof(idata->fi), (char *)&idata->fi); } if (rqst[1].rq_iov) SMB2_query_info_free(&rqst[1]); @@ -406,13 +415,19 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, tcon->tid); break; case SMB2_OP_POSIX_QUERY_INFO: + if (rc == 0 && cfile && cfile->symlink_target) { + idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!idata->symlink_target) + rc = -ENOMEM; + } if (rc == 0) { qi_rsp = (struct smb2_query_info_rsp *) rsp_iov[1].iov_base; rc = smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), le32_to_cpu(qi_rsp->OutputBufferLength), - &rsp_iov[1], sizeof(struct smb311_posix_qinfo) /* add SIDs */, ptr); + &rsp_iov[1], sizeof(idata->posix_fi) /* add SIDs */, + (char *)&idata->posix_fi); } if (rqst[1].rq_iov) SMB2_query_info_free(&rqst[1]); @@ -477,42 +492,33 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, free_set_inf_compound(rqst); break; } - free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); - free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); - free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); + + if (rc && err_iov && err_buftype) { + memcpy(err_iov, rsp_iov, 3 * sizeof(*err_iov)); + memcpy(err_buftype, resp_buftype, 3 * sizeof(*err_buftype)); + } else { + free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); + } kfree(vars); return rc; } -void -move_smb2_info_to_cifs(FILE_ALL_INFO *dst, struct smb2_file_all_info *src) -{ - memcpy(dst, src, (size_t)(&src->CurrentByteOffset) - (size_t)src); - dst->CurrentByteOffset = src->CurrentByteOffset; - dst->Mode = src->Mode; - dst->AlignmentRequirement = src->AlignmentRequirement; - dst->IndexNumber1 = 0; /* we don't use it */ -} - -int -smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - FILE_ALL_INFO *data, bool *adjust_tz, bool *reparse) +int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse) { int rc; - struct smb2_file_all_info *smb2_data; __u32 create_options = 0; struct cifsFileInfo *cfile; struct cached_fid *cfid = NULL; + struct kvec err_iov[3] = {}; + int err_buftype[3] = {}; *adjust_tz = false; *reparse = false; - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, - GFP_KERNEL); - if (smb2_data == NULL) - return -ENOMEM; - if (strcmp(full_path, "")) rc = -ENOENT; else @@ -520,63 +526,58 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, /* If it is a root and its handle is cached then use it */ if (!rc) { if (cfid->file_all_info_is_valid) { - move_smb2_info_to_cifs(data, - &cfid->file_all_info); + memcpy(&data->fi, &cfid->file_all_info, sizeof(data->fi)); } else { - rc = SMB2_query_info(xid, tcon, - cfid->fid.persistent_fid, - cfid->fid.volatile_fid, smb2_data); - if (!rc) - move_smb2_info_to_cifs(data, smb2_data); + rc = SMB2_query_info(xid, tcon, cfid->fid.persistent_fid, + cfid->fid.volatile_fid, &data->fi); } close_cached_dir(cfid); - goto out; + return rc; } cifs_get_readable_path(tcon, full_path, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, create_options, - ACL_NO_MODE, smb2_data, SMB2_OP_QUERY_INFO, cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN, + create_options, ACL_NO_MODE, data, SMB2_OP_QUERY_INFO, cfile, + err_iov, err_buftype); if (rc == -EOPNOTSUPP) { + if (err_iov[0].iov_base && err_buftype[0] != CIFS_NO_BUFFER && + ((struct smb2_hdr *)err_iov[0].iov_base)->Command == SMB2_CREATE && + ((struct smb2_hdr *)err_iov[0].iov_base)->Status == STATUS_STOPPED_ON_SYMLINK) { + rc = smb2_parse_symlink_response(cifs_sb, err_iov, &data->symlink_target); + if (rc) + goto out; + } *reparse = true; create_options |= OPEN_REPARSE_POINT; /* Failed on a symbolic link - query a reparse point info */ cifs_get_readable_path(tcon, full_path, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, - create_options, ACL_NO_MODE, - smb2_data, SMB2_OP_QUERY_INFO, cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, + FILE_OPEN, create_options, ACL_NO_MODE, data, + SMB2_OP_QUERY_INFO, cfile, NULL, NULL); } - if (rc) - goto out; - move_smb2_info_to_cifs(data, smb2_data); out: - kfree(smb2_data); + free_rsp_buf(err_buftype[0], err_iov[0].iov_base); + free_rsp_buf(err_buftype[1], err_iov[1].iov_base); + free_rsp_buf(err_buftype[2], err_iov[2].iov_base); return rc; } -int -smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - struct smb311_posix_qinfo *data, bool *adjust_tz, bool *reparse) +int smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse) { int rc; __u32 create_options = 0; struct cifsFileInfo *cfile; - struct smb311_posix_qinfo *smb2_data; + struct kvec err_iov[3] = {}; + int err_buftype[3] = {}; *adjust_tz = false; *reparse = false; - /* BB TODO: Make struct larger when add support for parsing owner SIDs */ - smb2_data = kzalloc(sizeof(struct smb311_posix_qinfo), - GFP_KERNEL); - if (smb2_data == NULL) - return -ENOMEM; - /* * BB TODO: Add support for using the cached root handle. * Create SMB2_query_posix_info worker function to do non-compounded query @@ -585,29 +586,32 @@ smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, */ cifs_get_readable_path(tcon, full_path, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, create_options, - ACL_NO_MODE, smb2_data, SMB2_OP_POSIX_QUERY_INFO, cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, FILE_OPEN, + create_options, ACL_NO_MODE, data, SMB2_OP_POSIX_QUERY_INFO, cfile, + err_iov, err_buftype); if (rc == -EOPNOTSUPP) { /* BB TODO: When support for special files added to Samba re-verify this path */ + if (err_iov[0].iov_base && err_buftype[0] != CIFS_NO_BUFFER && + ((struct smb2_hdr *)err_iov[0].iov_base)->Command == SMB2_CREATE && + ((struct smb2_hdr *)err_iov[0].iov_base)->Status == STATUS_STOPPED_ON_SYMLINK) { + rc = smb2_parse_symlink_response(cifs_sb, err_iov, &data->symlink_target); + if (rc) + goto out; + } *reparse = true; create_options |= OPEN_REPARSE_POINT; /* Failed on a symbolic link - query a reparse point info */ cifs_get_readable_path(tcon, full_path, &cfile); - rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, - FILE_READ_ATTRIBUTES, FILE_OPEN, - create_options, ACL_NO_MODE, - smb2_data, SMB2_OP_POSIX_QUERY_INFO, cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_READ_ATTRIBUTES, + FILE_OPEN, create_options, ACL_NO_MODE, data, + SMB2_OP_POSIX_QUERY_INFO, cfile, NULL, NULL); } - if (rc) - goto out; - - /* TODO: will need to allow for the 2 SIDs when add support for getting owner UID/GID */ - memcpy(data, smb2_data, sizeof(struct smb311_posix_qinfo)); out: - kfree(smb2_data); + free_rsp_buf(err_buftype[0], err_iov[0].iov_base); + free_rsp_buf(err_buftype[1], err_iov[1].iov_base); + free_rsp_buf(err_buftype[2], err_iov[2].iov_base); return rc; } @@ -619,7 +623,7 @@ smb2_mkdir(const unsigned int xid, struct inode *parent_inode, umode_t mode, return smb2_compound_op(xid, tcon, cifs_sb, name, FILE_WRITE_ATTRIBUTES, FILE_CREATE, CREATE_NOT_FILE, mode, NULL, SMB2_OP_MKDIR, - NULL); + NULL, NULL, NULL); } void @@ -641,7 +645,7 @@ smb2_mkdir_setinfo(struct inode *inode, const char *name, tmprc = smb2_compound_op(xid, tcon, cifs_sb, name, FILE_WRITE_ATTRIBUTES, FILE_CREATE, CREATE_NOT_FILE, ACL_NO_MODE, - &data, SMB2_OP_SET_INFO, cfile); + &data, SMB2_OP_SET_INFO, cfile, NULL, NULL); if (tmprc == 0) cifs_i->cifsAttrs = dosattrs; } @@ -652,7 +656,7 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, { return smb2_compound_op(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, CREATE_NOT_FILE, ACL_NO_MODE, - NULL, SMB2_OP_RMDIR, NULL); + NULL, SMB2_OP_RMDIR, NULL, NULL, NULL); } int @@ -661,7 +665,7 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name, { return smb2_compound_op(xid, tcon, cifs_sb, name, DELETE, FILE_OPEN, CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT, - ACL_NO_MODE, NULL, SMB2_OP_DELETE, NULL); + ACL_NO_MODE, NULL, SMB2_OP_DELETE, NULL, NULL, NULL); } static int @@ -680,7 +684,7 @@ smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon, } rc = smb2_compound_op(xid, tcon, cifs_sb, from_name, access, FILE_OPEN, 0, ACL_NO_MODE, smb2_to_name, - command, cfile); + command, cfile, NULL, NULL); smb2_rename_path: kfree(smb2_to_name); return rc; @@ -720,7 +724,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); return smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_WRITE_DATA, FILE_OPEN, 0, ACL_NO_MODE, - &eof, SMB2_OP_SET_EOF, cfile); + &eof, SMB2_OP_SET_EOF, cfile, NULL, NULL); } int @@ -746,7 +750,8 @@ smb2_set_file_info(struct inode *inode, const char *full_path, cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile); rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, FILE_WRITE_ATTRIBUTES, FILE_OPEN, - 0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, cfile); + 0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, cfile, + NULL, NULL); cifs_put_tlink(tlink); return rc; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 32d5387a9dde..73e951e9858c 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -831,33 +831,25 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, return rc; } -static int -smb2_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, const char *full_path, - u64 *uniqueid, FILE_ALL_INFO *data) +static int smb2_get_srv_inum(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + u64 *uniqueid, struct cifs_open_info_data *data) { - *uniqueid = le64_to_cpu(data->IndexNumber); + *uniqueid = le64_to_cpu(data->fi.IndexNumber); return 0; } -static int -smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_fid *fid, FILE_ALL_INFO *data) +static int smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, struct cifs_open_info_data *data) { - int rc; - struct smb2_file_all_info *smb2_data; + struct cifs_fid *fid = &cfile->fid; - smb2_data = kzalloc(sizeof(struct smb2_file_all_info) + PATH_MAX * 2, - GFP_KERNEL); - if (smb2_data == NULL) - return -ENOMEM; - - rc = SMB2_query_info(xid, tcon, fid->persistent_fid, fid->volatile_fid, - smb2_data); - if (!rc) - move_smb2_info_to_cifs(data, smb2_data); - kfree(smb2_data); - return rc; + if (cfile->symlink_target) { + data->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); + if (!data->symlink_target) + return -ENOMEM; + } + return SMB2_query_info(xid, tcon, fid->persistent_fid, fid->volatile_fid, &data->fi); } #ifdef CONFIG_CIFS_XATTR @@ -2828,9 +2820,6 @@ parse_reparse_point(struct reparse_data_buffer *buf, } } -#define SMB2_SYMLINK_STRUCT_SIZE \ - (sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp)) - static int smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, @@ -2842,13 +2831,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_fid fid; struct kvec err_iov = {NULL, 0}; - struct smb2_err_rsp *err_buf = NULL; - struct smb2_symlink_err_rsp *symlink; struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses); - unsigned int sub_len; - unsigned int sub_offset; - unsigned int print_len; - unsigned int print_offset; int flags = CIFS_CP_CREATE_CLOSE_OP; struct smb_rqst rqst[3]; int resp_buftype[3]; @@ -2965,47 +2948,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, goto querty_exit; } - err_buf = err_iov.iov_base; - if (le32_to_cpu(err_buf->ByteCount) < sizeof(struct smb2_symlink_err_rsp) || - err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE) { - rc = -EINVAL; - goto querty_exit; - } - - symlink = (struct smb2_symlink_err_rsp *)err_buf->ErrorData; - if (le32_to_cpu(symlink->SymLinkErrorTag) != SYMLINK_ERROR_TAG || - le32_to_cpu(symlink->ReparseTag) != IO_REPARSE_TAG_SYMLINK) { - rc = -EINVAL; - goto querty_exit; - } - - /* open must fail on symlink - reset rc */ - rc = 0; - sub_len = le16_to_cpu(symlink->SubstituteNameLength); - sub_offset = le16_to_cpu(symlink->SubstituteNameOffset); - print_len = le16_to_cpu(symlink->PrintNameLength); - print_offset = le16_to_cpu(symlink->PrintNameOffset); - - if (err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE + sub_offset + sub_len) { - rc = -EINVAL; - goto querty_exit; - } - - if (err_iov.iov_len < - SMB2_SYMLINK_STRUCT_SIZE + print_offset + print_len) { - rc = -EINVAL; - goto querty_exit; - } - - *target_path = cifs_strndup_from_utf16( - (char *)symlink->PathBuffer + sub_offset, - sub_len, true, cifs_sb->local_nls); - if (!(*target_path)) { - rc = -ENOMEM; - goto querty_exit; - } - convert_delimiter(*target_path, '/'); - cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); + rc = smb2_parse_symlink_response(cifs_sb, &err_iov, target_path); querty_exit: cifs_dbg(FYI, "query symlink rc %d\n", rc); @@ -5115,7 +5058,7 @@ smb2_make_node(unsigned int xid, struct inode *inode, { struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); int rc = -EPERM; - FILE_ALL_INFO *buf = NULL; + struct cifs_open_info_data buf = {}; struct cifs_io_parms io_parms = {0}; __u32 oplock = 0; struct cifs_fid fid; @@ -5131,7 +5074,7 @@ smb2_make_node(unsigned int xid, struct inode *inode, * and was used by default in earlier versions of Windows */ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) - goto out; + return rc; /* * TODO: Add ability to create instead via reparse point. Windows (e.g. @@ -5140,16 +5083,10 @@ smb2_make_node(unsigned int xid, struct inode *inode, */ if (!S_ISCHR(mode) && !S_ISBLK(mode)) - goto out; + return rc; cifs_dbg(FYI, "sfu compat create special file\n"); - buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (buf == NULL) { - rc = -ENOMEM; - goto out; - } - oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_WRITE; @@ -5164,21 +5101,21 @@ smb2_make_node(unsigned int xid, struct inode *inode, oplock = REQ_OPLOCK; else oplock = 0; - rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf); + rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf); if (rc) - goto out; + return rc; /* * BB Do not bother to decode buf since no local inode yet to put * timestamps in, but we can reuse it safely. */ - pdev = (struct win_dev *)buf; + pdev = (struct win_dev *)&buf.fi; io_parms.pid = current->tgid; io_parms.tcon = tcon; io_parms.offset = 0; io_parms.length = sizeof(struct win_dev); - iov[1].iov_base = buf; + iov[1].iov_base = &buf.fi; iov[1].iov_len = sizeof(struct win_dev); if (S_ISCHR(mode)) { memcpy(pdev->type, "IntxCHR", 8); @@ -5197,8 +5134,8 @@ smb2_make_node(unsigned int xid, struct inode *inode, d_drop(dentry); /* FIXME: add code here to set EAs */ -out: - kfree(buf); + + cifs_free_open_info(&buf); return rc; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index f57881b8464f..1237bb86e93a 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -56,6 +56,9 @@ struct smb2_rdma_crypto_transform { #define COMPOUND_FID 0xFFFFFFFFFFFFFFFFULL +#define SMB2_SYMLINK_STRUCT_SIZE \ + (sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp)) + #define SYMLINK_ERROR_TAG 0x4c4d5953 struct smb2_symlink_err_rsp { diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 3f740f24b96a..7818d0b83567 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -53,16 +53,12 @@ extern bool smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv); extern int smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid); - -extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst, - struct smb2_file_all_info *src); extern int smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *path, __u32 *reparse_tag); -extern int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, - const char *full_path, FILE_ALL_INFO *data, - bool *adjust_tz, bool *symlink); +int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse); extern int smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon, const char *full_path, __u64 size, struct cifs_sb_info *cifs_sb, bool set_alloc); @@ -95,9 +91,9 @@ extern int smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const unsigned char *path, char *pbuf, unsigned int *pbytes_read); -extern int smb2_open_file(const unsigned int xid, - struct cifs_open_parms *oparms, - __u32 *oplock, FILE_ALL_INFO *buf); +int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec *iov, char **path); +int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, + void *buf); extern int smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, const unsigned int xid); extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile); @@ -278,9 +274,9 @@ extern int smb2_query_info_compound(const unsigned int xid, struct kvec *rsp, int *buftype, struct cifs_sb_info *cifs_sb); /* query path info from the server using SMB311 POSIX extensions*/ -extern int smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, - struct cifs_sb_info *sb, const char *path, struct smb311_posix_qinfo *qinf, - bool *adjust_tx, bool *symlink); +int smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, const char *full_path, + struct cifs_open_info_data *data, bool *adjust_tz, bool *reparse); int posix_info_parse(const void *beg, const void *end, struct smb2_posix_info_parsed *out); int posix_info_sid_size(const void *beg, const void *end); -- cgit From 69ccafdd35cdffd72504bfed58dcaee5e73a88a7 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Tue, 4 Oct 2022 15:10:09 -0300 Subject: cifs: fix uninitialised var in smb2_compound_op() Fix uninitialised variable @idata when calling smb2_compound_op() with SMB2_OP_POSIX_QUERY_INFO. Reported-by: kernel test robot Signed-off-by: Paulo Alcantara (SUSE) Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/smb2inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index adf71b328f32..a6640e6ea58b 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -415,6 +415,7 @@ static int smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, tcon->tid); break; case SMB2_OP_POSIX_QUERY_INFO: + idata = ptr; if (rc == 0 && cfile && cfile->symlink_target) { idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); if (!idata->symlink_target) -- cgit From 9ee2afe5207b63b20426ee081f486d831bae871d Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Thu, 6 Oct 2022 13:04:05 -0300 Subject: cifs: prevent copying past input buffer boundaries Prevent copying past @data buffer in smb2_validate_and_copy_iov() as the output buffer in @iov might be potentially bigger and thus copying more bytes than requested in @minbufsize. Signed-off-by: Paulo Alcantara (SUSE) Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index b3c4d2e54eaa..a3b77df2848c 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3485,7 +3485,7 @@ smb2_validate_and_copy_iov(unsigned int offset, unsigned int buffer_length, if (rc) return rc; - memcpy(data, begin_of_buf, buffer_length); + memcpy(data, begin_of_buf, minbufsize); return 0; } @@ -3609,7 +3609,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, rc = smb2_validate_and_copy_iov(le16_to_cpu(rsp->OutputBufferOffset), le32_to_cpu(rsp->OutputBufferLength), - &rsp_iov, min_len, *data); + &rsp_iov, dlen ? *dlen : min_len, *data); if (rc && allocated) { kfree(*data); *data = NULL; -- cgit From ebe98f1447bbccf8228335c62d86af02a0ed23f7 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Thu, 6 Oct 2022 00:14:31 -0500 Subject: cifs: enable caching of directories for which a lease is held This expands the directory caching to now cache an open handle for all directories (up to a maximum) and not just the root directory. In this patch, locking and refcounting is intended to work as so: The main function to get a reference to a cached handle is find_or_create_cached_dir() called from open_cached_dir() These functions are protected under the cfid_list_lock spin-lock to make sure we do not race creating new references for cached dirs with deletion of expired ones. An successful open_cached_dir() will take out 2 references to the cfid if this was the very first and successful call to open the directory and it acquired a lease from the server. One reference is for the lease and the other is for the cfid that we return. The is lease reference is tracked by cfid->has_lease. If the directory already has a handle with an active lease, then we just take out one new reference for the cfid and return it. It can happen that we have a thread that tries to open a cached directory where we have a cfid already but we do not, yet, have a working lease. In this case we will just return NULL, and this the caller will fall back to the case when no handle was available. In this model the total number of references we have on a cfid is 1 for while the handle is open and we have a lease, and one additional reference for each open instance of a cfid. Once we get a lease break (cached_dir_lease_break()) we remove the cfid from the list under the spinlock. This prevents any new threads to use it, and we also call smb2_cached_lease_break() via the work_queue in order to drop the reference we got for the lease (we drop it outside of the spin-lock.) Anytime a thread calls close_cached_dir() we also drop a reference to the cfid. When the last reference to the cfid is released smb2_close_cached_fid() will be invoked which will drop the reference ot the dentry we held for this cfid and it will also, if we the handle is open/has a lease also call SMB2_close() to close the handle on the server. Two events require special handling: invalidate_all_cached_dirs() this function is called from SMB2_tdis() and cifs_mark_open_files_invalid(). In both cases the tcon is either gone already or will be shortly so we do not need to actually close the handles. They will be dropped server side as part of the tcon dropping. But we have to be careful about a potential race with a concurrent lease break so we need to take out additional refences to avoid the cfid from being freed while we are still referencing it. free_cached_dirs() which is called from tconInfoFree(). This is called quite late in the umount process so there should no longer be any open handles or files and we can just free all the remaining data. Signed-off-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/cached_dir.c | 428 +++++++++++++++++++++++++++++---------------------- fs/cifs/cached_dir.h | 20 ++- fs/cifs/inode.c | 6 +- fs/cifs/smb2ops.c | 2 +- 4 files changed, 263 insertions(+), 193 deletions(-) diff --git a/fs/cifs/cached_dir.c b/fs/cifs/cached_dir.c index b705dac383f9..e5573d4e2d83 100644 --- a/fs/cifs/cached_dir.c +++ b/fs/cifs/cached_dir.c @@ -11,7 +11,53 @@ #include "smb2proto.h" #include "cached_dir.h" -struct cached_fid *init_cached_dir(const char *path); +static struct cached_fid *init_cached_dir(const char *path); +static void free_cached_dir(struct cached_fid *cfid); + +static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, + const char *path, + bool lookup_only) +{ + struct cached_fid *cfid; + + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry(cfid, &cfids->entries, entry) { + if (!strcmp(cfid->path, path)) { + /* + * If it doesn't have a lease it is either not yet + * fully cached or it may be in the process of + * being deleted due to a lease break. + */ + if (!cfid->has_lease) { + spin_unlock(&cfids->cfid_list_lock); + return NULL; + } + kref_get(&cfid->refcount); + spin_unlock(&cfids->cfid_list_lock); + return cfid; + } + } + if (lookup_only) { + spin_unlock(&cfids->cfid_list_lock); + return NULL; + } + if (cfids->num_entries >= MAX_CACHED_FIDS) { + spin_unlock(&cfids->cfid_list_lock); + return NULL; + } + cfid = init_cached_dir(path); + if (cfid == NULL) { + spin_unlock(&cfids->cfid_list_lock); + return NULL; + } + cfid->cfids = cfids; + cfids->num_entries++; + list_add(&cfid->entry, &cfids->entries); + cfid->on_list = true; + kref_get(&cfid->refcount); + spin_unlock(&cfids->cfid_list_lock); + return cfid; +} /* * Open the and cache a directory handle. @@ -33,61 +79,65 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; struct kvec qi_iov[1]; int rc, flags = 0; - __le16 utf16_path = 0; /* Null - since an open of top of share */ + __le16 *utf16_path = NULL; u8 oplock = SMB2_OPLOCK_LEVEL_II; struct cifs_fid *pfid; - struct dentry *dentry; + struct dentry *dentry = NULL; struct cached_fid *cfid; + struct cached_fids *cfids; - if (tcon == NULL || tcon->nohandlecache || + + if (tcon == NULL || tcon->cfids == NULL || tcon->nohandlecache || is_smb1_server(tcon->ses->server)) return -EOPNOTSUPP; ses = tcon->ses; server = ses->server; + cfids = tcon->cfids; + + if (!server->ops->new_lease_key) + return -EIO; if (cifs_sb->root == NULL) return -ENOENT; + /* + * TODO: for better caching we need to find and use the dentry also + * for non-root directories. + */ if (!path[0]) dentry = cifs_sb->root; - else - return -ENOENT; - cfid = tcon->cfids->cfid; - if (cfid == NULL) { - cfid = init_cached_dir(path); - tcon->cfids->cfid = cfid; - } - if (cfid == NULL) + utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); + if (!utf16_path) return -ENOMEM; - mutex_lock(&cfid->fid_mutex); - if (cfid->is_valid) { - cifs_dbg(FYI, "found a cached root file handle\n"); + cfid = find_or_create_cached_dir(cfids, path, lookup_only); + if (cfid == NULL) { + kfree(utf16_path); + return -ENOENT; + } + /* + * At this point we either have a lease already and we can just + * return it. If not we are guaranteed to be the only thread accessing + * this cfid. + */ + if (cfid->has_lease) { *ret_cfid = cfid; - kref_get(&cfid->refcount); - mutex_unlock(&cfid->fid_mutex); + kfree(utf16_path); return 0; } /* * We do not hold the lock for the open because in case - * SMB2_open needs to reconnect, it will end up calling - * cifs_mark_open_files_invalid() which takes the lock again - * thus causing a deadlock + * SMB2_open needs to reconnect. + * This is safe because no other thread will be able to get a ref + * to the cfid until we have finished opening the file and (possibly) + * acquired a lease. */ - mutex_unlock(&cfid->fid_mutex); - - if (lookup_only) - return -ENOENT; - if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; - if (!server->ops->new_lease_key) - return -EIO; - pfid = &cfid->fid; server->ops->new_lease_key(pfid); @@ -108,7 +158,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, oparms.reconnect = false; rc = SMB2_open_init(tcon, server, - &rqst[0], &oplock, &oparms, &utf16_path); + &rqst[0], &oplock, &oparms, utf16_path); if (rc) goto oshr_free; smb2_set_next_command(tcon, &rqst[0]); @@ -131,47 +181,13 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, rc = compound_send_recv(xid, ses, server, flags, 2, rqst, resp_buftype, rsp_iov); - mutex_lock(&cfid->fid_mutex); - - /* - * Now we need to check again as the cached root might have - * been successfully re-opened from a concurrent process - */ - - if (cfid->is_valid) { - /* work was already done */ - - /* stash fids for close() later */ - struct cifs_fid fid = { - .persistent_fid = pfid->persistent_fid, - .volatile_fid = pfid->volatile_fid, - }; - - /* - * caller expects this func to set the fid in cfid to valid - * cached root, so increment the refcount. - */ - kref_get(&cfid->refcount); - - mutex_unlock(&cfid->fid_mutex); - - if (rc == 0) { - /* close extra handle outside of crit sec */ - SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); - } - rc = 0; - goto oshr_free; - } - - /* Cached root is still invalid, continue normaly */ - if (rc) { if (rc == -EREMCHG) { tcon->need_reconnect = true; pr_warn_once("server share %s deleted\n", tcon->tree_name); } - goto oshr_exit; + goto oshr_free; } atomic_inc(&tcon->num_remote_opens); @@ -184,46 +200,54 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, #endif /* CIFS_DEBUG2 */ cfid->tcon = tcon; - cfid->is_valid = true; - cfid->dentry = dentry; - if (dentry) + if (dentry) { + cfid->dentry = dentry; dget(dentry); - kref_init(&cfid->refcount); - + } /* BB TBD check to see if oplock level check can be removed below */ - if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { - /* - * See commit 2f94a3125b87. Increment the refcount when we - * get a lease for root, release it if lease break occurs - */ - kref_get(&cfid->refcount); - cfid->has_lease = true; - smb2_parse_contexts(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key, &oplock, - NULL, NULL); - } else - goto oshr_exit; + if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) + goto oshr_free; + + + smb2_parse_contexts(server, o_rsp, + &oparms.fid->epoch, + oparms.fid->lease_key, &oplock, + NULL, NULL); qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) - goto oshr_exit; + goto oshr_free; if (!smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), sizeof(struct smb2_file_all_info), &rsp_iov[1], sizeof(struct smb2_file_all_info), (char *)&cfid->file_all_info)) cfid->file_all_info_is_valid = true; - cfid->time = jiffies; + cfid->is_open = true; + cfid->has_lease = true; -oshr_exit: - mutex_unlock(&cfid->fid_mutex); oshr_free: + kfree(utf16_path); SMB2_open_free(&rqst[0]); SMB2_query_info_free(&rqst[1]); free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + spin_lock(&cfids->cfid_list_lock); + if (!cfid->has_lease) { + if (cfid->on_list) { + list_del(&cfid->entry); + cfid->on_list = false; + cfids->num_entries--; + } + rc = -ENOENT; + } + spin_unlock(&cfids->cfid_list_lock); + if (rc) { + free_cached_dir(cfid); + cfid = NULL; + } + if (rc == 0) *ret_cfid = cfid; @@ -235,20 +259,22 @@ int open_cached_dir_by_dentry(struct cifs_tcon *tcon, struct cached_fid **ret_cfid) { struct cached_fid *cfid; + struct cached_fids *cfids = tcon->cfids; - cfid = tcon->cfids->cfid; - if (cfid == NULL) + if (cfids == NULL) return -ENOENT; - mutex_lock(&cfid->fid_mutex); - if (cfid->dentry == dentry) { - cifs_dbg(FYI, "found a cached root file handle by dentry\n"); - *ret_cfid = cfid; - kref_get(&cfid->refcount); - mutex_unlock(&cfid->fid_mutex); - return 0; + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry(cfid, &cfids->entries, entry) { + if (dentry && cfid->dentry == dentry) { + cifs_dbg(FYI, "found a cached root file handle by dentry\n"); + kref_get(&cfid->refcount); + *ret_cfid = cfid; + spin_unlock(&cfids->cfid_list_lock); + return 0; + } } - mutex_unlock(&cfid->fid_mutex); + spin_unlock(&cfids->cfid_list_lock); return -ENOENT; } @@ -257,63 +283,29 @@ smb2_close_cached_fid(struct kref *ref) { struct cached_fid *cfid = container_of(ref, struct cached_fid, refcount); - struct cached_dirent *dirent, *q; - if (cfid->is_valid) { - cifs_dbg(FYI, "clear cached root file handle\n"); - SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, - cfid->fid.volatile_fid); + spin_lock(&cfid->cfids->cfid_list_lock); + if (cfid->on_list) { + list_del(&cfid->entry); + cfid->on_list = false; + cfid->cfids->num_entries--; } + spin_unlock(&cfid->cfids->cfid_list_lock); - /* - * We only check validity above to send SMB2_close, - * but we still need to invalidate these entries - * when this function is called - */ - cfid->is_valid = false; - cfid->file_all_info_is_valid = false; - cfid->has_lease = false; - if (cfid->dentry) { - dput(cfid->dentry); - cfid->dentry = NULL; - } - /* - * Delete all cached dirent names - */ - mutex_lock(&cfid->dirents.de_mutex); - list_for_each_entry_safe(dirent, q, &cfid->dirents.entries, entry) { - list_del(&dirent->entry); - kfree(dirent->name); - kfree(dirent); + dput(cfid->dentry); + cfid->dentry = NULL; + + if (cfid->is_open) { + SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, + cfid->fid.volatile_fid); } - cfid->dirents.is_valid = 0; - cfid->dirents.is_failed = 0; - cfid->dirents.ctx = NULL; - cfid->dirents.pos = 0; - mutex_unlock(&cfid->dirents.de_mutex); + free_cached_dir(cfid); } void close_cached_dir(struct cached_fid *cfid) { - mutex_lock(&cfid->fid_mutex); kref_put(&cfid->refcount, smb2_close_cached_fid); - mutex_unlock(&cfid->fid_mutex); -} - -void close_cached_dir_lease_locked(struct cached_fid *cfid) -{ - if (cfid->has_lease) { - cfid->has_lease = false; - kref_put(&cfid->refcount, smb2_close_cached_fid); - } -} - -void close_cached_dir_lease(struct cached_fid *cfid) -{ - mutex_lock(&cfid->fid_mutex); - close_cached_dir_lease_locked(cfid); - mutex_unlock(&cfid->fid_mutex); } /* @@ -326,41 +318,62 @@ void close_all_cached_dirs(struct cifs_sb_info *cifs_sb) struct cached_fid *cfid; struct cifs_tcon *tcon; struct tcon_link *tlink; + struct cached_fids *cfids; for (node = rb_first(root); node; node = rb_next(node)) { tlink = rb_entry(node, struct tcon_link, tl_rbnode); tcon = tlink_tcon(tlink); if (IS_ERR(tcon)) continue; - cfid = tcon->cfids->cfid; - if (cfid == NULL) + cfids = tcon->cfids; + if (cfids == NULL) continue; - mutex_lock(&cfid->fid_mutex); - if (cfid->dentry) { + list_for_each_entry(cfid, &cfids->entries, entry) { dput(cfid->dentry); cfid->dentry = NULL; } - mutex_unlock(&cfid->fid_mutex); } } /* - * Invalidate and close all cached dirs when a TCON has been reset + * Invalidate all cached dirs when a TCON has been reset * due to a session loss. */ void invalidate_all_cached_dirs(struct cifs_tcon *tcon) { - struct cached_fid *cfid = tcon->cfids->cfid; - - if (cfid == NULL) - return; - - mutex_lock(&cfid->fid_mutex); - cfid->is_valid = false; - /* cached handle is not valid, so SMB2_CLOSE won't be sent below */ - close_cached_dir_lease_locked(cfid); - memset(&cfid->fid, 0, sizeof(struct cifs_fid)); - mutex_unlock(&cfid->fid_mutex); + struct cached_fids *cfids = tcon->cfids; + struct cached_fid *cfid, *q; + struct list_head entry; + + INIT_LIST_HEAD(&entry); + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { + list_del(&cfid->entry); + list_add(&cfid->entry, &entry); + cfids->num_entries--; + cfid->is_open = false; + /* To prevent race with smb2_cached_lease_break() */ + kref_get(&cfid->refcount); + } + spin_unlock(&cfids->cfid_list_lock); + + list_for_each_entry_safe(cfid, q, &entry, entry) { + cfid->on_list = false; + list_del(&cfid->entry); + cancel_work_sync(&cfid->lease_break); + if (cfid->has_lease) { + /* + * We lease was never cancelled from the server so we + * need to drop the reference. + */ + spin_lock(&cfids->cfid_list_lock); + cfid->has_lease = false; + spin_unlock(&cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); + } + /* Drop the extra reference opened above*/ + kref_put(&cfid->refcount, smb2_close_cached_fid); + } } static void @@ -369,51 +382,83 @@ smb2_cached_lease_break(struct work_struct *work) struct cached_fid *cfid = container_of(work, struct cached_fid, lease_break); - close_cached_dir_lease(cfid); + spin_lock(&cfid->cfids->cfid_list_lock); + cfid->has_lease = false; + spin_unlock(&cfid->cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); } int cached_dir_lease_break(struct cifs_tcon *tcon, __u8 lease_key[16]) { - struct cached_fid *cfid = tcon->cfids->cfid; + struct cached_fids *cfids = tcon->cfids; + struct cached_fid *cfid; - if (cfid == NULL) + if (cfids == NULL) return false; - if (cfid->is_valid && - !memcmp(lease_key, - cfid->fid.lease_key, - SMB2_LEASE_KEY_SIZE)) { - cfid->time = 0; - INIT_WORK(&cfid->lease_break, - smb2_cached_lease_break); - queue_work(cifsiod_wq, - &cfid->lease_break); - return true; + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry(cfid, &cfids->entries, entry) { + if (cfid->has_lease && + !memcmp(lease_key, + cfid->fid.lease_key, + SMB2_LEASE_KEY_SIZE)) { + cfid->time = 0; + /* + * We found a lease remove it from the list + * so no threads can access it. + */ + list_del(&cfid->entry); + cfid->on_list = false; + cfids->num_entries--; + + queue_work(cifsiod_wq, + &cfid->lease_break); + spin_unlock(&cfids->cfid_list_lock); + return true; + } } + spin_unlock(&cfids->cfid_list_lock); return false; } -struct cached_fid *init_cached_dir(const char *path) +static struct cached_fid *init_cached_dir(const char *path) { struct cached_fid *cfid; - cfid = kzalloc(sizeof(*cfid), GFP_KERNEL); + cfid = kzalloc(sizeof(*cfid), GFP_ATOMIC); if (!cfid) return NULL; - cfid->path = kstrdup(path, GFP_KERNEL); + cfid->path = kstrdup(path, GFP_ATOMIC); if (!cfid->path) { kfree(cfid); return NULL; } + INIT_WORK(&cfid->lease_break, smb2_cached_lease_break); + INIT_LIST_HEAD(&cfid->entry); INIT_LIST_HEAD(&cfid->dirents.entries); mutex_init(&cfid->dirents.de_mutex); - mutex_init(&cfid->fid_mutex); + spin_lock_init(&cfid->fid_lock); + kref_init(&cfid->refcount); return cfid; } -void free_cached_dir(struct cached_fid *cfid) +static void free_cached_dir(struct cached_fid *cfid) { + struct cached_dirent *dirent, *q; + + dput(cfid->dentry); + cfid->dentry = NULL; + + /* + * Delete all cached dirent names + */ + list_for_each_entry_safe(dirent, q, &cfid->dirents.entries, entry) { + list_del(&dirent->entry); + kfree(dirent->name); + kfree(dirent); + } + kfree(cfid->path); cfid->path = NULL; kfree(cfid); @@ -426,15 +471,34 @@ struct cached_fids *init_cached_dirs(void) cfids = kzalloc(sizeof(*cfids), GFP_KERNEL); if (!cfids) return NULL; - mutex_init(&cfids->cfid_list_mutex); + spin_lock_init(&cfids->cfid_list_lock); + INIT_LIST_HEAD(&cfids->entries); return cfids; } +/* + * Called from tconInfoFree when we are tearing down the tcon. + * There are no active users or open files/directories at this point. + */ void free_cached_dirs(struct cached_fids *cfids) { - if (cfids->cfid) { - free_cached_dir(cfids->cfid); - cfids->cfid = NULL; + struct cached_fid *cfid, *q; + struct list_head entry; + + INIT_LIST_HEAD(&entry); + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { + cfid->on_list = false; + cfid->is_open = false; + list_del(&cfid->entry); + list_add(&cfid->entry, &entry); } + spin_unlock(&cfids->cfid_list_lock); + + list_for_each_entry_safe(cfid, q, &entry, entry) { + list_del(&cfid->entry); + free_cached_dir(cfid); + } + kfree(cfids); } diff --git a/fs/cifs/cached_dir.h b/fs/cifs/cached_dir.h index bdf6c3866653..e536304ca2ce 100644 --- a/fs/cifs/cached_dir.h +++ b/fs/cifs/cached_dir.h @@ -31,14 +31,17 @@ struct cached_dirents { }; struct cached_fid { + struct list_head entry; + struct cached_fids *cfids; const char *path; - bool is_valid:1; /* Do we have a useable root fid */ - bool file_all_info_is_valid:1; bool has_lease:1; + bool is_open:1; + bool on_list:1; + bool file_all_info_is_valid:1; unsigned long time; /* jiffies of when lease was taken */ struct kref refcount; struct cifs_fid fid; - struct mutex fid_mutex; + spinlock_t fid_lock; struct cifs_tcon *tcon; struct dentry *dentry; struct work_struct lease_break; @@ -46,9 +49,14 @@ struct cached_fid { struct cached_dirents dirents; }; +#define MAX_CACHED_FIDS 16 struct cached_fids { - struct mutex cfid_list_mutex; - struct cached_fid *cfid; + /* Must be held when: + * - accessing the cfids->entries list + */ + spinlock_t cfid_list_lock; + int num_entries; + struct list_head entries; }; extern struct cached_fids *init_cached_dirs(void); @@ -61,8 +69,6 @@ extern int open_cached_dir_by_dentry(struct cifs_tcon *tcon, struct dentry *dentry, struct cached_fid **cfid); extern void close_cached_dir(struct cached_fid *cfid); -extern void close_cached_dir_lease(struct cached_fid *cfid); -extern void close_cached_dir_lease_locked(struct cached_fid *cfid); extern void close_all_cached_dirs(struct cifs_sb_info *cifs_sb); extern void invalidate_all_cached_dirs(struct cifs_tcon *tcon); extern int cached_dir_lease_break(struct cifs_tcon *tcon, __u8 lease_key[16]); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index be6dafcb25e3..7cf96e581d24 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2299,13 +2299,13 @@ cifs_dentry_needs_reval(struct dentry *dentry) return true; if (!open_cached_dir_by_dentry(tcon, dentry->d_parent, &cfid)) { - mutex_lock(&cfid->fid_mutex); + spin_lock(&cfid->fid_lock); if (cfid->time && cifs_i->time > cfid->time) { - mutex_unlock(&cfid->fid_mutex); + spin_unlock(&cfid->fid_lock); close_cached_dir(cfid); return false; } - mutex_unlock(&cfid->fid_mutex); + spin_unlock(&cfid->fid_lock); close_cached_dir(cfid); } /* diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 73e951e9858c..b907d1fab8d9 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -801,7 +801,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, rc = open_cached_dir(xid, tcon, full_path, cifs_sb, true, &cfid); if (!rc) { - if (cfid->is_valid) { + if (cfid->has_lease) { close_cached_dir(cfid); return 0; } -- cgit From e4029e072673d8a694f660f551609dd4f9265088 Mon Sep 17 00:00:00 2001 From: Ronnie Sahlberg Date: Wed, 12 Oct 2022 06:13:03 -0500 Subject: cifs: find and use the dentry for cached non-root directories also This allows us to use cached attributes for the entries in a cached directory for as long as a lease is held on the directory itself. Previously we have always allowed "used cached attributes for 1 second" but this extends this to the lifetime of the lease as well as making the caching safer. Signed-off-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/cached_dir.c | 63 ++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 49 insertions(+), 14 deletions(-) diff --git a/fs/cifs/cached_dir.c b/fs/cifs/cached_dir.c index e5573d4e2d83..fe88b67c863f 100644 --- a/fs/cifs/cached_dir.c +++ b/fs/cifs/cached_dir.c @@ -5,6 +5,7 @@ * Copyright (c) 2022, Ronnie Sahlberg */ +#include #include "cifsglob.h" #include "cifsproto.h" #include "cifs_debug.h" @@ -59,6 +60,44 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, return cfid; } +static struct dentry * +path_to_dentry(struct cifs_sb_info *cifs_sb, const char *path) +{ + struct dentry *dentry; + const char *s, *p; + char sep; + + sep = CIFS_DIR_SEP(cifs_sb); + dentry = dget(cifs_sb->root); + s = path; + + do { + struct inode *dir = d_inode(dentry); + struct dentry *child; + + if (!S_ISDIR(dir->i_mode)) { + dput(dentry); + dentry = ERR_PTR(-ENOTDIR); + break; + } + + /* skip separators */ + while (*s == sep) + s++; + if (!*s) + break; + p = s++; + /* next separator */ + while (*s && *s != sep) + s++; + + child = lookup_positive_unlocked(p, dentry, s - p); + dput(dentry); + dentry = child; + } while (!IS_ERR(dentry)); + return dentry; +} + /* * Open the and cache a directory handle. * If error then *cfid is not initialized. @@ -86,7 +125,6 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, struct cached_fid *cfid; struct cached_fids *cfids; - if (tcon == NULL || tcon->cfids == NULL || tcon->nohandlecache || is_smb1_server(tcon->ses->server)) return -EOPNOTSUPP; @@ -101,13 +139,6 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, if (cifs_sb->root == NULL) return -ENOENT; - /* - * TODO: for better caching we need to find and use the dentry also - * for non-root directories. - */ - if (!path[0]) - dentry = cifs_sb->root; - utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); if (!utf16_path) return -ENOMEM; @@ -199,12 +230,6 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId); #endif /* CIFS_DEBUG2 */ - cfid->tcon = tcon; - if (dentry) { - cfid->dentry = dentry; - dget(dentry); - } - /* BB TBD check to see if oplock level check can be removed below */ if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) goto oshr_free; @@ -223,6 +248,16 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, &rsp_iov[1], sizeof(struct smb2_file_all_info), (char *)&cfid->file_all_info)) cfid->file_all_info_is_valid = true; + + if (!path[0]) + dentry = dget(cifs_sb->root); + else { + dentry = path_to_dentry(cifs_sb, path); + if (IS_ERR(dentry)) + goto oshr_free; + } + cfid->dentry = dentry; + cfid->tcon = tcon; cfid->time = jiffies; cfid->is_open = true; cfid->has_lease = true; -- cgit From d7173623bf0b1503bc4e6f13cd0fccab5e98c6ce Mon Sep 17 00:00:00 2001 From: Enzo Matsumiya Date: Wed, 12 Oct 2022 22:53:09 -0500 Subject: cifs: use ALIGN() and round_up() macros Improve code readability by using existing macros: Replace hardcoded alignment computations (e.g. (len + 7) & ~0x7) by ALIGN()/IS_ALIGNED() macros. Also replace (DIV_ROUND_UP(len, 8) * 8) with ALIGN(len, 8), which, if not optimized by the compiler, has the overhead of a multiplication and a division. Do the same for roundup() by replacing it by round_up() (division-less version, but requires the multiple to be a power of 2, which is always the case for us). And remove some unnecessary checks where !IS_ALIGNED() would fit, but calling round_up() directly is fine as it's a no-op if the value is already aligned. Signed-off-by: Enzo Matsumiya Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/cifssmb.c | 2 +- fs/cifs/connect.c | 11 +++++++++-- fs/cifs/sess.c | 18 ++++++------------ fs/cifs/smb2misc.c | 2 +- fs/cifs/smb2pdu.c | 38 ++++++++++++++++---------------------- 5 files changed, 33 insertions(+), 38 deletions(-) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 7a808e41b1b8..1724066c1536 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -2305,7 +2305,7 @@ int CIFSSMBRenameOpenFile(const unsigned int xid, struct cifs_tcon *pTcon, remap); } rename_info->target_name_len = cpu_to_le32(2 * len_of_str); - count = 12 /* sizeof(struct set_file_rename) */ + (2 * len_of_str); + count = sizeof(struct set_file_rename) + (2 * len_of_str); byte_count += count; pSMB->DataCount = cpu_to_le16(count); pSMB->TotalDataCount = pSMB->DataCount; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index e158257da1cd..ffb291579bb9 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2832,9 +2832,12 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) * sessinit is sent but no second negprot */ struct rfc1002_session_packet *ses_init_buf; + unsigned int req_noscope_len; struct smb_hdr *smb_buf; + ses_init_buf = kzalloc(sizeof(struct rfc1002_session_packet), GFP_KERNEL); + if (ses_init_buf) { ses_init_buf->trailer.session_req.called_len = 32; @@ -2870,8 +2873,12 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) ses_init_buf->trailer.session_req.scope2 = 0; smb_buf = (struct smb_hdr *)ses_init_buf; - /* sizeof RFC1002_SESSION_REQUEST with no scope */ - smb_buf->smb_buf_length = cpu_to_be32(0x81000044); + /* sizeof RFC1002_SESSION_REQUEST with no scopes */ + req_noscope_len = sizeof(struct rfc1002_session_packet) - 2; + + /* == cpu_to_be32(0x81000044) */ + smb_buf->smb_buf_length = + cpu_to_be32((RFC1002_SESSION_REQUEST << 24) | req_noscope_len); rc = smb_send(server, smb_buf, 0x44); kfree(ses_init_buf); /* diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index f1c3c6d9146c..c9edec7081de 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -601,11 +601,6 @@ static void unicode_ssetup_strings(char **pbcc_area, struct cifs_ses *ses, /* BB FIXME add check that strings total less than 335 or will need to send them as arrays */ - /* unicode strings, must be word aligned before the call */ -/* if ((long) bcc_ptr % 2) { - *bcc_ptr = 0; - bcc_ptr++; - } */ /* copy user */ if (ses->user_name == NULL) { /* null user mount */ @@ -1324,7 +1319,7 @@ sess_auth_ntlmv2(struct sess_data *sess_data) } if (ses->capabilities & CAP_UNICODE) { - if (sess_data->iov[0].iov_len % 2) { + if (!IS_ALIGNED(sess_data->iov[0].iov_len, 2)) { *bcc_ptr = 0; bcc_ptr++; } @@ -1364,7 +1359,7 @@ sess_auth_ntlmv2(struct sess_data *sess_data) /* no string area to decode, do nothing */ } else if (smb_buf->Flags2 & SMBFLG2_UNICODE) { /* unicode string area must be word-aligned */ - if (((unsigned long) bcc_ptr - (unsigned long) smb_buf) % 2) { + if (!IS_ALIGNED((unsigned long)bcc_ptr - (unsigned long)smb_buf, 2)) { ++bcc_ptr; --bytes_remaining; } @@ -1448,8 +1443,7 @@ sess_auth_kerberos(struct sess_data *sess_data) if (ses->capabilities & CAP_UNICODE) { /* unicode strings must be word aligned */ - if ((sess_data->iov[0].iov_len - + sess_data->iov[1].iov_len) % 2) { + if (!IS_ALIGNED(sess_data->iov[0].iov_len + sess_data->iov[1].iov_len, 2)) { *bcc_ptr = 0; bcc_ptr++; } @@ -1500,7 +1494,7 @@ sess_auth_kerberos(struct sess_data *sess_data) /* no string area to decode, do nothing */ } else if (smb_buf->Flags2 & SMBFLG2_UNICODE) { /* unicode string area must be word-aligned */ - if (((unsigned long) bcc_ptr - (unsigned long) smb_buf) % 2) { + if (!IS_ALIGNED((unsigned long)bcc_ptr - (unsigned long)smb_buf, 2)) { ++bcc_ptr; --bytes_remaining; } @@ -1552,7 +1546,7 @@ _sess_auth_rawntlmssp_assemble_req(struct sess_data *sess_data) bcc_ptr = sess_data->iov[2].iov_base; /* unicode strings must be word aligned */ - if ((sess_data->iov[0].iov_len + sess_data->iov[1].iov_len) % 2) { + if (!IS_ALIGNED(sess_data->iov[0].iov_len + sess_data->iov[1].iov_len, 2)) { *bcc_ptr = 0; bcc_ptr++; } @@ -1753,7 +1747,7 @@ sess_auth_rawntlmssp_authenticate(struct sess_data *sess_data) /* no string area to decode, do nothing */ } else if (smb_buf->Flags2 & SMBFLG2_UNICODE) { /* unicode string area must be word-aligned */ - if (((unsigned long) bcc_ptr - (unsigned long) smb_buf) % 2) { + if (!IS_ALIGNED((unsigned long)bcc_ptr - (unsigned long)smb_buf, 2)) { ++bcc_ptr; --bytes_remaining; } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 7db5c09ecceb..a38720477966 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -248,7 +248,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) * Some windows servers (win2016) will pad also the final * PDU in a compound to 8 bytes. */ - if (((calc_len + 7) & ~7) == len) + if (ALIGN(calc_len, 8) == len) return 0; /* diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index a3b77df2848c..e1162217ad1a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -466,15 +466,14 @@ build_signing_ctxt(struct smb2_signing_capabilities *pneg_ctxt) /* * Context Data length must be rounded to multiple of 8 for some servers */ - pneg_ctxt->DataLength = cpu_to_le16(DIV_ROUND_UP( - sizeof(struct smb2_signing_capabilities) - - sizeof(struct smb2_neg_context) + - (num_algs * 2 /* sizeof u16 */), 8) * 8); + pneg_ctxt->DataLength = cpu_to_le16(ALIGN(sizeof(struct smb2_signing_capabilities) - + sizeof(struct smb2_neg_context) + + (num_algs * sizeof(u16)), 8)); pneg_ctxt->SigningAlgorithmCount = cpu_to_le16(num_algs); pneg_ctxt->SigningAlgorithms[0] = cpu_to_le16(SIGNING_ALG_AES_CMAC); - ctxt_len += 2 /* sizeof le16 */ * num_algs; - ctxt_len = DIV_ROUND_UP(ctxt_len, 8) * 8; + ctxt_len += sizeof(__le16) * num_algs; + ctxt_len = ALIGN(ctxt_len, 8); return ctxt_len; /* TBD add SIGNING_ALG_AES_GMAC and/or SIGNING_ALG_HMAC_SHA256 */ } @@ -511,8 +510,7 @@ build_netname_ctxt(struct smb2_netname_neg_context *pneg_ctxt, char *hostname) /* copy up to max of first 100 bytes of server name to NetName field */ pneg_ctxt->DataLength = cpu_to_le16(2 * cifs_strtoUTF16(pneg_ctxt->NetName, hostname, 100, cp)); /* context size is DataLength + minimal smb2_neg_context */ - return DIV_ROUND_UP(le16_to_cpu(pneg_ctxt->DataLength) + - sizeof(struct smb2_neg_context), 8) * 8; + return ALIGN(le16_to_cpu(pneg_ctxt->DataLength) + sizeof(struct smb2_neg_context), 8); } static void @@ -557,18 +555,18 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, * round up total_len of fixed part of SMB3 negotiate request to 8 * byte boundary before adding negotiate contexts */ - *total_len = roundup(*total_len, 8); + *total_len = ALIGN(*total_len, 8); pneg_ctxt = (*total_len) + (char *)req; req->NegotiateContextOffset = cpu_to_le32(*total_len); build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt); - ctxt_len = DIV_ROUND_UP(sizeof(struct smb2_preauth_neg_context), 8) * 8; + ctxt_len = ALIGN(sizeof(struct smb2_preauth_neg_context), 8); *total_len += ctxt_len; pneg_ctxt += ctxt_len; build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt); - ctxt_len = DIV_ROUND_UP(sizeof(struct smb2_encryption_neg_context), 8) * 8; + ctxt_len = ALIGN(sizeof(struct smb2_encryption_neg_context), 8); *total_len += ctxt_len; pneg_ctxt += ctxt_len; @@ -595,9 +593,7 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, if (server->compress_algorithm) { build_compression_ctxt((struct smb2_compression_capabilities_context *) pneg_ctxt); - ctxt_len = DIV_ROUND_UP( - sizeof(struct smb2_compression_capabilities_context), - 8) * 8; + ctxt_len = ALIGN(sizeof(struct smb2_compression_capabilities_context), 8); *total_len += ctxt_len; pneg_ctxt += ctxt_len; neg_context_count++; @@ -780,7 +776,7 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, if (rc) break; /* offsets must be 8 byte aligned */ - clen = (clen + 7) & ~0x7; + clen = ALIGN(clen, 8); offset += clen + sizeof(struct smb2_neg_context); len_of_ctxts -= clen; } @@ -2426,7 +2422,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) unsigned int group_offset = 0; struct smb3_acl acl; - *len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8); + *len = round_up(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8); if (set_owner) { /* sizeof(struct owner_group_sids) is already multiple of 8 so no need to round */ @@ -2500,7 +2496,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) memcpy(aclptr, &acl, sizeof(struct smb3_acl)); buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); - *len = roundup(ptr - (__u8 *)buf, 8); + *len = round_up((unsigned int)(ptr - (__u8 *)buf), 8); return buf; } @@ -2594,7 +2590,7 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len, * final path needs to be 8-byte aligned as specified in * MS-SMB2 2.2.13 SMB2 CREATE Request. */ - *out_size = roundup(*out_len * sizeof(__le16), 8); + *out_size = round_up(*out_len * sizeof(__le16), 8); *out_path = kzalloc(*out_size + sizeof(__le16) /* null */, GFP_KERNEL); if (!*out_path) return -ENOMEM; @@ -2839,9 +2835,7 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2; /* MUST set path len (NameLength) to 0 opening root of share */ req->NameLength = cpu_to_le16(uni_path_len - 2); - copy_size = uni_path_len; - if (copy_size % 8 != 0) - copy_size = roundup(copy_size, 8); + copy_size = round_up(uni_path_len, 8); copy_path = kzalloc(copy_size, GFP_KERNEL); if (!copy_path) return -ENOMEM; @@ -4103,7 +4097,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len, if (request_type & CHAINED_REQUEST) { if (!(request_type & END_OF_CHAIN)) { /* next 8-byte aligned request */ - *total_len = DIV_ROUND_UP(*total_len, 8) * 8; + *total_len = ALIGN(*total_len, 8); shdr->NextCommand = cpu_to_le32(*total_len); } else /* END_OF_CHAIN */ shdr->NextCommand = 0; -- cgit From 3cebf80e9a0d3adcb174053be32c88a640b3344b Mon Sep 17 00:00:00 2001 From: Fangrui Song Date: Sun, 18 Sep 2022 02:29:34 -0700 Subject: riscv: Pass -mno-relax only on lld < 15.0.0 lld since llvm:6611d58f5bbc ("[ELF] Relax R_RISCV_ALIGN"), which will be included in the 15.0.0 release, has implemented some RISC-V linker relaxation. -mno-relax is no longer needed in KBUILD_CFLAGS/KBUILD_AFLAGS to suppress R_RISCV_ALIGN which older lld can not handle: ld.lld: error: capability.c:(.fixup+0x0): relocation R_RISCV_ALIGN requires unimplemented linker relaxation; recompile with -mno-relax but the .o is already compiled with -mno-relax Signed-off-by: Fangrui Song Link: https://lore.kernel.org/r/20220710071117.446112-1-maskray@google.com/ Link: https://lore.kernel.org/r/20220918092933.19943-1-palmer@rivosinc.com Reviewed-by: Nick Desaulniers Tested-by: Nick Desaulniers Tested-by: Nathan Chancellor Tested-by: Conor Dooley Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index d63295e21373..76364cf67a72 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -37,6 +37,7 @@ else endif ifeq ($(CONFIG_LD_IS_LLD),y) +ifeq ($(shell test $(CONFIG_LLD_VERSION) -lt 150000; echo $$?),0) KBUILD_CFLAGS += -mno-relax KBUILD_AFLAGS += -mno-relax ifndef CONFIG_AS_IS_LLVM @@ -44,6 +45,7 @@ ifndef CONFIG_AS_IS_LLVM KBUILD_AFLAGS += -Wa,-mno-relax endif endif +endif # ISA string setting riscv-march-$(CONFIG_ARCH_RV32I) := rv32ima -- cgit From e47bddcb2ec531022a915f896f13586470b593d0 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Mon, 5 Sep 2022 13:10:23 +0200 Subject: riscv: cleanup svpbmt cpufeature probing For better readability (and compile time coverage) use IS_ENABLED instead of ifdef and drop the new unneeded switch statement. Signed-off-by: Heiko Stuebner Reviewed-by: Guo Ren Reviewed-by: Conor Dooley Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20220905111027.2463297-2-heiko@sntech.de Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/cpufeature.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 553d755483ed..764ea220161f 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -253,16 +253,13 @@ void __init riscv_fill_hwcap(void) #ifdef CONFIG_RISCV_ALTERNATIVE static bool __init_or_module cpufeature_probe_svpbmt(unsigned int stage) { -#ifdef CONFIG_RISCV_ISA_SVPBMT - switch (stage) { - case RISCV_ALTERNATIVES_EARLY_BOOT: + if (!IS_ENABLED(CONFIG_RISCV_ISA_SVPBMT)) return false; - default: - return riscv_isa_extension_available(NULL, SVPBMT); - } -#endif - return false; + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + return riscv_isa_extension_available(NULL, SVPBMT); } static bool __init_or_module cpufeature_probe_zicbom(unsigned int stage) -- cgit From f055268e3946555deb9bb80b2c8c9798c64dbc47 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Mon, 5 Sep 2022 13:10:24 +0200 Subject: riscv: drop some idefs from CMO initialization Wrapping things in #ifdefs makes the code harder to read while we also have IS_ENABLED() macros to do this in regular code and the extension detection is not _that_ runtime critical. So define a stub for riscv_noncoherent_supported() in the non-CONFIG_RISCV_DMA_NONCOHERENT case and move the code to us IS_ENABLED. Suggested-by: Conor Dooley Signed-off-by: Heiko Stuebner Reviewed-by: Guo Ren Reviewed-by: Conor Dooley Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20220905111027.2463297-3-heiko@sntech.de Signed-off-by: Palmer Dabbelt --- arch/riscv/errata/thead/errata.c | 7 +++---- arch/riscv/include/asm/cacheflush.h | 2 ++ arch/riscv/kernel/cpufeature.c | 22 +++++++++------------- 3 files changed, 14 insertions(+), 17 deletions(-) diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index 202c83f677b2..bffa711aaf64 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -30,7 +30,9 @@ static bool errata_probe_pbmt(unsigned int stage, static bool errata_probe_cmo(unsigned int stage, unsigned long arch_id, unsigned long impid) { -#ifdef CONFIG_ERRATA_THEAD_CMO + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_CMO)) + return false; + if (arch_id != 0 || impid != 0) return false; @@ -39,9 +41,6 @@ static bool errata_probe_cmo(unsigned int stage, riscv_noncoherent_supported(); return true; -#else - return false; -#endif } static u32 thead_errata_probe(unsigned int stage, diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index a60acaecfeda..4363d0beb38a 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -50,6 +50,8 @@ static inline void riscv_init_cbom_blocksize(void) { } #ifdef CONFIG_RISCV_DMA_NONCOHERENT void riscv_noncoherent_supported(void); +#else +static inline void riscv_noncoherent_supported(void) {} #endif /* diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 764ea220161f..729f7a218093 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -264,21 +264,17 @@ static bool __init_or_module cpufeature_probe_svpbmt(unsigned int stage) static bool __init_or_module cpufeature_probe_zicbom(unsigned int stage) { -#ifdef CONFIG_RISCV_ISA_ZICBOM - switch (stage) { - case RISCV_ALTERNATIVES_EARLY_BOOT: + if (!IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM)) + return false; + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + if (!riscv_isa_extension_available(NULL, ZICBOM)) return false; - default: - if (riscv_isa_extension_available(NULL, ZICBOM)) { - riscv_noncoherent_supported(); - return true; - } else { - return false; - } - } -#endif - return false; + riscv_noncoherent_supported(); + return true; } /* -- cgit From 499590c084f13b6aca225e5766edeebd48437ee8 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Mon, 5 Sep 2022 13:10:25 +0200 Subject: riscv: use BIT() macros in t-head errata init Using the appropriate BIT macro makes the code better readable. Suggested-by: Conor Dooley Signed-off-by: Heiko Stuebner Reviewed-by: Guo Ren Reviewed-by: Conor Dooley Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20220905111027.2463297-4-heiko@sntech.de Signed-off-by: Palmer Dabbelt --- arch/riscv/errata/thead/errata.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index bffa711aaf64..a6f4bd8ccf3f 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -49,10 +49,10 @@ static u32 thead_errata_probe(unsigned int stage, u32 cpu_req_errata = 0; if (errata_probe_pbmt(stage, archid, impid)) - cpu_req_errata |= (1U << ERRATA_THEAD_PBMT); + cpu_req_errata |= BIT(ERRATA_THEAD_PBMT); if (errata_probe_cmo(stage, archid, impid)) - cpu_req_errata |= (1U << ERRATA_THEAD_CMO); + cpu_req_errata |= BIT(ERRATA_THEAD_CMO); return cpu_req_errata; } -- cgit From e283187c034cd80c1dd98ad732c73ce930a5efa4 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Mon, 5 Sep 2022 13:10:26 +0200 Subject: riscv: use BIT() marco for cpufeature probing Using the appropriate BIT macro makes the code better readable. Suggested-by: Conor Dooley Signed-off-by: Heiko Stuebner Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220905111027.2463297-5-heiko@sntech.de Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/cpufeature.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 729f7a218093..08f7445985dc 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -289,10 +289,10 @@ static u32 __init_or_module cpufeature_probe(unsigned int stage) u32 cpu_req_feature = 0; if (cpufeature_probe_svpbmt(stage)) - cpu_req_feature |= (1U << CPUFEATURE_SVPBMT); + cpu_req_feature |= BIT(CPUFEATURE_SVPBMT); if (cpufeature_probe_zicbom(stage)) - cpu_req_feature |= (1U << CPUFEATURE_ZICBOM); + cpu_req_feature |= BIT(CPUFEATURE_ZICBOM); return cpu_req_feature; } -- cgit From 14057733109dcc83c35a6730f3b7112aac4d2b82 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Mon, 5 Sep 2022 13:10:27 +0200 Subject: riscv: check for kernel config option in t-head memory types errata The t-head variant of page-based memory types should also check first for the enabled kernel config option. Fixes: a35707c3d850 ("riscv: add memory-type errata for T-Head") Signed-off-by: Heiko Stuebner Reviewed-by: Conor Dooley Reviewed-by: Andrew Jones Reviewed-by: Guo Ren Link: https://lore.kernel.org/r/20220905111027.2463297-6-heiko@sntech.de Signed-off-by: Palmer Dabbelt --- arch/riscv/errata/thead/errata.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index a6f4bd8ccf3f..902e12452821 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -17,6 +17,9 @@ static bool errata_probe_pbmt(unsigned int stage, unsigned long arch_id, unsigned long impid) { + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PBMT)) + return false; + if (arch_id != 0 || impid != 0) return false; -- cgit From 917c362b5f8a6e31ff35719b1bacfc1b76a1fd2f Mon Sep 17 00:00:00 2001 From: Frank Rowand Date: Wed, 12 Oct 2022 17:05:48 -0500 Subject: MAINTAINERS: of: collapse overlay entry into main device tree entry Pantelis has not been active in recent years so no need to maintain a separate entry for device tree overlays. Signed-off-by: Frank Rowand Link: https://lore.kernel.org/r/20221012220548.4163865-1-frowand.list@gmail.com Signed-off-by: Rob Herring --- MAINTAINERS | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index a198da986146..a497bd2b0ea6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15359,17 +15359,6 @@ L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/ulp/opa_vnic -OPEN FIRMWARE AND DEVICE TREE OVERLAYS -M: Pantelis Antoniou -M: Frank Rowand -L: devicetree@vger.kernel.org -S: Maintained -F: Documentation/devicetree/dynamic-resolution-notes.rst -F: Documentation/devicetree/overlay-notes.rst -F: drivers/of/overlay.c -F: drivers/of/resolver.c -K: of_overlay_notifier_ - OPEN FIRMWARE AND FLATTENED DEVICE TREE M: Rob Herring M: Frank Rowand @@ -15382,6 +15371,9 @@ F: Documentation/ABI/testing/sysfs-firmware-ofw F: drivers/of/ F: include/linux/of*.h F: scripts/dtc/ +K: of_overlay_notifier_ +K: of_overlay_fdt_apply +K: of_overlay_remove OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS M: Rob Herring -- cgit From 877d95dcfd0a56102d4b97a9691115f5fb5e9ea3 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Thu, 6 Oct 2022 10:44:09 +0200 Subject: Documentation: rtla: Correct command line example The '-t/-T' parameters seem to have been swapped: -t/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt] -T/--thread us: stop trace if the thread latency is higher than the argument in us Swap them back. Signed-off-by: Pierre Gondois Acked-by: Daniel Bristot de Oliveira Link: https://lore.kernel.org/r/20221006084409.3882542-1-pierre.gondois@arm.com Signed-off-by: Jonathan Corbet --- Documentation/tools/rtla/rtla-timerlat-top.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/tools/rtla/rtla-timerlat-top.rst b/Documentation/tools/rtla/rtla-timerlat-top.rst index 1c321de1c171..7c4e4b109493 100644 --- a/Documentation/tools/rtla/rtla-timerlat-top.rst +++ b/Documentation/tools/rtla/rtla-timerlat-top.rst @@ -39,7 +39,7 @@ higher than *30 us*. It is also set to stop the session if a *Thread* timer latency higher than *30 us* is hit. Finally, it is set to save the trace buffer if the stop condition is hit:: - [root@alien ~]# rtla timerlat top -s 30 -t 30 -T + [root@alien ~]# rtla timerlat top -s 30 -T 30 -t Timer Latency 0 00:00:59 | IRQ Timer Latency (us) | Thread Timer Latency (us) CPU COUNT | cur min avg max | cur min avg max -- cgit From 44dce4b084f83f41922ed8c2a2c7d148254848bb Mon Sep 17 00:00:00 2001 From: Zong Li Date: Tue, 13 Sep 2022 06:18:11 +0000 Subject: dt-bindings: sifive-ccache: change Sifive L2 cache to Composable cache Since composable cache may be L3 cache if private L2 cache exists, we should use its original name Composable cache to prevent confusion. Signed-off-by: Zong Li Suggested-by: Conor Dooley Suggested-by: Ben Dooks Reviewed-by: Conor Dooley Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20220913061817.22564-2-zong.li@sifive.com Signed-off-by: Palmer Dabbelt --- .../devicetree/bindings/riscv/sifive,ccache0.yaml | 164 +++++++++++++++++++++ .../devicetree/bindings/riscv/sifive-l2-cache.yaml | 146 ------------------ 2 files changed, 164 insertions(+), 146 deletions(-) create mode 100644 Documentation/devicetree/bindings/riscv/sifive,ccache0.yaml delete mode 100644 Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml diff --git a/Documentation/devicetree/bindings/riscv/sifive,ccache0.yaml b/Documentation/devicetree/bindings/riscv/sifive,ccache0.yaml new file mode 100644 index 000000000000..bf3f07421f7e --- /dev/null +++ b/Documentation/devicetree/bindings/riscv/sifive,ccache0.yaml @@ -0,0 +1,164 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +# Copyright (C) 2020 SiFive, Inc. +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/riscv/sifive,ccache0.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: SiFive Composable Cache Controller + +maintainers: + - Sagar Kadam + - Paul Walmsley + +description: + The SiFive Composable Cache Controller is used to provide access to fast copies + of memory for masters in a Core Complex. The Composable Cache Controller also + acts as directory-based coherency manager. + All the properties in ePAPR/DeviceTree specification applies for this platform. + +select: + properties: + compatible: + contains: + enum: + - sifive,ccache0 + - sifive,fu540-c000-ccache + - sifive,fu740-c000-ccache + + required: + - compatible + +properties: + compatible: + oneOf: + - items: + - enum: + - sifive,ccache0 + - sifive,fu540-c000-ccache + - sifive,fu740-c000-ccache + - const: cache + - items: + - const: microchip,mpfs-ccache + - const: sifive,fu540-c000-ccache + - const: cache + + cache-block-size: + const: 64 + + cache-level: + enum: [2, 3] + + cache-sets: + enum: [1024, 2048] + + cache-size: + const: 2097152 + + cache-unified: true + + interrupts: + minItems: 3 + items: + - description: DirError interrupt + - description: DataError interrupt + - description: DataFail interrupt + - description: DirFail interrupt + + reg: + maxItems: 1 + + next-level-cache: true + + memory-region: + maxItems: 1 + description: | + The reference to the reserved-memory for the L2 Loosely Integrated Memory region. + The reserved memory node should be defined as per the bindings in reserved-memory.txt. + +allOf: + - $ref: /schemas/cache-controller.yaml# + + - if: + properties: + compatible: + contains: + enum: + - sifive,fu740-c000-ccache + - microchip,mpfs-ccache + + then: + properties: + interrupts: + description: | + Must contain entries for DirError, DataError, DataFail, DirFail signals. + minItems: 4 + + else: + properties: + interrupts: + description: | + Must contain entries for DirError, DataError and DataFail signals. + maxItems: 3 + + - if: + properties: + compatible: + contains: + const: sifive,fu740-c000-ccache + + then: + properties: + cache-sets: + const: 2048 + + else: + properties: + cache-sets: + const: 1024 + + - if: + properties: + compatible: + contains: + const: sifive,ccache0 + + then: + properties: + cache-level: + enum: [2, 3] + + else: + properties: + cache-level: + const: 2 + +additionalProperties: false + +required: + - compatible + - cache-block-size + - cache-level + - cache-sets + - cache-size + - cache-unified + - interrupts + - reg + +examples: + - | + cache-controller@2010000 { + compatible = "sifive,fu540-c000-ccache", "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <1024>; + cache-size = <2097152>; + cache-unified; + reg = <0x2010000 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <1>, + <2>, + <3>; + next-level-cache = <&L25>; + memory-region = <&l2_lim>; + }; diff --git a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml deleted file mode 100644 index ca3b9be58058..000000000000 --- a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml +++ /dev/null @@ -1,146 +0,0 @@ -# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) -# Copyright (C) 2020 SiFive, Inc. -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/riscv/sifive-l2-cache.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: SiFive L2 Cache Controller - -maintainers: - - Sagar Kadam - - Paul Walmsley - -description: - The SiFive Level 2 Cache Controller is used to provide access to fast copies - of memory for masters in a Core Complex. The Level 2 Cache Controller also - acts as directory-based coherency manager. - All the properties in ePAPR/DeviceTree specification applies for this platform. - -select: - properties: - compatible: - contains: - enum: - - sifive,fu540-c000-ccache - - sifive,fu740-c000-ccache - - required: - - compatible - -properties: - compatible: - oneOf: - - items: - - enum: - - sifive,fu540-c000-ccache - - sifive,fu740-c000-ccache - - const: cache - - items: - - const: microchip,mpfs-ccache - - const: sifive,fu540-c000-ccache - - const: cache - - cache-block-size: - const: 64 - - cache-level: - const: 2 - - cache-sets: - enum: [1024, 2048] - - cache-size: - const: 2097152 - - cache-unified: true - - interrupts: - minItems: 3 - items: - - description: DirError interrupt - - description: DataError interrupt - - description: DataFail interrupt - - description: DirFail interrupt - - reg: - maxItems: 1 - - next-level-cache: true - - memory-region: - maxItems: 1 - description: | - The reference to the reserved-memory for the L2 Loosely Integrated Memory region. - The reserved memory node should be defined as per the bindings in reserved-memory.txt. - -allOf: - - $ref: /schemas/cache-controller.yaml# - - - if: - properties: - compatible: - contains: - enum: - - sifive,fu740-c000-ccache - - microchip,mpfs-ccache - - then: - properties: - interrupts: - description: | - Must contain entries for DirError, DataError, DataFail, DirFail signals. - minItems: 4 - - else: - properties: - interrupts: - description: | - Must contain entries for DirError, DataError and DataFail signals. - maxItems: 3 - - - if: - properties: - compatible: - contains: - const: sifive,fu740-c000-ccache - - then: - properties: - cache-sets: - const: 2048 - - else: - properties: - cache-sets: - const: 1024 - -additionalProperties: false - -required: - - compatible - - cache-block-size - - cache-level - - cache-sets - - cache-size - - cache-unified - - interrupts - - reg - -examples: - - | - cache-controller@2010000 { - compatible = "sifive,fu540-c000-ccache", "cache"; - cache-block-size = <64>; - cache-level = <2>; - cache-sets = <1024>; - cache-size = <2097152>; - cache-unified; - reg = <0x2010000 0x1000>; - interrupt-parent = <&plic0>; - interrupts = <1>, - <2>, - <3>; - next-level-cache = <&L25>; - memory-region = <&l2_lim>; - }; -- cgit From ca120a79cf5a3323172c82e77efd70ae10d120ef Mon Sep 17 00:00:00 2001 From: Greentime Hu Date: Tue, 13 Sep 2022 06:18:12 +0000 Subject: soc: sifive: ccache: Rename SiFive L2 cache to Composable cache. Since composable cache may be L3 cache if there is a L2 cache, we should use its original name composable cache to prevent confusion. There are some new lines were generated due to adding the compatible "sifive,ccache0" into ID table and indent requirement. The sifive L2 has been renamed to sifive CCACHE, EDAC driver needs to apply the change as well. Signed-off-by: Greentime Hu Signed-off-by: Zong Li Co-developed-by: Zong Li Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220913061817.22564-3-zong.li@sifive.com Signed-off-by: Palmer Dabbelt --- drivers/edac/Kconfig | 2 +- drivers/edac/sifive_edac.c | 12 +- drivers/soc/sifive/Kconfig | 6 +- drivers/soc/sifive/Makefile | 2 +- drivers/soc/sifive/sifive_ccache.c | 245 +++++++++++++++++++++++++++++++++++ drivers/soc/sifive/sifive_l2_cache.c | 237 --------------------------------- include/soc/sifive/sifive_ccache.h | 16 +++ include/soc/sifive/sifive_l2_cache.h | 16 --- 8 files changed, 272 insertions(+), 264 deletions(-) create mode 100644 drivers/soc/sifive/sifive_ccache.c delete mode 100644 drivers/soc/sifive/sifive_l2_cache.c create mode 100644 include/soc/sifive/sifive_ccache.h delete mode 100644 include/soc/sifive/sifive_l2_cache.h diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 17562cf1fe97..456602d373b7 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -473,7 +473,7 @@ config EDAC_ALTERA_SDMMC config EDAC_SIFIVE bool "Sifive platform EDAC driver" - depends on EDAC=y && SIFIVE_L2 + depends on EDAC=y && SIFIVE_CCACHE help Support for error detection and correction on the SiFive SoCs. diff --git a/drivers/edac/sifive_edac.c b/drivers/edac/sifive_edac.c index ee800aec7d47..b844e2626fd5 100644 --- a/drivers/edac/sifive_edac.c +++ b/drivers/edac/sifive_edac.c @@ -2,7 +2,7 @@ /* * SiFive Platform EDAC Driver * - * Copyright (C) 2018-2019 SiFive, Inc. + * Copyright (C) 2018-2022 SiFive, Inc. * * This driver is partially based on octeon_edac-pc.c * @@ -10,7 +10,7 @@ #include #include #include "edac_module.h" -#include +#include #define DRVNAME "sifive_edac" @@ -32,9 +32,9 @@ int ecc_err_event(struct notifier_block *this, unsigned long event, void *ptr) p = container_of(this, struct sifive_edac_priv, notifier); - if (event == SIFIVE_L2_ERR_TYPE_UE) + if (event == SIFIVE_CCACHE_ERR_TYPE_UE) edac_device_handle_ue(p->dci, 0, 0, msg); - else if (event == SIFIVE_L2_ERR_TYPE_CE) + else if (event == SIFIVE_CCACHE_ERR_TYPE_CE) edac_device_handle_ce(p->dci, 0, 0, msg); return NOTIFY_OK; @@ -67,7 +67,7 @@ static int ecc_register(struct platform_device *pdev) goto err; } - register_sifive_l2_error_notifier(&p->notifier); + register_sifive_ccache_error_notifier(&p->notifier); return 0; @@ -81,7 +81,7 @@ static int ecc_unregister(struct platform_device *pdev) { struct sifive_edac_priv *p = platform_get_drvdata(pdev); - unregister_sifive_l2_error_notifier(&p->notifier); + unregister_sifive_ccache_error_notifier(&p->notifier); edac_device_del_device(&pdev->dev); edac_device_free_ctl_info(p->dci); diff --git a/drivers/soc/sifive/Kconfig b/drivers/soc/sifive/Kconfig index 58cf8c40d08d..ed4c571f8771 100644 --- a/drivers/soc/sifive/Kconfig +++ b/drivers/soc/sifive/Kconfig @@ -2,9 +2,9 @@ if SOC_SIFIVE -config SIFIVE_L2 - bool "Sifive L2 Cache controller" +config SIFIVE_CCACHE + bool "Sifive Composable Cache controller" help - Support for the L2 cache controller on SiFive platforms. + Support for the composable cache controller on SiFive platforms. endif diff --git a/drivers/soc/sifive/Makefile b/drivers/soc/sifive/Makefile index b5caff77938f..1f5dc339bf82 100644 --- a/drivers/soc/sifive/Makefile +++ b/drivers/soc/sifive/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_SIFIVE_L2) += sifive_l2_cache.o +obj-$(CONFIG_SIFIVE_CCACHE) += sifive_ccache.o diff --git a/drivers/soc/sifive/sifive_ccache.c b/drivers/soc/sifive/sifive_ccache.c new file mode 100644 index 000000000000..949b824e89ad --- /dev/null +++ b/drivers/soc/sifive/sifive_ccache.c @@ -0,0 +1,245 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SiFive composable cache controller Driver + * + * Copyright (C) 2018-2022 SiFive, Inc. + * + */ +#include +#include +#include +#include +#include +#include +#include + +#define SIFIVE_CCACHE_DIRECCFIX_LOW 0x100 +#define SIFIVE_CCACHE_DIRECCFIX_HIGH 0x104 +#define SIFIVE_CCACHE_DIRECCFIX_COUNT 0x108 + +#define SIFIVE_CCACHE_DIRECCFAIL_LOW 0x120 +#define SIFIVE_CCACHE_DIRECCFAIL_HIGH 0x124 +#define SIFIVE_CCACHE_DIRECCFAIL_COUNT 0x128 + +#define SIFIVE_CCACHE_DATECCFIX_LOW 0x140 +#define SIFIVE_CCACHE_DATECCFIX_HIGH 0x144 +#define SIFIVE_CCACHE_DATECCFIX_COUNT 0x148 + +#define SIFIVE_CCACHE_DATECCFAIL_LOW 0x160 +#define SIFIVE_CCACHE_DATECCFAIL_HIGH 0x164 +#define SIFIVE_CCACHE_DATECCFAIL_COUNT 0x168 + +#define SIFIVE_CCACHE_CONFIG 0x00 +#define SIFIVE_CCACHE_WAYENABLE 0x08 +#define SIFIVE_CCACHE_ECCINJECTERR 0x40 + +#define SIFIVE_CCACHE_MAX_ECCINTR 4 + +static void __iomem *ccache_base; +static int g_irq[SIFIVE_CCACHE_MAX_ECCINTR]; +static struct riscv_cacheinfo_ops ccache_cache_ops; + +enum { + DIR_CORR = 0, + DATA_CORR, + DATA_UNCORR, + DIR_UNCORR, +}; + +#ifdef CONFIG_DEBUG_FS +static struct dentry *sifive_test; + +static ssize_t ccache_write(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + unsigned int val; + + if (kstrtouint_from_user(data, count, 0, &val)) + return -EINVAL; + if ((val < 0xFF) || (val >= 0x10000 && val < 0x100FF)) + writel(val, ccache_base + SIFIVE_CCACHE_ECCINJECTERR); + else + return -EINVAL; + return count; +} + +static const struct file_operations ccache_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .write = ccache_write +}; + +static void setup_sifive_debug(void) +{ + sifive_test = debugfs_create_dir("sifive_ccache_cache", NULL); + + debugfs_create_file("sifive_debug_inject_error", 0200, + sifive_test, NULL, &ccache_fops); +} +#endif + +static void ccache_config_read(void) +{ + u32 regval, val; + + regval = readl(ccache_base + SIFIVE_CCACHE_CONFIG); + val = regval & 0xFF; + pr_info("CCACHE: No. of Banks in the cache: %d\n", val); + val = (regval & 0xFF00) >> 8; + pr_info("CCACHE: No. of ways per bank: %d\n", val); + val = (regval & 0xFF0000) >> 16; + pr_info("CCACHE: Sets per bank: %llu\n", (uint64_t)1 << val); + val = (regval & 0xFF000000) >> 24; + pr_info("CCACHE: Bytes per cache block: %llu\n", (uint64_t)1 << val); + + regval = readl(ccache_base + SIFIVE_CCACHE_WAYENABLE); + pr_info("CCACHE: Index of the largest way enabled: %d\n", regval); +} + +static const struct of_device_id sifive_ccache_ids[] = { + { .compatible = "sifive,fu540-c000-ccache" }, + { .compatible = "sifive,fu740-c000-ccache" }, + { .compatible = "sifive,ccache0" }, + { /* end of table */ } +}; + +static ATOMIC_NOTIFIER_HEAD(ccache_err_chain); + +int register_sifive_ccache_error_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&ccache_err_chain, nb); +} +EXPORT_SYMBOL_GPL(register_sifive_ccache_error_notifier); + +int unregister_sifive_ccache_error_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&ccache_err_chain, nb); +} +EXPORT_SYMBOL_GPL(unregister_sifive_ccache_error_notifier); + +static int ccache_largest_wayenabled(void) +{ + return readl(ccache_base + SIFIVE_CCACHE_WAYENABLE) & 0xFF; +} + +static ssize_t number_of_ways_enabled_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", ccache_largest_wayenabled()); +} + +static DEVICE_ATTR_RO(number_of_ways_enabled); + +static struct attribute *priv_attrs[] = { + &dev_attr_number_of_ways_enabled.attr, + NULL, +}; + +static const struct attribute_group priv_attr_group = { + .attrs = priv_attrs, +}; + +static const struct attribute_group *ccache_get_priv_group(struct cacheinfo + *this_leaf) +{ + /* We want to use private group for composable cache only */ + if (this_leaf->level == 2) + return &priv_attr_group; + else + return NULL; +} + +static irqreturn_t ccache_int_handler(int irq, void *device) +{ + unsigned int add_h, add_l; + + if (irq == g_irq[DIR_CORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_LOW); + pr_err("CCACHE: DirError @ 0x%08X.%08X\n", add_h, add_l); + /* Reading this register clears the DirError interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_CE, + "DirECCFix"); + } + if (irq == g_irq[DIR_UNCORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_LOW); + /* Reading this register clears the DirFail interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DIRECCFAIL_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_UE, + "DirECCFail"); + panic("CCACHE: DirFail @ 0x%08X.%08X\n", add_h, add_l); + } + if (irq == g_irq[DATA_CORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_LOW); + pr_err("CCACHE: DataError @ 0x%08X.%08X\n", add_h, add_l); + /* Reading this register clears the DataError interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_CE, + "DatECCFix"); + } + if (irq == g_irq[DATA_UNCORR]) { + add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_HIGH); + add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_LOW); + pr_err("CCACHE: DataFail @ 0x%08X.%08X\n", add_h, add_l); + /* Reading this register clears the DataFail interrupt sig */ + readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_COUNT); + atomic_notifier_call_chain(&ccache_err_chain, + SIFIVE_CCACHE_ERR_TYPE_UE, + "DatECCFail"); + } + + return IRQ_HANDLED; +} + +static int __init sifive_ccache_init(void) +{ + struct device_node *np; + struct resource res; + int i, rc, intr_num; + + np = of_find_matching_node(NULL, sifive_ccache_ids); + if (!np) + return -ENODEV; + + if (of_address_to_resource(np, 0, &res)) + return -ENODEV; + + ccache_base = ioremap(res.start, resource_size(&res)); + if (!ccache_base) + return -ENOMEM; + + intr_num = of_property_count_u32_elems(np, "interrupts"); + if (!intr_num) { + pr_err("CCACHE: no interrupts property\n"); + return -ENODEV; + } + + for (i = 0; i < intr_num; i++) { + g_irq[i] = irq_of_parse_and_map(np, i); + rc = request_irq(g_irq[i], ccache_int_handler, 0, "ccache_ecc", + NULL); + if (rc) { + pr_err("CCACHE: Could not request IRQ %d\n", g_irq[i]); + return rc; + } + } + + ccache_config_read(); + + ccache_cache_ops.get_priv_group = ccache_get_priv_group; + riscv_set_cacheinfo_ops(&ccache_cache_ops); + +#ifdef CONFIG_DEBUG_FS + setup_sifive_debug(); +#endif + return 0; +} + +device_initcall(sifive_ccache_init); diff --git a/drivers/soc/sifive/sifive_l2_cache.c b/drivers/soc/sifive/sifive_l2_cache.c deleted file mode 100644 index 59640a1d0b28..000000000000 --- a/drivers/soc/sifive/sifive_l2_cache.c +++ /dev/null @@ -1,237 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * SiFive L2 cache controller Driver - * - * Copyright (C) 2018-2019 SiFive, Inc. - * - */ -#include -#include -#include -#include -#include -#include -#include - -#define SIFIVE_L2_DIRECCFIX_LOW 0x100 -#define SIFIVE_L2_DIRECCFIX_HIGH 0x104 -#define SIFIVE_L2_DIRECCFIX_COUNT 0x108 - -#define SIFIVE_L2_DIRECCFAIL_LOW 0x120 -#define SIFIVE_L2_DIRECCFAIL_HIGH 0x124 -#define SIFIVE_L2_DIRECCFAIL_COUNT 0x128 - -#define SIFIVE_L2_DATECCFIX_LOW 0x140 -#define SIFIVE_L2_DATECCFIX_HIGH 0x144 -#define SIFIVE_L2_DATECCFIX_COUNT 0x148 - -#define SIFIVE_L2_DATECCFAIL_LOW 0x160 -#define SIFIVE_L2_DATECCFAIL_HIGH 0x164 -#define SIFIVE_L2_DATECCFAIL_COUNT 0x168 - -#define SIFIVE_L2_CONFIG 0x00 -#define SIFIVE_L2_WAYENABLE 0x08 -#define SIFIVE_L2_ECCINJECTERR 0x40 - -#define SIFIVE_L2_MAX_ECCINTR 4 - -static void __iomem *l2_base; -static int g_irq[SIFIVE_L2_MAX_ECCINTR]; -static struct riscv_cacheinfo_ops l2_cache_ops; - -enum { - DIR_CORR = 0, - DATA_CORR, - DATA_UNCORR, - DIR_UNCORR, -}; - -#ifdef CONFIG_DEBUG_FS -static struct dentry *sifive_test; - -static ssize_t l2_write(struct file *file, const char __user *data, - size_t count, loff_t *ppos) -{ - unsigned int val; - - if (kstrtouint_from_user(data, count, 0, &val)) - return -EINVAL; - if ((val < 0xFF) || (val >= 0x10000 && val < 0x100FF)) - writel(val, l2_base + SIFIVE_L2_ECCINJECTERR); - else - return -EINVAL; - return count; -} - -static const struct file_operations l2_fops = { - .owner = THIS_MODULE, - .open = simple_open, - .write = l2_write -}; - -static void setup_sifive_debug(void) -{ - sifive_test = debugfs_create_dir("sifive_l2_cache", NULL); - - debugfs_create_file("sifive_debug_inject_error", 0200, - sifive_test, NULL, &l2_fops); -} -#endif - -static void l2_config_read(void) -{ - u32 regval, val; - - regval = readl(l2_base + SIFIVE_L2_CONFIG); - val = regval & 0xFF; - pr_info("L2CACHE: No. of Banks in the cache: %d\n", val); - val = (regval & 0xFF00) >> 8; - pr_info("L2CACHE: No. of ways per bank: %d\n", val); - val = (regval & 0xFF0000) >> 16; - pr_info("L2CACHE: Sets per bank: %llu\n", (uint64_t)1 << val); - val = (regval & 0xFF000000) >> 24; - pr_info("L2CACHE: Bytes per cache block: %llu\n", (uint64_t)1 << val); - - regval = readl(l2_base + SIFIVE_L2_WAYENABLE); - pr_info("L2CACHE: Index of the largest way enabled: %d\n", regval); -} - -static const struct of_device_id sifive_l2_ids[] = { - { .compatible = "sifive,fu540-c000-ccache" }, - { .compatible = "sifive,fu740-c000-ccache" }, - { /* end of table */ }, -}; - -static ATOMIC_NOTIFIER_HEAD(l2_err_chain); - -int register_sifive_l2_error_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&l2_err_chain, nb); -} -EXPORT_SYMBOL_GPL(register_sifive_l2_error_notifier); - -int unregister_sifive_l2_error_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&l2_err_chain, nb); -} -EXPORT_SYMBOL_GPL(unregister_sifive_l2_error_notifier); - -static int l2_largest_wayenabled(void) -{ - return readl(l2_base + SIFIVE_L2_WAYENABLE) & 0xFF; -} - -static ssize_t number_of_ways_enabled_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", l2_largest_wayenabled()); -} - -static DEVICE_ATTR_RO(number_of_ways_enabled); - -static struct attribute *priv_attrs[] = { - &dev_attr_number_of_ways_enabled.attr, - NULL, -}; - -static const struct attribute_group priv_attr_group = { - .attrs = priv_attrs, -}; - -static const struct attribute_group *l2_get_priv_group(struct cacheinfo *this_leaf) -{ - /* We want to use private group for L2 cache only */ - if (this_leaf->level == 2) - return &priv_attr_group; - else - return NULL; -} - -static irqreturn_t l2_int_handler(int irq, void *device) -{ - unsigned int add_h, add_l; - - if (irq == g_irq[DIR_CORR]) { - add_h = readl(l2_base + SIFIVE_L2_DIRECCFIX_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DIRECCFIX_LOW); - pr_err("L2CACHE: DirError @ 0x%08X.%08X\n", add_h, add_l); - /* Reading this register clears the DirError interrupt sig */ - readl(l2_base + SIFIVE_L2_DIRECCFIX_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_CE, - "DirECCFix"); - } - if (irq == g_irq[DIR_UNCORR]) { - add_h = readl(l2_base + SIFIVE_L2_DIRECCFAIL_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DIRECCFAIL_LOW); - /* Reading this register clears the DirFail interrupt sig */ - readl(l2_base + SIFIVE_L2_DIRECCFAIL_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_UE, - "DirECCFail"); - panic("L2CACHE: DirFail @ 0x%08X.%08X\n", add_h, add_l); - } - if (irq == g_irq[DATA_CORR]) { - add_h = readl(l2_base + SIFIVE_L2_DATECCFIX_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DATECCFIX_LOW); - pr_err("L2CACHE: DataError @ 0x%08X.%08X\n", add_h, add_l); - /* Reading this register clears the DataError interrupt sig */ - readl(l2_base + SIFIVE_L2_DATECCFIX_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_CE, - "DatECCFix"); - } - if (irq == g_irq[DATA_UNCORR]) { - add_h = readl(l2_base + SIFIVE_L2_DATECCFAIL_HIGH); - add_l = readl(l2_base + SIFIVE_L2_DATECCFAIL_LOW); - pr_err("L2CACHE: DataFail @ 0x%08X.%08X\n", add_h, add_l); - /* Reading this register clears the DataFail interrupt sig */ - readl(l2_base + SIFIVE_L2_DATECCFAIL_COUNT); - atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_UE, - "DatECCFail"); - } - - return IRQ_HANDLED; -} - -static int __init sifive_l2_init(void) -{ - struct device_node *np; - struct resource res; - int i, rc, intr_num; - - np = of_find_matching_node(NULL, sifive_l2_ids); - if (!np) - return -ENODEV; - - if (of_address_to_resource(np, 0, &res)) - return -ENODEV; - - l2_base = ioremap(res.start, resource_size(&res)); - if (!l2_base) - return -ENOMEM; - - intr_num = of_property_count_u32_elems(np, "interrupts"); - if (!intr_num) { - pr_err("L2CACHE: no interrupts property\n"); - return -ENODEV; - } - - for (i = 0; i < intr_num; i++) { - g_irq[i] = irq_of_parse_and_map(np, i); - rc = request_irq(g_irq[i], l2_int_handler, 0, "l2_ecc", NULL); - if (rc) { - pr_err("L2CACHE: Could not request IRQ %d\n", g_irq[i]); - return rc; - } - } - - l2_config_read(); - - l2_cache_ops.get_priv_group = l2_get_priv_group; - riscv_set_cacheinfo_ops(&l2_cache_ops); - -#ifdef CONFIG_DEBUG_FS - setup_sifive_debug(); -#endif - return 0; -} -device_initcall(sifive_l2_init); diff --git a/include/soc/sifive/sifive_ccache.h b/include/soc/sifive/sifive_ccache.h new file mode 100644 index 000000000000..4d4ed49388a0 --- /dev/null +++ b/include/soc/sifive/sifive_ccache.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * SiFive Composable Cache Controller header file + * + */ + +#ifndef __SOC_SIFIVE_CCACHE_H +#define __SOC_SIFIVE_CCACHE_H + +extern int register_sifive_ccache_error_notifier(struct notifier_block *nb); +extern int unregister_sifive_ccache_error_notifier(struct notifier_block *nb); + +#define SIFIVE_CCACHE_ERR_TYPE_CE 0 +#define SIFIVE_CCACHE_ERR_TYPE_UE 1 + +#endif /* __SOC_SIFIVE_CCACHE_H */ diff --git a/include/soc/sifive/sifive_l2_cache.h b/include/soc/sifive/sifive_l2_cache.h deleted file mode 100644 index 92ade10ed67e..000000000000 --- a/include/soc/sifive/sifive_l2_cache.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * SiFive L2 Cache Controller header file - * - */ - -#ifndef __SOC_SIFIVE_L2_CACHE_H -#define __SOC_SIFIVE_L2_CACHE_H - -extern int register_sifive_l2_error_notifier(struct notifier_block *nb); -extern int unregister_sifive_l2_error_notifier(struct notifier_block *nb); - -#define SIFIVE_L2_ERR_TYPE_CE 0 -#define SIFIVE_L2_ERR_TYPE_UE 1 - -#endif /* __SOC_SIFIVE_L2_CACHE_H */ -- cgit From 95f196f3212bbc258611c22865aef12b98304e1d Mon Sep 17 00:00:00 2001 From: Zong Li Date: Tue, 13 Sep 2022 06:18:13 +0000 Subject: soc: sifive: ccache: determine the cache level from dts Composable cache could be L2 or L3 cache, use 'cache-level' property of device node to determine the level. Signed-off-by: Zong Li Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220913061817.22564-4-zong.li@sifive.com Signed-off-by: Palmer Dabbelt --- drivers/soc/sifive/sifive_ccache.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/soc/sifive/sifive_ccache.c b/drivers/soc/sifive/sifive_ccache.c index 949b824e89ad..b361b661ea09 100644 --- a/drivers/soc/sifive/sifive_ccache.c +++ b/drivers/soc/sifive/sifive_ccache.c @@ -38,6 +38,7 @@ static void __iomem *ccache_base; static int g_irq[SIFIVE_CCACHE_MAX_ECCINTR]; static struct riscv_cacheinfo_ops ccache_cache_ops; +static int level; enum { DIR_CORR = 0, @@ -144,7 +145,7 @@ static const struct attribute_group *ccache_get_priv_group(struct cacheinfo *this_leaf) { /* We want to use private group for composable cache only */ - if (this_leaf->level == 2) + if (this_leaf->level == level) return &priv_attr_group; else return NULL; @@ -215,6 +216,9 @@ static int __init sifive_ccache_init(void) if (!ccache_base) return -ENOMEM; + if (of_property_read_u32(np, "cache-level", &level)) + return -ENOENT; + intr_num = of_property_count_u32_elems(np, "interrupts"); if (!intr_num) { pr_err("CCACHE: no interrupts property\n"); -- cgit From 3fb787e5bad50687a65ded7f3bb805cab70dff59 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 13 Sep 2022 06:18:14 +0000 Subject: soc: sifive: ccache: reduce printing on init The driver prints out 6 lines on startup, which can easily be redcued to two lines without losing any information. Note, to make the types work better, uint64_t has been replaced with ULL to make the unsigned long long match the format in the print statement. Signed-off-by: Ben Dooks Signed-off-by: Zong Li Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220913061817.22564-5-zong.li@sifive.com Signed-off-by: Palmer Dabbelt --- drivers/soc/sifive/sifive_ccache.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-) diff --git a/drivers/soc/sifive/sifive_ccache.c b/drivers/soc/sifive/sifive_ccache.c index b361b661ea09..17080af7dfa0 100644 --- a/drivers/soc/sifive/sifive_ccache.c +++ b/drivers/soc/sifive/sifive_ccache.c @@ -81,20 +81,17 @@ static void setup_sifive_debug(void) static void ccache_config_read(void) { - u32 regval, val; - - regval = readl(ccache_base + SIFIVE_CCACHE_CONFIG); - val = regval & 0xFF; - pr_info("CCACHE: No. of Banks in the cache: %d\n", val); - val = (regval & 0xFF00) >> 8; - pr_info("CCACHE: No. of ways per bank: %d\n", val); - val = (regval & 0xFF0000) >> 16; - pr_info("CCACHE: Sets per bank: %llu\n", (uint64_t)1 << val); - val = (regval & 0xFF000000) >> 24; - pr_info("CCACHE: Bytes per cache block: %llu\n", (uint64_t)1 << val); - - regval = readl(ccache_base + SIFIVE_CCACHE_WAYENABLE); - pr_info("CCACHE: Index of the largest way enabled: %d\n", regval); + u32 cfg; + + cfg = readl(ccache_base + SIFIVE_CCACHE_CONFIG); + + pr_info("CCACHE: %u banks, %u ways, sets/bank=%llu, bytes/block=%llu\n", + (cfg & 0xff), (cfg >> 8) & 0xff, + BIT_ULL((cfg >> 16) & 0xff), + BIT_ULL((cfg >> 24) & 0xff)); + + cfg = readl(ccache_base + SIFIVE_CCACHE_WAYENABLE); + pr_info("CCACHE: Index of the largest way enabled: %u\n", cfg); } static const struct of_device_id sifive_ccache_ids[] = { -- cgit From 696ab9bda22a770d079dc3a23bac9aaa553d98f4 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 13 Sep 2022 06:18:15 +0000 Subject: soc: sifive: ccache: use pr_fmt() to remove CCACHE: prefixes Use the pr_fmt() macro to prefix all the output with "CCACHE:" to avoid having to write it out each time, or make a large diff when the next change comes along. Signed-off-by: Ben Dooks Signed-off-by: Zong Li Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220913061817.22564-6-zong.li@sifive.com Signed-off-by: Palmer Dabbelt --- drivers/soc/sifive/sifive_ccache.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/soc/sifive/sifive_ccache.c b/drivers/soc/sifive/sifive_ccache.c index 17080af7dfa0..91f0c2b32ea2 100644 --- a/drivers/soc/sifive/sifive_ccache.c +++ b/drivers/soc/sifive/sifive_ccache.c @@ -5,6 +5,9 @@ * Copyright (C) 2018-2022 SiFive, Inc. * */ + +#define pr_fmt(fmt) "CCACHE: " fmt + #include #include #include @@ -85,13 +88,13 @@ static void ccache_config_read(void) cfg = readl(ccache_base + SIFIVE_CCACHE_CONFIG); - pr_info("CCACHE: %u banks, %u ways, sets/bank=%llu, bytes/block=%llu\n", + pr_info("%u banks, %u ways, sets/bank=%llu, bytes/block=%llu\n", (cfg & 0xff), (cfg >> 8) & 0xff, BIT_ULL((cfg >> 16) & 0xff), BIT_ULL((cfg >> 24) & 0xff)); cfg = readl(ccache_base + SIFIVE_CCACHE_WAYENABLE); - pr_info("CCACHE: Index of the largest way enabled: %u\n", cfg); + pr_info("Index of the largest way enabled: %u\n", cfg); } static const struct of_device_id sifive_ccache_ids[] = { @@ -155,7 +158,7 @@ static irqreturn_t ccache_int_handler(int irq, void *device) if (irq == g_irq[DIR_CORR]) { add_h = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_HIGH); add_l = readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_LOW); - pr_err("CCACHE: DirError @ 0x%08X.%08X\n", add_h, add_l); + pr_err("DirError @ 0x%08X.%08X\n", add_h, add_l); /* Reading this register clears the DirError interrupt sig */ readl(ccache_base + SIFIVE_CCACHE_DIRECCFIX_COUNT); atomic_notifier_call_chain(&ccache_err_chain, @@ -175,7 +178,7 @@ static irqreturn_t ccache_int_handler(int irq, void *device) if (irq == g_irq[DATA_CORR]) { add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_HIGH); add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_LOW); - pr_err("CCACHE: DataError @ 0x%08X.%08X\n", add_h, add_l); + pr_err("DataError @ 0x%08X.%08X\n", add_h, add_l); /* Reading this register clears the DataError interrupt sig */ readl(ccache_base + SIFIVE_CCACHE_DATECCFIX_COUNT); atomic_notifier_call_chain(&ccache_err_chain, @@ -185,7 +188,7 @@ static irqreturn_t ccache_int_handler(int irq, void *device) if (irq == g_irq[DATA_UNCORR]) { add_h = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_HIGH); add_l = readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_LOW); - pr_err("CCACHE: DataFail @ 0x%08X.%08X\n", add_h, add_l); + pr_err("DataFail @ 0x%08X.%08X\n", add_h, add_l); /* Reading this register clears the DataFail interrupt sig */ readl(ccache_base + SIFIVE_CCACHE_DATECCFAIL_COUNT); atomic_notifier_call_chain(&ccache_err_chain, @@ -218,7 +221,7 @@ static int __init sifive_ccache_init(void) intr_num = of_property_count_u32_elems(np, "interrupts"); if (!intr_num) { - pr_err("CCACHE: no interrupts property\n"); + pr_err("No interrupts property\n"); return -ENODEV; } @@ -227,7 +230,7 @@ static int __init sifive_ccache_init(void) rc = request_irq(g_irq[i], ccache_int_handler, 0, "ccache_ecc", NULL); if (rc) { - pr_err("CCACHE: Could not request IRQ %d\n", g_irq[i]); + pr_err("Could not request IRQ %d\n", g_irq[i]); return rc; } } -- cgit From afc7a5834f0de13aee46df62f09e479c1bbf7b9d Mon Sep 17 00:00:00 2001 From: Zong Li Date: Tue, 13 Sep 2022 06:18:16 +0000 Subject: soc: sifive: ccache: define the macro for the register shifts Define the macro for the register shifts, it could make the code be more readable Signed-off-by: Zong Li Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220913061817.22564-7-zong.li@sifive.com Signed-off-by: Palmer Dabbelt --- drivers/soc/sifive/sifive_ccache.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/soc/sifive/sifive_ccache.c b/drivers/soc/sifive/sifive_ccache.c index 91f0c2b32ea2..1c171150e878 100644 --- a/drivers/soc/sifive/sifive_ccache.c +++ b/drivers/soc/sifive/sifive_ccache.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -33,6 +34,11 @@ #define SIFIVE_CCACHE_DATECCFAIL_COUNT 0x168 #define SIFIVE_CCACHE_CONFIG 0x00 +#define SIFIVE_CCACHE_CONFIG_BANK_MASK GENMASK_ULL(7, 0) +#define SIFIVE_CCACHE_CONFIG_WAYS_MASK GENMASK_ULL(15, 8) +#define SIFIVE_CCACHE_CONFIG_SETS_MASK GENMASK_ULL(23, 16) +#define SIFIVE_CCACHE_CONFIG_BLKS_MASK GENMASK_ULL(31, 24) + #define SIFIVE_CCACHE_WAYENABLE 0x08 #define SIFIVE_CCACHE_ECCINJECTERR 0x40 @@ -87,11 +93,11 @@ static void ccache_config_read(void) u32 cfg; cfg = readl(ccache_base + SIFIVE_CCACHE_CONFIG); - - pr_info("%u banks, %u ways, sets/bank=%llu, bytes/block=%llu\n", - (cfg & 0xff), (cfg >> 8) & 0xff, - BIT_ULL((cfg >> 16) & 0xff), - BIT_ULL((cfg >> 24) & 0xff)); + pr_info("%llu banks, %llu ways, sets/bank=%llu, bytes/block=%llu\n", + FIELD_GET(SIFIVE_CCACHE_CONFIG_BANK_MASK, cfg), + FIELD_GET(SIFIVE_CCACHE_CONFIG_WAYS_MASK, cfg), + BIT_ULL(FIELD_GET(SIFIVE_CCACHE_CONFIG_SETS_MASK, cfg)), + BIT_ULL(FIELD_GET(SIFIVE_CCACHE_CONFIG_BLKS_MASK, cfg))); cfg = readl(ccache_base + SIFIVE_CCACHE_WAYENABLE); pr_info("Index of the largest way enabled: %u\n", cfg); -- cgit From da29dbcda49d60f34055df19bd4783b889fc7dfc Mon Sep 17 00:00:00 2001 From: Greentime Hu Date: Tue, 13 Sep 2022 06:18:17 +0000 Subject: riscv: Add cache information in AUX vector There are no standard CSR registers to provide cache information, the way for RISC-V is to get this information from DT. sysconf syscall could use them to get information of cache through AUX vector. The result of 'getconf -a|grep -i cache' as follows: LEVEL1_ICACHE_SIZE 32768 LEVEL1_ICACHE_ASSOC 2 LEVEL1_ICACHE_LINESIZE 64 LEVEL1_DCACHE_SIZE 32768 LEVEL1_DCACHE_ASSOC 4 LEVEL1_DCACHE_LINESIZE 64 LEVEL2_CACHE_SIZE 524288 LEVEL2_CACHE_ASSOC 8 LEVEL2_CACHE_LINESIZE 64 LEVEL3_CACHE_SIZE 4194304 LEVEL3_CACHE_ASSOC 16 LEVEL3_CACHE_LINESIZE 64 LEVEL4_CACHE_SIZE 0 LEVEL4_CACHE_ASSOC 0 LEVEL4_CACHE_LINESIZE 0 Signed-off-by: Greentime Hu Signed-off-by: Zong Li Suggested-by: Zong Li Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220913061817.22564-8-zong.li@sifive.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/elf.h | 4 ++++ arch/riscv/include/uapi/asm/auxvec.h | 4 +++- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h index 14fc7342490b..e7acffdf21d2 100644 --- a/arch/riscv/include/asm/elf.h +++ b/arch/riscv/include/asm/elf.h @@ -99,6 +99,10 @@ do { \ get_cache_size(2, CACHE_TYPE_UNIFIED)); \ NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, \ get_cache_geometry(2, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L3_CACHESIZE, \ + get_cache_size(3, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L3_CACHEGEOMETRY, \ + get_cache_geometry(3, CACHE_TYPE_UNIFIED)); \ } while (0) #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h index 32c73ba1d531..fb187a33ce58 100644 --- a/arch/riscv/include/uapi/asm/auxvec.h +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -30,8 +30,10 @@ #define AT_L1D_CACHEGEOMETRY 43 #define AT_L2_CACHESIZE 44 #define AT_L2_CACHEGEOMETRY 45 +#define AT_L3_CACHESIZE 46 +#define AT_L3_CACHEGEOMETRY 47 /* entries in ARCH_DLINFO */ -#define AT_VECTOR_SIZE_ARCH 7 +#define AT_VECTOR_SIZE_ARCH 9 #endif /* _UAPI_ASM_RISCV_AUXVEC_H */ -- cgit From a8616d2dc193b6becc36b5f3cfeaa9ac7a5762f9 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Sat, 24 Sep 2022 15:07:37 +0800 Subject: riscv: vdso: fix NULL deference in vdso_join_timens() when vfork Testing tools/testing/selftests/timens/vfork_exec.c got below kernel log: [ 6.838454] Unable to handle kernel access to user memory without uaccess routines at virtual address 0000000000000020 [ 6.842255] Oops [#1] [ 6.842871] Modules linked in: [ 6.844249] CPU: 1 PID: 64 Comm: vfork_exec Not tainted 6.0.0-rc3-rt15+ #8 [ 6.845861] Hardware name: riscv-virtio,qemu (DT) [ 6.848009] epc : vdso_join_timens+0xd2/0x110 [ 6.850097] ra : vdso_join_timens+0xd2/0x110 [ 6.851164] epc : ffffffff8000635c ra : ffffffff8000635c sp : ff6000000181fbf0 [ 6.852562] gp : ffffffff80cff648 tp : ff60000000fdb700 t0 : 3030303030303030 [ 6.853852] t1 : 0000000000000030 t2 : 3030303030303030 s0 : ff6000000181fc40 [ 6.854984] s1 : ff60000001e6c000 a0 : 0000000000000010 a1 : ffffffff8005654c [ 6.856221] a2 : 00000000ffffefff a3 : 0000000000000000 a4 : 0000000000000000 [ 6.858114] a5 : 0000000000000000 a6 : 0000000000000008 a7 : 0000000000000038 [ 6.859484] s2 : ff60000001e6c068 s3 : ff6000000108abb0 s4 : 0000000000000000 [ 6.860751] s5 : 0000000000001000 s6 : ffffffff8089dc40 s7 : ffffffff8089dc38 [ 6.862029] s8 : ffffffff8089dc30 s9 : ff60000000fdbe38 s10: 000000000000005e [ 6.863304] s11: ffffffff80cc3510 t3 : ffffffff80d1112f t4 : ffffffff80d1112f [ 6.864565] t5 : ffffffff80d11130 t6 : ff6000000181fa00 [ 6.865561] status: 0000000000000120 badaddr: 0000000000000020 cause: 000000000000000d [ 6.868046] [] timens_commit+0x38/0x11a [ 6.869089] [] timens_on_fork+0x72/0xb4 [ 6.870055] [] begin_new_exec+0x3c6/0x9f0 [ 6.871231] [] load_elf_binary+0x628/0x1214 [ 6.872304] [] bprm_execve+0x1f2/0x4e4 [ 6.873243] [] do_execveat_common+0x16e/0x1ee [ 6.874258] [] sys_execve+0x3c/0x48 [ 6.875162] [] ret_from_syscall+0x0/0x2 [ 6.877484] ---[ end trace 0000000000000000 ]--- This is because the mm->context.vdso_info is NULL in vfork case. From another side, mm->context.vdso_info either points to vdso info for RV64 or vdso info for compat, there's no need to bloat riscv's mm_context_t, we can handle the difference when setup the additional page for vdso. Signed-off-by: Jisheng Zhang Suggested-by: Palmer Dabbelt Fixes: 3092eb456375 ("riscv: compat: vdso: Add setup additional pages implementation") Link: https://lore.kernel.org/r/20220924070737.3048-1-jszhang@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/mmu.h | 1 - arch/riscv/kernel/vdso.c | 13 ++++++++++--- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h index cedcf8ea3c76..0099dc116168 100644 --- a/arch/riscv/include/asm/mmu.h +++ b/arch/riscv/include/asm/mmu.h @@ -16,7 +16,6 @@ typedef struct { atomic_long_t id; #endif void *vdso; - void *vdso_info; #ifdef CONFIG_SMP /* A local icache flush is needed before user execution can resume. */ cpumask_t icache_stale_mask; diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 69b05b6c181b..4abc9aebdfae 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -60,6 +60,11 @@ struct __vdso_info { struct vm_special_mapping *cm; }; +static struct __vdso_info vdso_info; +#ifdef CONFIG_COMPAT +static struct __vdso_info compat_vdso_info; +#endif + static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { @@ -114,15 +119,18 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { struct mm_struct *mm = task->mm; struct vm_area_struct *vma; - struct __vdso_info *vdso_info = mm->context.vdso_info; mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, vdso_info->dm)) + if (vma_is_special_mapping(vma, vdso_info.dm)) zap_page_range(vma, vma->vm_start, size); +#ifdef CONFIG_COMPAT + if (vma_is_special_mapping(vma, compat_vdso_info.dm)) + zap_page_range(vma, vma->vm_start, size); +#endif } mmap_read_unlock(mm); @@ -264,7 +272,6 @@ static int __setup_additional_pages(struct mm_struct *mm, vdso_base += VVAR_SIZE; mm->context.vdso = (void *)vdso_base; - mm->context.vdso_info = (void *)vdso_info; ret = _install_special_mapping(mm, vdso_base, vdso_text_len, -- cgit From 5a5294fbe0200d1327f0e089135dad77b45aa2ee Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Wed, 28 Sep 2022 06:18:07 -0700 Subject: RISC-V: Re-enable counter access from userspace These counters were part of the ISA when we froze the uABI, removing them breaks userspace. Link: https://lore.kernel.org/all/YxEhC%2FmDW1lFt36J@aurel32.net/ Fixes: e9991434596f ("RISC-V: Add perf platform driver based on SBI PMU extension") Tested-by: Conor Dooley Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220928131807.30386-1-palmer@rivosinc.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- drivers/perf/riscv_pmu_sbi.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 15e5a47be7d5..3852c18362f5 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -652,8 +652,11 @@ static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node) struct riscv_pmu *pmu = hlist_entry_safe(node, struct riscv_pmu, node); struct cpu_hw_events *cpu_hw_evt = this_cpu_ptr(pmu->hw_events); - /* Enable the access for TIME csr only from the user mode now */ - csr_write(CSR_SCOUNTEREN, 0x2); + /* + * Enable the access for CYCLE, TIME, and INSTRET CSRs from userspace, + * as is necessary to maintain uABI compatibility. + */ + csr_write(CSR_SCOUNTEREN, 0x7); /* Stop all the counters so that they can be enabled from perf */ pmu_sbi_stop_all(pmu); -- cgit From c45fc916c2b2cc2a0587659c18d6ceef9b7299be Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Fri, 29 Jul 2022 12:11:17 +0100 Subject: riscv: enable software resend of irqs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The PLIC specification does not describe the interrupt pendings bits as read-write, only that they "can be read". To allow for retriggering of interrupts (and the use of the irq debugfs interface) enable HARDIRQS_SW_RESEND for RISC-V. Link: https://github.com/riscv/riscv-plic-spec/blob/master/riscv-plic.adoc#interrupt-pending-bits Signed-off-by: Conor Dooley Acked-by: Marc Zyngier Acked-by: Palmer Dabbelt Tested-by: Palmer Dabbelt # on QEMU Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20220729111116.259146-1-conor.dooley@microchip.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index e84f2742b6bb..c56bc70158ac 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -70,6 +70,7 @@ config RISCV select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO + select HARDIRQS_SW_RESEND select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL -- cgit From 9cc205e3c17d5716da7ebb7fa0c985555e95d009 Mon Sep 17 00:00:00 2001 From: "Maciej W. Rozycki" Date: Thu, 22 Sep 2022 22:56:06 +0100 Subject: RISC-V: Make port I/O string accessors actually work Fix port I/O string accessors such as `insb', `outsb', etc. which use the physical PCI port I/O address rather than the corresponding memory mapping to get at the requested location, which in turn breaks at least accesses made by our parport driver to a PCIe parallel port such as: PCI parallel port detected: 1415:c118, I/O at 0x1000(0x1008), IRQ 20 parport0: PC-style at 0x1000 (0x1008), irq 20, using FIFO [PCSPP,TRISTATE,COMPAT,EPP,ECP] causing a memory access fault: Unable to handle kernel access to user memory without uaccess routines at virtual address 0000000000001008 Oops [#1] Modules linked in: CPU: 1 PID: 350 Comm: cat Not tainted 6.0.0-rc2-00283-g10d4879f9ef0-dirty #23 Hardware name: SiFive HiFive Unmatched A00 (DT) epc : parport_pc_fifo_write_block_pio+0x266/0x416 ra : parport_pc_fifo_write_block_pio+0xb4/0x416 epc : ffffffff80542c3e ra : ffffffff80542a8c sp : ffffffd88899fc60 gp : ffffffff80fa2700 tp : ffffffd882b1e900 t0 : ffffffd883d0b000 t1 : ffffffffff000002 t2 : 4646393043330a38 s0 : ffffffd88899fcf0 s1 : 0000000000001000 a0 : 0000000000000010 a1 : 0000000000000000 a2 : ffffffd883d0a010 a3 : 0000000000000023 a4 : 00000000ffff8fbb a5 : ffffffd883d0a001 a6 : 0000000100000000 a7 : ffffffc800000000 s2 : ffffffffff000002 s3 : ffffffff80d28880 s4 : ffffffff80fa1f50 s5 : 0000000000001008 s6 : 0000000000000008 s7 : ffffffd883d0a000 s8 : 0004000000000000 s9 : ffffffff80dc1d80 s10: ffffffd8807e4000 s11: 0000000000000000 t3 : 00000000000000ff t4 : 393044410a303930 t5 : 0000000000001000 t6 : 0000000000040000 status: 0000000200000120 badaddr: 0000000000001008 cause: 000000000000000f [] parport_pc_compat_write_block_pio+0xfe/0x200 [] parport_write+0x46/0xf8 [] lp_write+0x158/0x2d2 [] vfs_write+0x8e/0x2c2 [] ksys_write+0x52/0xc2 [] sys_write+0xe/0x16 [] ret_from_syscall+0x0/0x2 ---[ end trace 0000000000000000 ]--- For simplicity address the problem by adding PCI_IOBASE to the physical address requested in the respective wrapper macros only, observing that the raw accessors such as `__insb', `__outsb', etc. are not supposed to be used other than by said macros. Remove the cast to `long' that is no longer needed on `addr' now that it is used as an offset from PCI_IOBASE and add parentheses around `addr' needed for predictable evaluation in macro expansion. No need to make said adjustments in separate changes given that current code is gravely broken and does not ever work. Signed-off-by: Maciej W. Rozycki Fixes: fab957c11efe2 ("RISC-V: Atomic and Locking Code") Cc: stable@vger.kernel.org # v4.15+ Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/alpine.DEB.2.21.2209220223080.29493@angie.orcam.me.uk Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/io.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index 69605a474270..92080a227937 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -101,9 +101,9 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr)) __io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr)) -#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count) -#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count) -#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count) +#define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count) +#define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count) +#define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count) __io_writes_outs(writes, u8, b, __io_bw(), __io_aw()) __io_writes_outs(writes, u16, w, __io_bw(), __io_aw()) @@ -115,22 +115,22 @@ __io_writes_outs(writes, u32, l, __io_bw(), __io_aw()) __io_writes_outs(outs, u8, b, __io_pbw(), __io_paw()) __io_writes_outs(outs, u16, w, __io_pbw(), __io_paw()) __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw()) -#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count) -#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count) -#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count) +#define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count) +#define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count) +#define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count) #ifdef CONFIG_64BIT __io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr)) #define readsq(addr, buffer, count) __readsq(addr, buffer, count) __io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr)) -#define insq(addr, buffer, count) __insq((void __iomem *)addr, buffer, count) +#define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count) __io_writes_outs(writes, u64, q, __io_bw(), __io_aw()) #define writesq(addr, buffer, count) __writesq(addr, buffer, count) __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) -#define outsq(addr, buffer, count) __outsq((void __iomem *)addr, buffer, count) +#define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count) #endif #include -- cgit From 4919d3eb2ec0ee364f7e3cf2d99646c1b224fae8 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 12 Oct 2022 20:07:01 +0200 Subject: rtc: cmos: Fix event handler registration ordering issue Because acpi_install_fixed_event_handler() enables the event automatically on success, it is incorrect to call it before the handler routine passed to it is ready to handle events. Unfortunately, the rtc-cmos driver does exactly the incorrect thing by calling cmos_wake_setup(), which passes rtc_handler() to acpi_install_fixed_event_handler(), before cmos_do_probe(), because rtc_handler() uses dev_get_drvdata() to get to the cmos object pointer and the driver data pointer is only populated in cmos_do_probe(). This leads to a NULL pointer dereference in rtc_handler() on boot if the RTC fixed event happens to be active at the init time. To address this issue, change the initialization ordering of the driver so that cmos_wake_setup() is always called after a successful cmos_do_probe() call. While at it, change cmos_pnp_probe() to call cmos_do_probe() after the initial if () statement used for computing the IRQ argument to be passed to cmos_do_probe() which is cleaner than calling it in each branch of that if () (local variable "irq" can be of type int, because it is passed to that function as an argument of type int). Note that commit 6492fed7d8c9 ("rtc: rtc-cmos: Do not check ACPI_FADT_LOW_POWER_S0") caused this issue to affect a larger number of systems, because previously it only affected systems with ACPI_FADT_LOW_POWER_S0 set, but it is present regardless of that commit. Fixes: 6492fed7d8c9 ("rtc: rtc-cmos: Do not check ACPI_FADT_LOW_POWER_S0") Fixes: a474aaedac99 ("rtc-cmos: move wake setup from ACPI glue into RTC driver") Link: https://lore.kernel.org/linux-acpi/20221010141630.zfzi7mk7zvnmclzy@techsingularity.net/ Reported-by: Mel Gorman Signed-off-by: Rafael J. Wysocki Reviewed-by: Bjorn Helgaas Tested-by: Mel Gorman Link: https://lore.kernel.org/r/5629262.DvuYhMxLoT@kreacher Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-cmos.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index bdb1df843c78..610413b4e9ca 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -1352,10 +1352,10 @@ static void cmos_check_acpi_rtc_status(struct device *dev, static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) { - cmos_wake_setup(&pnp->dev); + int irq, ret; if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0)) { - unsigned int irq = 0; + irq = 0; #ifdef CONFIG_X86 /* Some machines contain a PNP entry for the RTC, but * don't define the IRQ. It should always be safe to @@ -1364,13 +1364,17 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) if (nr_legacy_irqs()) irq = RTC_IRQ; #endif - return cmos_do_probe(&pnp->dev, - pnp_get_resource(pnp, IORESOURCE_IO, 0), irq); } else { - return cmos_do_probe(&pnp->dev, - pnp_get_resource(pnp, IORESOURCE_IO, 0), - pnp_irq(pnp, 0)); + irq = pnp_irq(pnp, 0); } + + ret = cmos_do_probe(&pnp->dev, pnp_get_resource(pnp, IORESOURCE_IO, 0), irq); + if (ret) + return ret; + + cmos_wake_setup(&pnp->dev); + + return 0; } static void cmos_pnp_remove(struct pnp_dev *pnp) @@ -1454,10 +1458,9 @@ static inline void cmos_of_init(struct platform_device *pdev) {} static int __init cmos_platform_probe(struct platform_device *pdev) { struct resource *resource; - int irq; + int irq, ret; cmos_of_init(pdev); - cmos_wake_setup(&pdev->dev); if (RTC_IOMAPPED) resource = platform_get_resource(pdev, IORESOURCE_IO, 0); @@ -1467,7 +1470,13 @@ static int __init cmos_platform_probe(struct platform_device *pdev) if (irq < 0) irq = -1; - return cmos_do_probe(&pdev->dev, resource, irq); + ret = cmos_do_probe(&pdev->dev, resource, irq); + if (ret) + return ret; + + cmos_wake_setup(&pdev->dev); + + return 0; } static int cmos_platform_remove(struct platform_device *pdev) -- cgit From e5f12a398371280649ccc9d6eb0b97fd42a5df98 Mon Sep 17 00:00:00 2001 From: Ke Sun Date: Sat, 8 Oct 2022 15:13:21 +0800 Subject: rtc: rv3028: Fix codestyle errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Compiler warnings： drivers/rtc/rtc-rv3028.c: In function 'rv3028_param_set': drivers/rtc/rtc-rv3028.c:559:20: warning: statement will never be executed [-Wswitch-unreachable] 559 | u8 mode; | ^~~~ drivers/rtc/rtc-rv3028.c: In function 'rv3028_param_get': drivers/rtc/rtc-rv3028.c:526:21: warning: statement will never be executed [-Wswitch-unreachable] 526 | u32 value; | ^~~~~ Fix it by moving the variable declaration to the beginning of the function. Cc: Alessandro Zummo Cc: Alexandre Belloni Cc: linux-rtc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Reported-by: k2ci Signed-off-by: Ke Sun Link: https://lore.kernel.org/r/20221008071321.1799971-1-sunke@kylinos.cn Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-rv3028.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c index cdc623b3e365..dd170e3efd83 100644 --- a/drivers/rtc/rtc-rv3028.c +++ b/drivers/rtc/rtc-rv3028.c @@ -521,10 +521,9 @@ static int rv3028_param_get(struct device *dev, struct rtc_param *param) { struct rv3028_data *rv3028 = dev_get_drvdata(dev); int ret; + u32 value; switch(param->param) { - u32 value; - case RTC_PARAM_BACKUP_SWITCH_MODE: ret = regmap_read(rv3028->regmap, RV3028_BACKUP, &value); if (ret < 0) @@ -554,9 +553,9 @@ static int rv3028_param_get(struct device *dev, struct rtc_param *param) static int rv3028_param_set(struct device *dev, struct rtc_param *param) { struct rv3028_data *rv3028 = dev_get_drvdata(dev); + u8 mode; switch(param->param) { - u8 mode; case RTC_PARAM_BACKUP_SWITCH_MODE: switch (param->uvalue) { case RTC_BSM_DISABLED: -- cgit From ab0c23b535f3f9d8345d8ad4c18c0a8594459d55 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 11 Oct 2022 17:07:45 +0100 Subject: MAINTAINERS: add RISC-V's patchwork The RISC-V patchwork instance on kernel.org has had some necromancy performed on it & will be used going forward. The statuses that are intended to be used are: - New: No action has been taken yet - Under Review: The maintainer is waiting for review comments from others - Changes Requested: Either the maintainer or a reviewer requested changes in the patch. The patch author is expected to submit a new version - Superseded: There's a new version of the patch available - Not Applicable: The patch is not intended for the RISC-V tree - Accepted: The patch has been applied - Rejected: The patch has been rejected, with reasons stated in an email Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20221011160744.2167025-1-conor@kernel.org/ Signed-off-by: Palmer Dabbelt --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index b3415857a812..557da4a32717 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17634,6 +17634,7 @@ M: Palmer Dabbelt M: Albert Ou L: linux-riscv@lists.infradead.org S: Supported +Q: https://patchwork.kernel.org/project/linux-riscv/list/ P: Documentation/riscv/patch-acceptance.rst T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git F: arch/riscv/ -- cgit From 28be7ca4fcfd69a2d52aaa331adbf9dbe91f9e6e Mon Sep 17 00:00:00 2001 From: Mark Tomlinson Date: Mon, 10 Oct 2022 15:46:13 +1300 Subject: tipc: Fix recognition of trial period The trial period exists until jiffies is after addr_trial_end. But as jiffies will eventually overflow, just using time_after will eventually give incorrect results. As the node address is set once the trial period ends, this can be used to know that we are not in the trial period. Fixes: e415577f57f4 ("tipc: correct discovery message handling during address trial period") Signed-off-by: Mark Tomlinson Signed-off-by: David S. Miller --- net/tipc/discover.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index da69e1abf68f..e8630707901e 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -148,8 +148,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, { struct net *net = d->net; struct tipc_net *tn = tipc_net(net); - bool trial = time_before(jiffies, tn->addr_trial_end); u32 self = tipc_own_addr(net); + bool trial = time_before(jiffies, tn->addr_trial_end) && !self; if (mtyp == DSC_TRIAL_FAIL_MSG) { if (!trial) -- cgit From 777ecaabd614d47c482a5c9031579e66da13989a Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Wed, 12 Oct 2022 17:25:14 +0200 Subject: tipc: fix an information leak in tipc_topsrv_kern_subscr Use a 8-byte write to initialize sub.usr_handle in tipc_topsrv_kern_subscr(), otherwise four bytes remain uninitialized when issuing setsockopt(..., SOL_TIPC, ...). This resulted in an infoleak reported by KMSAN when the packet was received: ===================================================== BUG: KMSAN: kernel-infoleak in copyout+0xbc/0x100 lib/iov_iter.c:169 instrument_copy_to_user ./include/linux/instrumented.h:121 copyout+0xbc/0x100 lib/iov_iter.c:169 _copy_to_iter+0x5c0/0x20a0 lib/iov_iter.c:527 copy_to_iter ./include/linux/uio.h:176 simple_copy_to_iter+0x64/0xa0 net/core/datagram.c:513 __skb_datagram_iter+0x123/0xdc0 net/core/datagram.c:419 skb_copy_datagram_iter+0x58/0x200 net/core/datagram.c:527 skb_copy_datagram_msg ./include/linux/skbuff.h:3903 packet_recvmsg+0x521/0x1e70 net/packet/af_packet.c:3469 ____sys_recvmsg+0x2c4/0x810 net/socket.c:? ___sys_recvmsg+0x217/0x840 net/socket.c:2743 __sys_recvmsg net/socket.c:2773 __do_sys_recvmsg net/socket.c:2783 __se_sys_recvmsg net/socket.c:2780 __x64_sys_recvmsg+0x364/0x540 net/socket.c:2780 do_syscall_x64 arch/x86/entry/common.c:50 do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd arch/x86/entry/entry_64.S:120 ... Uninit was stored to memory at: tipc_sub_subscribe+0x42d/0xb50 net/tipc/subscr.c:156 tipc_conn_rcv_sub+0x246/0x620 net/tipc/topsrv.c:375 tipc_topsrv_kern_subscr+0x2e8/0x400 net/tipc/topsrv.c:579 tipc_group_create+0x4e7/0x7d0 net/tipc/group.c:190 tipc_sk_join+0x2a8/0x770 net/tipc/socket.c:3084 tipc_setsockopt+0xae5/0xe40 net/tipc/socket.c:3201 __sys_setsockopt+0x87f/0xdc0 net/socket.c:2252 __do_sys_setsockopt net/socket.c:2263 __se_sys_setsockopt net/socket.c:2260 __x64_sys_setsockopt+0xe0/0x160 net/socket.c:2260 do_syscall_x64 arch/x86/entry/common.c:50 do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd arch/x86/entry/entry_64.S:120 Local variable sub created at: tipc_topsrv_kern_subscr+0x57/0x400 net/tipc/topsrv.c:562 tipc_group_create+0x4e7/0x7d0 net/tipc/group.c:190 Bytes 84-87 of 88 are uninitialized Memory access of size 88 starts at ffff88801ed57cd0 Data copied to user address 0000000020000400 ... ===================================================== Signed-off-by: Alexander Potapenko Fixes: 026321c6d056a5 ("tipc: rename tipc_server to tipc_topsrv") Signed-off-by: David S. Miller --- net/tipc/topsrv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 5522865deae9..14fd05fd6107 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -568,7 +568,7 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.seq.upper = upper; sub.timeout = TIPC_WAIT_FOREVER; sub.filter = filter; - *(u32 *)&sub.usr_handle = port; + *(u64 *)&sub.usr_handle = (u64)port; con = tipc_conn_alloc(tipc_topsrv(net)); if (IS_ERR(con)) -- cgit From a2550d3ce53c68f54042bc5e468c4d07491ffe0e Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Wed, 12 Oct 2022 19:18:36 +0200 Subject: net: dsa: qca8k: fix inband mgmt for big-endian systems The header and the data of the skb for the inband mgmt requires to be in little-endian. This is problematic for big-endian system as the mgmt header is written in the cpu byte order. Fix this by converting each value for the mgmt header and data to little-endian, and convert to cpu byte order the mgmt header and data sent by the switch. Fixes: 5950c7c0a68c ("net: dsa: qca8k: add support for mgmt read/write in Ethernet packet") Tested-by: Pawel Dembicki Tested-by: Lech Perczak Signed-off-by: Christian Marangi Reviewed-by: Lech Perczak Signed-off-by: David S. Miller --- drivers/net/dsa/qca/qca8k-8xxx.c | 63 ++++++++++++++++++++++++++++++---------- include/linux/dsa/tag_qca.h | 6 ++-- 2 files changed, 50 insertions(+), 19 deletions(-) diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 5669c92c93f7..644338ca0510 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -137,27 +137,42 @@ static void qca8k_rw_reg_ack_handler(struct dsa_switch *ds, struct sk_buff *skb) struct qca8k_mgmt_eth_data *mgmt_eth_data; struct qca8k_priv *priv = ds->priv; struct qca_mgmt_ethhdr *mgmt_ethhdr; + u32 command; u8 len, cmd; + int i; mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb_mac_header(skb); mgmt_eth_data = &priv->mgmt_eth_data; - cmd = FIELD_GET(QCA_HDR_MGMT_CMD, mgmt_ethhdr->command); - len = FIELD_GET(QCA_HDR_MGMT_LENGTH, mgmt_ethhdr->command); + command = get_unaligned_le32(&mgmt_ethhdr->command); + cmd = FIELD_GET(QCA_HDR_MGMT_CMD, command); + len = FIELD_GET(QCA_HDR_MGMT_LENGTH, command); /* Make sure the seq match the requested packet */ - if (mgmt_ethhdr->seq == mgmt_eth_data->seq) + if (get_unaligned_le32(&mgmt_ethhdr->seq) == mgmt_eth_data->seq) mgmt_eth_data->ack = true; if (cmd == MDIO_READ) { - mgmt_eth_data->data[0] = mgmt_ethhdr->mdio_data; + u32 *val = mgmt_eth_data->data; + + *val = get_unaligned_le32(&mgmt_ethhdr->mdio_data); /* Get the rest of the 12 byte of data. * The read/write function will extract the requested data. */ - if (len > QCA_HDR_MGMT_DATA1_LEN) - memcpy(mgmt_eth_data->data + 1, skb->data, - QCA_HDR_MGMT_DATA2_LEN); + if (len > QCA_HDR_MGMT_DATA1_LEN) { + __le32 *data2 = (__le32 *)skb->data; + int data_len = min_t(int, QCA_HDR_MGMT_DATA2_LEN, + len - QCA_HDR_MGMT_DATA1_LEN); + + val++; + + for (i = sizeof(u32); i <= data_len; i += sizeof(u32)) { + *val = get_unaligned_le32(data2); + val++; + data2++; + } + } } complete(&mgmt_eth_data->rw_done); @@ -169,8 +184,10 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 * struct qca_mgmt_ethhdr *mgmt_ethhdr; unsigned int real_len; struct sk_buff *skb; - u32 *data2; + __le32 *data2; + u32 command; u16 hdr; + int i; skb = dev_alloc_skb(QCA_HDR_MGMT_PKT_LEN); if (!skb) @@ -199,20 +216,32 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 * hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, BIT(0)); hdr |= FIELD_PREP(QCA_HDR_XMIT_CONTROL, QCA_HDR_XMIT_TYPE_RW_REG); - mgmt_ethhdr->command = FIELD_PREP(QCA_HDR_MGMT_ADDR, reg); - mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_LENGTH, real_len); - mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CMD, cmd); - mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CHECK_CODE, + command = FIELD_PREP(QCA_HDR_MGMT_ADDR, reg); + command |= FIELD_PREP(QCA_HDR_MGMT_LENGTH, real_len); + command |= FIELD_PREP(QCA_HDR_MGMT_CMD, cmd); + command |= FIELD_PREP(QCA_HDR_MGMT_CHECK_CODE, QCA_HDR_MGMT_CHECK_CODE_VAL); + put_unaligned_le32(command, &mgmt_ethhdr->command); + if (cmd == MDIO_WRITE) - mgmt_ethhdr->mdio_data = *val; + put_unaligned_le32(*val, &mgmt_ethhdr->mdio_data); mgmt_ethhdr->hdr = htons(hdr); data2 = skb_put_zero(skb, QCA_HDR_MGMT_DATA2_LEN + QCA_HDR_MGMT_PADDING_LEN); - if (cmd == MDIO_WRITE && len > QCA_HDR_MGMT_DATA1_LEN) - memcpy(data2, val + 1, len - QCA_HDR_MGMT_DATA1_LEN); + if (cmd == MDIO_WRITE && len > QCA_HDR_MGMT_DATA1_LEN) { + int data_len = min_t(int, QCA_HDR_MGMT_DATA2_LEN, + len - QCA_HDR_MGMT_DATA1_LEN); + + val++; + + for (i = sizeof(u32); i <= data_len; i += sizeof(u32)) { + put_unaligned_le32(*val, data2); + data2++; + val++; + } + } return skb; } @@ -220,9 +249,11 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 * static void qca8k_mdio_header_fill_seq_num(struct sk_buff *skb, u32 seq_num) { struct qca_mgmt_ethhdr *mgmt_ethhdr; + u32 seq; + seq = FIELD_PREP(QCA_HDR_MGMT_SEQ_NUM, seq_num); mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb->data; - mgmt_ethhdr->seq = FIELD_PREP(QCA_HDR_MGMT_SEQ_NUM, seq_num); + put_unaligned_le32(seq, &mgmt_ethhdr->seq); } static int qca8k_read_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h index 50be7cbd93a5..0e176da1e43f 100644 --- a/include/linux/dsa/tag_qca.h +++ b/include/linux/dsa/tag_qca.h @@ -61,9 +61,9 @@ struct sk_buff; /* Special struct emulating a Ethernet header */ struct qca_mgmt_ethhdr { - u32 command; /* command bit 31:0 */ - u32 seq; /* seq 63:32 */ - u32 mdio_data; /* first 4byte mdio */ + __le32 command; /* command bit 31:0 */ + __le32 seq; /* seq 63:32 */ + __le32 mdio_data; /* first 4byte mdio */ __be16 hdr; /* qca hdr */ } __packed; -- cgit From 0d4636f7d72df3179b20a2d32b647881917a5e2a Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Wed, 12 Oct 2022 19:18:37 +0200 Subject: net: dsa: qca8k: fix ethtool autocast mib for big-endian systems The switch sends autocast mib in little-endian. This is problematic for big-endian system as the values needs to be converted. Fix this by converting each mib value to cpu byte order. Fixes: 5c957c7ca78c ("net: dsa: qca8k: add support for mib autocast in Ethernet packet") Tested-by: Pawel Dembicki Tested-by: Lech Perczak Signed-off-by: Christian Marangi Signed-off-by: David S. Miller --- drivers/net/dsa/qca/qca8k-8xxx.c | 20 ++++++++------------ include/linux/dsa/tag_qca.h | 2 +- 2 files changed, 9 insertions(+), 13 deletions(-) diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 644338ca0510..c5c3b4e92f28 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -1518,9 +1518,9 @@ static void qca8k_mib_autocast_handler(struct dsa_switch *ds, struct sk_buff *sk struct qca8k_priv *priv = ds->priv; const struct qca8k_mib_desc *mib; struct mib_ethhdr *mib_ethhdr; - int i, mib_len, offset = 0; - u64 *data; + __le32 *data2; u8 port; + int i; mib_ethhdr = (struct mib_ethhdr *)skb_mac_header(skb); mib_eth_data = &priv->mib_eth_data; @@ -1532,28 +1532,24 @@ static void qca8k_mib_autocast_handler(struct dsa_switch *ds, struct sk_buff *sk if (port != mib_eth_data->req_port) goto exit; - data = mib_eth_data->data; + data2 = (__le32 *)skb->data; for (i = 0; i < priv->info->mib_count; i++) { mib = &ar8327_mib[i]; /* First 3 mib are present in the skb head */ if (i < 3) { - data[i] = mib_ethhdr->data[i]; + mib_eth_data->data[i] = get_unaligned_le32(mib_ethhdr->data + i); continue; } - mib_len = sizeof(uint32_t); - /* Some mib are 64 bit wide */ if (mib->size == 2) - mib_len = sizeof(uint64_t); - - /* Copy the mib value from packet to the */ - memcpy(data + i, skb->data + offset, mib_len); + mib_eth_data->data[i] = get_unaligned_le64((__le64 *)data2); + else + mib_eth_data->data[i] = get_unaligned_le32(data2); - /* Set the offset for the next mib */ - offset += mib_len; + data2 += mib->size; } exit: diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h index 0e176da1e43f..b1b5720d89a5 100644 --- a/include/linux/dsa/tag_qca.h +++ b/include/linux/dsa/tag_qca.h @@ -73,7 +73,7 @@ enum mdio_cmd { }; struct mib_ethhdr { - u32 data[3]; /* first 3 mib counter */ + __le32 data[3]; /* first 3 mib counter */ __be16 hdr; /* qca hdr */ } __packed; -- cgit From aae425efdfd1b1d8452260a3cb49344ebf20b1f5 Mon Sep 17 00:00:00 2001 From: Jan Sokolowski Date: Wed, 12 Oct 2022 13:54:40 -0700 Subject: i40e: Fix DMA mappings leak During reallocation of RX buffers, new DMA mappings are created for those buffers. steps for reproduction: while : do for ((i=0; i<=8160; i=i+32)) do ethtool -G enp130s0f0 rx $i tx $i sleep 0.5 ethtool -g enp130s0f0 done done This resulted in crash: i40e 0000:01:00.1: Unable to allocate memory for the Rx descriptor ring, size=65536 Driver BUG WARNING: CPU: 0 PID: 4300 at net/core/xdp.c:141 xdp_rxq_info_unreg+0x43/0x50 Call Trace: i40e_free_rx_resources+0x70/0x80 [i40e] i40e_set_ringparam+0x27c/0x800 [i40e] ethnl_set_rings+0x1b2/0x290 genl_family_rcv_msg_doit.isra.15+0x10f/0x150 genl_family_rcv_msg+0xb3/0x160 ? rings_fill_reply+0x1a0/0x1a0 genl_rcv_msg+0x47/0x90 ? genl_family_rcv_msg+0x160/0x160 netlink_rcv_skb+0x4c/0x120 genl_rcv+0x24/0x40 netlink_unicast+0x196/0x230 netlink_sendmsg+0x204/0x3d0 sock_sendmsg+0x4c/0x50 __sys_sendto+0xee/0x160 ? handle_mm_fault+0xbe/0x1e0 ? syscall_trace_enter+0x1d3/0x2c0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x5b/0x1a0 entry_SYSCALL_64_after_hwframe+0x65/0xca RIP: 0033:0x7f5eac8b035b Missing register, driver bug WARNING: CPU: 0 PID: 4300 at net/core/xdp.c:119 xdp_rxq_info_unreg_mem_model+0x69/0x140 Call Trace: xdp_rxq_info_unreg+0x1e/0x50 i40e_free_rx_resources+0x70/0x80 [i40e] i40e_set_ringparam+0x27c/0x800 [i40e] ethnl_set_rings+0x1b2/0x290 genl_family_rcv_msg_doit.isra.15+0x10f/0x150 genl_family_rcv_msg+0xb3/0x160 ? rings_fill_reply+0x1a0/0x1a0 genl_rcv_msg+0x47/0x90 ? genl_family_rcv_msg+0x160/0x160 netlink_rcv_skb+0x4c/0x120 genl_rcv+0x24/0x40 netlink_unicast+0x196/0x230 netlink_sendmsg+0x204/0x3d0 sock_sendmsg+0x4c/0x50 __sys_sendto+0xee/0x160 ? handle_mm_fault+0xbe/0x1e0 ? syscall_trace_enter+0x1d3/0x2c0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x5b/0x1a0 entry_SYSCALL_64_after_hwframe+0x65/0xca RIP: 0033:0x7f5eac8b035b This was caused because of new buffers with different RX ring count should substitute older ones, but those buffers were freed in i40e_configure_rx_ring and reallocated again with i40e_alloc_rx_bi, thus kfree on rx_bi caused leak of already mapped DMA. Fix this by reallocating ZC with rx_bi_zc struct when BPF program loads. Additionally reallocate back to rx_bi when BPF program unloads. If BPF program is loaded/unloaded and XSK pools are created, reallocate RX queues accordingly in XSP_SETUP_XSK_POOL handler. Fixes: be1222b585fd ("i40e: Separate kernel allocated rx_bi rings from AF_XDP rings") Signed-off-by: Jan Sokolowski Signed-off-by: Mateusz Palczewski Signed-off-by: Jacob Keller Tested-by: Chandan (A Contingent Worker at Intel) Tested-by: Gurucharan (A Contingent worker at Intel) Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 3 -- drivers/net/ethernet/intel/i40e/i40e_main.c | 16 +++--- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 13 ++--- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 1 - drivers/net/ethernet/intel/i40e/i40e_xsk.c | 67 +++++++++++++++++++++++--- drivers/net/ethernet/intel/i40e/i40e_xsk.h | 2 +- 6 files changed, 74 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 7e75706f76db..87f36d1ce800 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2181,9 +2181,6 @@ static int i40e_set_ringparam(struct net_device *netdev, */ rx_rings[i].tail = hw->hw_addr + I40E_PRTGEN_STATUS; err = i40e_setup_rx_descriptors(&rx_rings[i]); - if (err) - goto rx_unwind; - err = i40e_alloc_rx_bi(&rx_rings[i]); if (err) goto rx_unwind; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2c07fa8ecfc8..b5dcd15ced36 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3566,12 +3566,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (ring->vsi->type == I40E_VSI_MAIN) xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - kfree(ring->rx_bi); ring->xsk_pool = i40e_xsk_pool(ring); if (ring->xsk_pool) { - ret = i40e_alloc_rx_bi_zc(ring); - if (ret) - return ret; ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); /* For AF_XDP ZC, we disallow packets to span on @@ -3589,9 +3585,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->queue_index); } else { - ret = i40e_alloc_rx_bi(ring); - if (ret) - return ret; ring->rx_buf_len = vsi->rx_buf_len; if (ring->vsi->type == I40E_VSI_MAIN) { ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -13296,6 +13289,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, i40e_reset_and_rebuild(pf, true, true); } + if (!i40e_enabled_xdp_vsi(vsi) && prog) { + if (i40e_realloc_rx_bi_zc(vsi, true)) + return -ENOMEM; + } else if (i40e_enabled_xdp_vsi(vsi) && !prog) { + if (i40e_realloc_rx_bi_zc(vsi, false)) + return -ENOMEM; + } + for (i = 0; i < vsi->num_queue_pairs; i++) WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog); @@ -13528,6 +13529,7 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) i40e_queue_pair_disable_irq(vsi, queue_pair); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); + i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 69e67eb6aea7..b97c95f89fa0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1457,14 +1457,6 @@ err: return -ENOMEM; } -int i40e_alloc_rx_bi(struct i40e_ring *rx_ring) -{ - unsigned long sz = sizeof(*rx_ring->rx_bi) * rx_ring->count; - - rx_ring->rx_bi = kzalloc(sz, GFP_KERNEL); - return rx_ring->rx_bi ? 0 : -ENOMEM; -} - static void i40e_clear_rx_bi(struct i40e_ring *rx_ring) { memset(rx_ring->rx_bi, 0, sizeof(*rx_ring->rx_bi) * rx_ring->count); @@ -1593,6 +1585,11 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) rx_ring->xdp_prog = rx_ring->vsi->xdp_prog; + rx_ring->rx_bi = + kcalloc(rx_ring->count, sizeof(*rx_ring->rx_bi), GFP_KERNEL); + if (!rx_ring->rx_bi) + return -ENOMEM; + return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 41f86e9535a0..768290dc6f48 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -469,7 +469,6 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); -int i40e_alloc_rx_bi(struct i40e_ring *rx_ring); /** * i40e_get_head - Retrieve head from head writeback diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 6d4009e0cbd6..cd7b52fb6b46 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -10,14 +10,6 @@ #include "i40e_txrx_common.h" #include "i40e_xsk.h" -int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring) -{ - unsigned long sz = sizeof(*rx_ring->rx_bi_zc) * rx_ring->count; - - rx_ring->rx_bi_zc = kzalloc(sz, GFP_KERNEL); - return rx_ring->rx_bi_zc ? 0 : -ENOMEM; -} - void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring) { memset(rx_ring->rx_bi_zc, 0, @@ -29,6 +21,58 @@ static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx) return &rx_ring->rx_bi_zc[idx]; } +/** + * i40e_realloc_rx_xdp_bi - reallocate SW ring for either XSK or normal buffer + * @rx_ring: Current rx ring + * @pool_present: is pool for XSK present + * + * Try allocating memory and return ENOMEM, if failed to allocate. + * If allocation was successful, substitute buffer with allocated one. + * Returns 0 on success, negative on failure + */ +static int i40e_realloc_rx_xdp_bi(struct i40e_ring *rx_ring, bool pool_present) +{ + size_t elem_size = pool_present ? sizeof(*rx_ring->rx_bi_zc) : + sizeof(*rx_ring->rx_bi); + void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL); + + if (!sw_ring) + return -ENOMEM; + + if (pool_present) { + kfree(rx_ring->rx_bi); + rx_ring->rx_bi = NULL; + rx_ring->rx_bi_zc = sw_ring; + } else { + kfree(rx_ring->rx_bi_zc); + rx_ring->rx_bi_zc = NULL; + rx_ring->rx_bi = sw_ring; + } + return 0; +} + +/** + * i40e_realloc_rx_bi_zc - reallocate rx SW rings + * @vsi: Current VSI + * @zc: is zero copy set + * + * Reallocate buffer for rx_rings that might be used by XSK. + * XDP requires more memory, than rx_buf provides. + * Returns 0 on success, negative on failure + */ +int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc) +{ + struct i40e_ring *rx_ring; + unsigned long q; + + for_each_set_bit(q, vsi->af_xdp_zc_qps, vsi->alloc_queue_pairs) { + rx_ring = vsi->rx_rings[q]; + if (i40e_realloc_rx_xdp_bi(rx_ring, zc)) + return -ENOMEM; + } + return 0; +} + /** * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a * certain ring/qid @@ -69,6 +113,10 @@ static int i40e_xsk_pool_enable(struct i40e_vsi *vsi, if (err) return err; + err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], true); + if (err) + return err; + err = i40e_queue_pair_enable(vsi, qid); if (err) return err; @@ -113,6 +161,9 @@ static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid) xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR); if (if_running) { + err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], false); + if (err) + return err; err = i40e_queue_pair_enable(vsi, qid); if (err) return err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index bb962987f300..821df248f8be 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -32,7 +32,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring); int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); -int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring); +int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc); void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring); #endif /* _I40E_XSK_H_ */ -- cgit From 0d87bbd39d7fd1135ab9eca672d760470f6508e8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 12 Oct 2022 15:55:20 -0700 Subject: tls: strp: make sure the TCP skbs do not have overlapping data TLS tries to get away with using the TCP input queue directly. This does not work if there is duplicated data (multiple skbs holding bytes for the same seq number range due to retransmits). Check for this condition and fall back to copy mode, it should be rare. Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 9b79e334dbd9..955ac3e0bf4d 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -273,7 +273,7 @@ static int tls_strp_read_copyin(struct tls_strparser *strp) return desc.error; } -static int tls_strp_read_short(struct tls_strparser *strp) +static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) { struct skb_shared_info *shinfo; struct page *page; @@ -283,7 +283,7 @@ static int tls_strp_read_short(struct tls_strparser *strp) * to read the data out. Otherwise the connection will stall. * Without pressure threshold of INT_MAX will never be ready. */ - if (likely(!tcp_epollin_ready(strp->sk, INT_MAX))) + if (likely(qshort && !tcp_epollin_ready(strp->sk, INT_MAX))) return 0; shinfo = skb_shinfo(strp->anchor); @@ -315,6 +315,27 @@ static int tls_strp_read_short(struct tls_strparser *strp) return 0; } +static bool tls_strp_check_no_dup(struct tls_strparser *strp) +{ + unsigned int len = strp->stm.offset + strp->stm.full_len; + struct sk_buff *skb; + u32 seq; + + skb = skb_shinfo(strp->anchor)->frag_list; + seq = TCP_SKB_CB(skb)->seq; + + while (skb->len < len) { + seq += skb->len; + len -= skb->len; + skb = skb->next; + + if (TCP_SKB_CB(skb)->seq != seq) + return false; + } + + return true; +} + static void tls_strp_load_anchor_with_queue(struct tls_strparser *strp, int len) { struct tcp_sock *tp = tcp_sk(strp->sk); @@ -373,7 +394,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) return tls_strp_read_copyin(strp); if (inq < strp->stm.full_len) - return tls_strp_read_short(strp); + return tls_strp_read_copy(strp, true); if (!strp->stm.full_len) { tls_strp_load_anchor_with_queue(strp, inq); @@ -387,9 +408,12 @@ static int tls_strp_read_sock(struct tls_strparser *strp) strp->stm.full_len = sz; if (!strp->stm.full_len || inq < strp->stm.full_len) - return tls_strp_read_short(strp); + return tls_strp_read_copy(strp, true); } + if (!tls_strp_check_no_dup(strp)) + return tls_strp_read_copy(strp, false); + strp->msg_ready = 1; tls_rx_msg_ready(strp); -- cgit From 3d6642eac74d9442fde232181aa52d26d47991df Mon Sep 17 00:00:00 2001 From: zhangxiangqian Date: Thu, 13 Oct 2022 15:41:12 +0800 Subject: net: macvlan: change schedule system_wq to system_unbound_wq For FT2000+/64 devices, when four virtual machines share the same physical network interface, DROP will occur due to the single core CPU performance problem. ip_check_defrag and macvlan_process_broadcast is on the same CPU. When the MACVLAN PORT increases, the CPU usage reaches more than 90%. bc_queue > bc_queue_len_used (default 1000), causing DROP. Signed-off-by: zhangxiangqian Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 8f8f73099de8..c5cfe8555199 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -361,7 +361,7 @@ static void macvlan_broadcast_enqueue(struct macvlan_port *port, } spin_unlock(&port->bc_queue.lock); - schedule_work(&port->bc_work); + queue_work(system_unbound_wq, &port->bc_work); if (err) goto free_nskb; -- cgit From 9a9a5d80ec9887814042c69768c2fee7961db7f4 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Thu, 13 Oct 2022 14:46:36 -0700 Subject: MAINTAINERS: git://github -> https://github.com for petkan Github deprecated the git:// links about a year ago, so let's move to the https:// URLs instead. Reported-by: Conor Dooley Link: https://github.blog/2021-09-01-improving-git-protocol-security-github/ Signed-off-by: Palmer Dabbelt Signed-off-by: David S. Miller --- MAINTAINERS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index a96c60c787af..fb514facd169 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21300,7 +21300,7 @@ L: linux-usb@vger.kernel.org L: netdev@vger.kernel.org S: Maintained W: https://github.com/petkan/pegasus -T: git git://github.com/petkan/pegasus.git +T: git https://github.com/petkan/pegasus.git F: drivers/net/usb/pegasus.* USB PHY LAYER @@ -21337,7 +21337,7 @@ L: linux-usb@vger.kernel.org L: netdev@vger.kernel.org S: Maintained W: https://github.com/petkan/rtl8150 -T: git git://github.com/petkan/rtl8150.git +T: git https://github.com/petkan/rtl8150.git F: drivers/net/usb/rtl8150.c USB SERIAL SUBSYSTEM -- cgit From 0c93411795513a0e8dfcb5bcc7bab756b98bfc73 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 13 Oct 2022 19:42:05 -0400 Subject: MAINTAINERS: nfc: s3fwrn5: Drop Krzysztof Opasiak Emails to Krzysztof Opasiak bounce ("Recipient address rejected: User unknown") so drop his email from maintainers of s3fwrn5 NFC bindings and driver. Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml | 1 - MAINTAINERS | 1 - 2 files changed, 2 deletions(-) diff --git a/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml index 64995cbb0f97..41c9760227cd 100644 --- a/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml +++ b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml @@ -8,7 +8,6 @@ title: Samsung S3FWRN5 NCI NFC Controller maintainers: - Krzysztof Kozlowski - - Krzysztof Opasiak properties: compatible: diff --git a/MAINTAINERS b/MAINTAINERS index fb514facd169..abbe88e1c50b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18217,7 +18217,6 @@ F: include/media/drv-intf/s3c_camif.h SAMSUNG S3FWRN5 NFC DRIVER M: Krzysztof Kozlowski -M: Krzysztof Opasiak L: linux-nfc@lists.01.org (subscribers-only) S: Maintained F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml -- cgit From aca7c13d3bee81a968337a5515411409ae9d095d Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 14 Oct 2022 10:13:55 +0200 Subject: parisc: fbdev/stifb: Align graphics memory size to 4MB Independend of the current graphics resolution, adjust the reported graphics card memory size to the next 4MB boundary. This fixes the fbtest program which expects a naturally aligned size. Signed-off-by: Helge Deller Cc: --- drivers/video/fbdev/stifb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 38a861e22c33..7753e586e65a 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1298,7 +1298,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) /* limit fbsize to max visible screen size */ if (fix->smem_len > yres*fix->line_length) - fix->smem_len = yres*fix->line_length; + fix->smem_len = ALIGN(yres*fix->line_length, 4*1024*1024); fix->accel = FB_ACCEL_NONE; -- cgit From 70be49f2f6223ddd2fcddb0089a40864c37e1494 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 14 Oct 2022 10:18:53 +0200 Subject: parisc: Fix userspace graphics card breakage due to pgtable special bit Commit df24e1783e6e ("parisc: Add vDSO support") introduced the vDSO support, for which a _PAGE_SPECIAL page table flag was needed. Since we wanted to keep every page table entry in 32-bits, this patch re-used the existing - but yet unused - _PAGE_DMB flag (which triggers a hardware break if a page is accessed) to store the special bit. But when graphics card memory is mmapped into userspace, the kernel uses vm_iomap_memory() which sets the the special flag. So, with the DMB bit set, every access to the graphics memory now triggered a hardware exception and segfaulted the userspace program. Fix this breakage by dropping the DMB bit when writing the page protection bits to the CPU TLB. In addition this patch adds a small optimization: if huge pages aren't configured (which is at least the case for 32-bit kernels), then the special bit is stored in the hpage (HUGE PAGE) bit instead. That way we can skip to reset the DMB bit. Fixes: df24e1783e6e ("parisc: Add vDSO support") Cc: # 5.18+ Signed-off-by: Helge Deller --- arch/parisc/include/asm/pgtable.h | 7 ++++++- arch/parisc/kernel/entry.S | 8 ++++++++ 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index df7b931865d2..ecd028854469 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -192,6 +192,11 @@ extern void __update_cache(pte_t pte); #define _PAGE_PRESENT_BIT 22 /* (0x200) Software: translation valid */ #define _PAGE_HPAGE_BIT 21 /* (0x400) Software: Huge Page */ #define _PAGE_USER_BIT 20 /* (0x800) Software: User accessible page */ +#ifdef CONFIG_HUGETLB_PAGE +#define _PAGE_SPECIAL_BIT _PAGE_DMB_BIT /* DMB feature is currently unused */ +#else +#define _PAGE_SPECIAL_BIT _PAGE_HPAGE_BIT /* use unused HUGE PAGE bit */ +#endif /* N.B. The bits are defined in terms of a 32 bit word above, so the */ /* following macro is ok for both 32 and 64 bit. */ @@ -219,7 +224,7 @@ extern void __update_cache(pte_t pte); #define _PAGE_PRESENT (1 << xlate_pabit(_PAGE_PRESENT_BIT)) #define _PAGE_HUGE (1 << xlate_pabit(_PAGE_HPAGE_BIT)) #define _PAGE_USER (1 << xlate_pabit(_PAGE_USER_BIT)) -#define _PAGE_SPECIAL (_PAGE_DMB) +#define _PAGE_SPECIAL (1 << xlate_pabit(_PAGE_SPECIAL_BIT)) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED) #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL) diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index df8102fb435f..0e5ebfe8d9d2 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -499,6 +499,10 @@ * Finally, _PAGE_READ goes in the top bit of PL1 (so we * trigger an access rights trap in user space if the user * tries to read an unreadable page */ +#if _PAGE_SPECIAL_BIT == _PAGE_DMB_BIT + /* need to drop DMB bit, as it's used as SPECIAL flag */ + depi 0,_PAGE_SPECIAL_BIT,1,\pte +#endif depd \pte,8,7,\prot /* PAGE_USER indicates the page can be read with user privileges, @@ -529,6 +533,10 @@ * makes the tlb entry for the differently formatted pa11 * insertion instructions */ .macro make_insert_tlb_11 spc,pte,prot +#if _PAGE_SPECIAL_BIT == _PAGE_DMB_BIT + /* need to drop DMB bit, as it's used as SPECIAL flag */ + depi 0,_PAGE_SPECIAL_BIT,1,\pte +#endif zdep \spc,30,15,\prot dep \pte,8,7,\prot extru,= \pte,_PAGE_NO_CACHE_BIT,1,%r0 -- cgit From 96cb9d0554457086664d3bd10630b11193d863f1 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Mon, 10 Oct 2022 09:06:07 -0600 Subject: hwrng: bcm2835 - use hwrng_msleep() instead of cpu_relax() Rather than busy looping, yield back to the scheduler and sleep for a bit in the event that there's no data. This should hopefully prevent the stalls that Mark reported: <6>[ 3.362859] Freeing initrd memory: 16196K <3>[ 23.160131] rcu: INFO: rcu_sched self-detected stall on CPU <3>[ 23.166057] rcu: 0-....: (2099 ticks this GP) idle=03b4/1/0x40000002 softirq=28/28 fqs=1050 <4>[ 23.174895] (t=2101 jiffies g=-1147 q=2353 ncpus=4) <4>[ 23.180203] CPU: 0 PID: 49 Comm: hwrng Not tainted 6.0.0 #1 <4>[ 23.186125] Hardware name: BCM2835 <4>[ 23.189837] PC is at bcm2835_rng_read+0x30/0x6c <4>[ 23.194709] LR is at hwrng_fillfn+0x71/0xf4 <4>[ 23.199218] pc : [] lr : [] psr: 40000033 <4>[ 23.205840] sp : f093df70 ip : 00000000 fp : 00000000 <4>[ 23.211404] r10: c3c7e800 r9 : 00000000 r8 : c17e6b20 <4>[ 23.216968] r7 : c17e6b64 r6 : c18b0a74 r5 : c07ccd99 r4 : c3f171c0 <4>[ 23.223855] r3 : 000fffff r2 : 00000040 r1 : c3c7e800 r0 : c3f171c0 <4>[ 23.230743] Flags: nZcv IRQs on FIQs on Mode SVC_32 ISA Thumb Segment none <4>[ 23.238426] Control: 50c5387d Table: 0020406a DAC: 00000051 <4>[ 23.244519] CPU: 0 PID: 49 Comm: hwrng Not tainted 6.0.0 #1 Link: https://lore.kernel.org/all/Y0QJLauamRnCDUef@sirena.org.uk/ Signed-off-by: Jason A. Donenfeld Acked-by: Florian Fainelli Signed-off-by: Herbert Xu --- drivers/char/hw_random/bcm2835-rng.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c index e7dd457e9b22..e98fcac578d6 100644 --- a/drivers/char/hw_random/bcm2835-rng.c +++ b/drivers/char/hw_random/bcm2835-rng.c @@ -71,7 +71,7 @@ static int bcm2835_rng_read(struct hwrng *rng, void *buf, size_t max, while ((rng_readl(priv, RNG_STATUS) >> 24) == 0) { if (!wait) return 0; - cpu_relax(); + hwrng_msleep(rng, 1000); } num_words = rng_readl(priv, RNG_STATUS) >> 24; -- cgit From 4efb365a3f04d0bee7833f168b0b00a15edefeac Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 11 Oct 2022 15:08:32 +0200 Subject: MAINTAINERS: update btrfs website links and files We have the new documentation hosted on Read The Docs and content is migrated there from the wiki. Also update http to https and add the tracepoint definition header. Signed-off-by: David Sterba --- MAINTAINERS | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index f5ca4aefd184..5ec615e817be 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4428,13 +4428,15 @@ M: Josef Bacik M: David Sterba L: linux-btrfs@vger.kernel.org S: Maintained -W: http://btrfs.wiki.kernel.org/ -Q: http://patchwork.kernel.org/project/linux-btrfs/list/ +W: https://btrfs.readthedocs.io +W: https://btrfs.wiki.kernel.org/ +Q: https://patchwork.kernel.org/project/linux-btrfs/list/ C: irc://irc.libera.chat/btrfs T: git git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git F: Documentation/filesystems/btrfs.rst F: fs/btrfs/ F: include/linux/btrfs* +F: include/trace/events/btrfs.h F: include/uapi/linux/btrfs* BTTV VIDEO4LINUX DRIVER -- cgit From f21cb52036373a108acde5853931facfea727a7b Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 10 Oct 2022 22:28:08 -0700 Subject: perf stat: Support old kernels for bperf cgroup counting The recent change in the cgroup will break the backward compatiblity in the BPF program. It should support both old and new kernels using BPF CO-RE technique. Like the task_struct->__state handling in the offcpu analysis, we can check the field name in the cgroup struct. Signed-off-by: Namhyung Kim Acked-by: Andrii Nakryiko Acked-by: Jiri Olsa Cc: Johannes Weiner Cc: Song Liu Cc: Tejun Heo Cc: bpf@vger.kernel.org Cc: cgroups@vger.kernel.org Cc: zefan li Link: http://lore.kernel.org/lkml/20221011052808.282394-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/bperf_cgroup.bpf.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c index 435a87556688..6a438e0102c5 100644 --- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c @@ -43,6 +43,18 @@ struct { __uint(value_size, sizeof(struct bpf_perf_event_value)); } cgrp_readings SEC(".maps"); +/* new kernel cgroup definition */ +struct cgroup___new { + int level; + struct cgroup *ancestors[]; +} __attribute__((preserve_access_index)); + +/* old kernel cgroup definition */ +struct cgroup___old { + int level; + u64 ancestor_ids[]; +} __attribute__((preserve_access_index)); + const volatile __u32 num_events = 1; const volatile __u32 num_cpus = 1; @@ -50,6 +62,21 @@ int enabled = 0; int use_cgroup_v2 = 0; int perf_subsys_id = -1; +static inline __u64 get_cgroup_v1_ancestor_id(struct cgroup *cgrp, int level) +{ + /* recast pointer to capture new type for compiler */ + struct cgroup___new *cgrp_new = (void *)cgrp; + + if (bpf_core_field_exists(cgrp_new->ancestors)) { + return BPF_CORE_READ(cgrp_new, ancestors[level], kn, id); + } else { + /* recast pointer to capture old type for compiler */ + struct cgroup___old *cgrp_old = (void *)cgrp; + + return BPF_CORE_READ(cgrp_old, ancestor_ids[level]); + } +} + static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) { struct task_struct *p = (void *)bpf_get_current_task(); @@ -77,7 +104,7 @@ static inline int get_cgroup_v1_idx(__u32 *cgrps, int size) break; // convert cgroup-id to a map index - cgrp_id = BPF_CORE_READ(cgrp, ancestors[i], kn, id); + cgrp_id = get_cgroup_v1_ancestor_id(cgrp, i); elem = bpf_map_lookup_elem(&cgrp_idx, &cgrp_id); if (!elem) continue; -- cgit From fe180a52014fd4a768345fc7ff11a7ced45765e6 Mon Sep 17 00:00:00 2001 From: James Clark Date: Wed, 5 Oct 2022 15:05:08 +0100 Subject: perf test: Fix test_arm_coresight.sh failures on Juno This test commonly fails on Arm Juno because the instruction interval is large enough to miss generating any samples for Perf in system-wide mode. Fix this by lowering the interval until a comfortable number of Perf instructions are generated. The test is still quick to run because only a small amount of trace is gathered. Before: sudo ./perf test coresight -vvv ... Recording trace with system wide mode Looking at perf.data file for dumping branch samples: Looking at perf.data file for reporting branch samples: Looking at perf.data file for instruction samples: CoreSight system wide testing: FAIL ... After: sudo ./perf test coresight -vvv ... Recording trace with system wide mode Looking at perf.data file for dumping branch samples: Looking at perf.data file for reporting branch samples: Looking at perf.data file for instruction samples: CoreSight system wide testing: PASS ... Reviewed-by: Leo Yan Signed-off-by: James Clark Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: coresight@lists.linaro.org Link: https://lore.kernel.org/r/20221005140508.1537277-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_arm_coresight.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index e4cb4f1806ff..daad786cf48d 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -70,7 +70,7 @@ perf_report_instruction_samples() { # 68.12% touch libc-2.27.so [.] _dl_addr # 5.80% touch libc-2.27.so [.] getenv # 4.35% touch ld-2.27.so [.] _dl_fixup - perf report --itrace=i1000i --stdio -i ${perfdata} 2>&1 | \ + perf report --itrace=i20i --stdio -i ${perfdata} 2>&1 | \ egrep " +[0-9]+\.[0-9]+% +$1" > /dev/null 2>&1 } -- cgit From 11df33c36c4b7a04d2674531f2c6178ad8d61572 Mon Sep 17 00:00:00 2001 From: Richard Acayan Date: Mon, 10 Oct 2022 21:38:28 -0400 Subject: modpost: put modpost options before argument The musl implementation of getopt stops looking for options after the first non-option argument. Put the options before the non-option argument so environments using musl can still build the kernel and modules. Fixes: f73edc8951b2 ("kbuild: unify two modpost invocations") Link: https://git.musl-libc.org/cgit/musl/tree/src/misc/getopt.c?h=dc9285ad1dc19349c407072cc48ba70dab86de45#n44 Signed-off-by: Richard Acayan Signed-off-by: Masahiro Yamada --- scripts/Makefile.modpost | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 7740ce3b29e8..8489a3402eb8 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -119,7 +119,7 @@ quiet_cmd_modpost = MODPOST $@ echo >&2 "WARNING: $(missing-input) is missing."; \ echo >&2 " Modules may not have dependencies or modversions."; \ echo >&2 " You may get many unresolved symbol warnings.";) \ - sed 's/ko$$/o/' $(or $(modorder-if-needed), /dev/null) | $(MODPOST) $(modpost-args) $(vmlinux.o-if-present) -T - + sed 's/ko$$/o/' $(or $(modorder-if-needed), /dev/null) | $(MODPOST) $(modpost-args) -T - $(vmlinux.o-if-present) targets += $(output-symdump) $(output-symdump): $(modorder-if-needed) $(vmlinux.o-if-present) $(moudle.symvers-if-present) $(MODPOST) FORCE -- cgit From 04518e4c2edc78bc90b4651d50c4aad48d09ac23 Mon Sep 17 00:00:00 2001 From: Guru Das Srinagesh Date: Tue, 11 Oct 2022 12:06:00 -0700 Subject: scripts/clang-tools: Convert clang-tidy args to list Convert list of clang-tidy arguments to a list for ease of adding to them and extending them as required. Signed-off-by: Guru Das Srinagesh Suggested-by: Nick Desaulniers Reviewed-by: Nick Desaulniers Signed-off-by: Masahiro Yamada --- scripts/clang-tools/run-clang-tools.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/scripts/clang-tools/run-clang-tools.py b/scripts/clang-tools/run-clang-tools.py index bb78c9bde55c..56f2ec8f0f40 100755 --- a/scripts/clang-tools/run-clang-tools.py +++ b/scripts/clang-tools/run-clang-tools.py @@ -45,13 +45,14 @@ def init(l, a): def run_analysis(entry): # Disable all checks, then re-enable the ones we want - checks = "-checks=-*," + checks = [] + checks.append("-checks=-*") if args.type == "clang-tidy": - checks += "linuxkernel-*" + checks.append("linuxkernel-*") else: - checks += "clang-analyzer-*" - checks += ",-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling" - p = subprocess.run(["clang-tidy", "-p", args.path, checks, entry["file"]], + checks.append("clang-analyzer-*") + checks.append("-clang-analyzer-security.insecureAPI.DeprecatedOrUnsafeBufferHandling") + p = subprocess.run(["clang-tidy", "-p", args.path, ",".join(checks), entry["file"]], stdout=subprocess.PIPE, stderr=subprocess.STDOUT, cwd=entry["directory"]) -- cgit From d5e57375a562f021b455e3f958cc28d54d0ff54b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 14 Oct 2022 10:39:21 -0300 Subject: libperf: Do not include non-UAPI linux/compiler.h header Its just for that __packed define, so use it expanded as __attribute__((packed)), like the other files in /usr/include do. This was problem was preventing building the libperf examples on ALT Linux and Fedora 35, fix it. Reported-by: Vitaly Chikunov Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Dmitry Levin Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lore.kernel.org/lkml/Y0lnpl2Ix7VljVDc@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/include/perf/event.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index e282faf8fd75..ad47d7b31046 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -6,7 +6,6 @@ #include #include #include -#include #include /* pid_t */ #define event_contains(obj, mem) ((obj).header.size > offsetof(typeof(obj), mem)) @@ -207,7 +206,7 @@ struct perf_record_range_cpu_map { __u16 end_cpu; }; -struct __packed perf_record_cpu_map_data { +struct perf_record_cpu_map_data { __u16 type; union { /* Used when type == PERF_CPU_MAP__CPUS. */ @@ -219,7 +218,7 @@ struct __packed perf_record_cpu_map_data { /* Used when type == PERF_CPU_MAP__RANGE_CPUS. */ struct perf_record_range_cpu_map range_cpu_data; }; -}; +} __attribute__((packed)); #pragma GCC diagnostic pop -- cgit From 531778b129937ea3a6923bc67a45d024712a12f7 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 6 Oct 2022 15:22:32 -0700 Subject: perf annotate: Add missing condition flags for arm64 According to the document [1], it can also have 'hs', 'lo', 'vc', 'vs' as a condition code. Let's add them too. [1] https://community.arm.com/arm-community-blogs/b/architectures-and-processors-blog/posts/condition-codes-1-condition-flags-and-codes Reported-by: Kevin Nomura Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mike Leach Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20221006222232.266416-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/annotate/instructions.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c index 037e292ecd8e..4af0c3a0f86e 100644 --- a/tools/perf/arch/arm64/annotate/instructions.c +++ b/tools/perf/arch/arm64/annotate/instructions.c @@ -102,7 +102,7 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused) if (err) goto out_free_arm; /* b, b.cond, br, cbz/cbnz, tbz/tbnz */ - err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl)?n?z?$", + err = regcomp(&arm->jump_insn, "^[ct]?br?\\.?(cc|cs|eq|ge|gt|hi|hs|le|lo|ls|lt|mi|ne|pl|vc|vs)?n?z?$", REG_EXTENDED); if (err) goto out_free_call; -- cgit From 7d60fa2cde0d3d80c55492f86a2a944da7510a67 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 4 Oct 2022 13:02:11 -0700 Subject: perf mem: Fix -C option behavior for perf mem record The -C/--cpu option was maily for report but it also affected record as it ate the option. So users needed to use "--" after perf mem record to pass the info to the perf record properly. Check if this option is set for record, and pass it to the actual perf record. Before) $ sudo perf --debug perf-event-open mem record -C 0 2>&1 | grep -a sys_perf_event_open ... sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 4 sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8 = 5 sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8 = 6 sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8 = 7 sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 8 sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8 = 9 sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8 = 10 sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8 = 11 ... After) $ sudo perf --debug perf-event-open mem record -C 0 2>&1 | grep -a sys_perf_event_open ... sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 4 sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 5 sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 6 sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 7 Reported-by: Ravi Bangoria Reviewed-by: Leo Yan Signed-off-by: Namhyung Kim Tested-by: Leo Yan Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20221004200211.1444521-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-mem.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index f7dd8216de72..923fb8316fda 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -97,6 +97,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) else rec_argc = argc + 9 * perf_pmu__hybrid_pmu_num(); + if (mem->cpu_list) + rec_argc += 2; + rec_argv = calloc(rec_argc + 1, sizeof(char *)); if (!rec_argv) return -1; @@ -159,6 +162,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) if (all_kernel) rec_argv[i++] = "--all-kernel"; + if (mem->cpu_list) { + rec_argv[i++] = "-C"; + rec_argv[i++] = mem->cpu_list; + } + for (j = 0; j < argc; j++, i++) rec_argv[i] = argv[j]; -- cgit From 0cef141e8630c0b08bd1c4309be2ba74480c69a3 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 4 Oct 2022 12:26:34 -0700 Subject: perf list: Fix metricgroups title message $ perf list metricgroups gives List of pre-defined events (to be used in -e): Metric Groups: Backend Bad BadSpec But that's incorrect of course because metric groups or metrics can only be specified with -M. So fix the message to say -e or -M Signed-off-by: Andi Kleen Cc: Jiri Olsa Link: https://lore.kernel.org/r/20221004192634.998984-1-ak@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-list.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 744dd3520584..58e1ec1654ef 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -60,7 +60,7 @@ int cmd_list(int argc, const char **argv) setup_pager(); if (!raw_dump && pager_in_use()) - printf("\nList of pre-defined events (to be used in -e):\n\n"); + printf("\nList of pre-defined events (to be used in -e or -M):\n\n"); if (hybrid_type) { pmu_name = perf_pmu__hybrid_type_to_pmu(hybrid_type); -- cgit From e552b7be12ed62357df84392efa525ecb01910fb Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 4 Oct 2022 14:12:35 -0500 Subject: perf: Skip and warn on unknown format 'configN' attrs If the kernel exposes a new perf_event_attr field in a format attr, perf will return an error stating the specified PMU can't be found. For example, a format attr with 'config3:0-63' causes an error as config3 is unknown to perf. This causes a compatibility issue between a newer kernel with older perf tool. Before this change with a kernel adding 'config3' I get: $ perf record -e arm_spe// -- true event syntax error: 'arm_spe//' \___ Cannot find PMU `arm_spe'. Missing kernel support? Run 'perf list' for a list of valid events Usage: perf record [] [] or: perf record [] -- [] -e, --event event selector. use 'perf list' to list available events After this change, I get: $ perf record -e arm_spe// -- true WARNING: 'arm_spe_0' format 'inv_event_filter' requires 'perf_event_attr::config3' which is not supported by this version of perf! [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.091 MB perf.data ] To support unknown configN formats, rework the YACC implementation to pass any config[0-9]+ format to perf_pmu__new_format() to handle with a warning. Reviewed-by: Namhyung Kim Signed-off-by: Rob Herring Tested-by: Leo Yan Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220914-arm-perf-tool-spe1-2-v2-v4-1-83c098e6212e@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 3 +++ tools/perf/util/pmu.c | 17 +++++++++++++++++ tools/perf/util/pmu.h | 2 ++ tools/perf/util/pmu.l | 2 -- tools/perf/util/pmu.y | 15 ++++----------- 5 files changed, 26 insertions(+), 13 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 437389dacf48..5973f46c2375 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -246,6 +246,9 @@ __add_event(struct list_head *list, int *idx, struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) : cpu_list ? perf_cpu_map__new(cpu_list) : NULL; + if (pmu) + perf_pmu__warn_invalid_formats(pmu); + if (pmu && attr->type == PERF_TYPE_RAW) perf_pmu__warn_invalid_config(pmu, attr->config, name); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 74a2cafb4e8d..03284059175f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1005,6 +1005,23 @@ err: return NULL; } +void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu) +{ + struct perf_pmu_format *format; + + /* fake pmu doesn't have format list */ + if (pmu == &perf_pmu__fake) + return; + + list_for_each_entry(format, &pmu->format, list) + if (format->value >= PERF_PMU_FORMAT_VALUE_CONFIG_END) { + pr_warning("WARNING: '%s' format '%s' requires 'perf_event_attr::config%d'" + "which is not supported by this version of perf!\n", + pmu->name, format->name, format->value); + return; + } +} + static struct perf_pmu *pmu_find(const char *name) { struct perf_pmu *pmu; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index a7b0f9507510..68e15c38ae71 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -17,6 +17,7 @@ enum { PERF_PMU_FORMAT_VALUE_CONFIG, PERF_PMU_FORMAT_VALUE_CONFIG1, PERF_PMU_FORMAT_VALUE_CONFIG2, + PERF_PMU_FORMAT_VALUE_CONFIG_END, }; #define PERF_PMU_FORMAT_BITS 64 @@ -139,6 +140,7 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu); void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, const char *name); +void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); bool perf_pmu__has_hybrid(void); int perf_pmu__match(char *pattern, char *name, char *tok); diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l index a15d9fbd7c0e..58b4926cfaca 100644 --- a/tools/perf/util/pmu.l +++ b/tools/perf/util/pmu.l @@ -27,8 +27,6 @@ num_dec [0-9]+ {num_dec} { return value(10); } config { return PP_CONFIG; } -config1 { return PP_CONFIG1; } -config2 { return PP_CONFIG2; } - { return '-'; } : { return ':'; } , { return ','; } diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index 0dab0ec2eff7..e675d79a0274 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -18,7 +18,7 @@ do { \ %} -%token PP_CONFIG PP_CONFIG1 PP_CONFIG2 +%token PP_CONFIG %token PP_VALUE PP_ERROR %type PP_VALUE %type bit_term @@ -45,18 +45,11 @@ PP_CONFIG ':' bits $3)); } | -PP_CONFIG1 ':' bits +PP_CONFIG PP_VALUE ':' bits { ABORT_ON(perf_pmu__new_format(format, name, - PERF_PMU_FORMAT_VALUE_CONFIG1, - $3)); -} -| -PP_CONFIG2 ':' bits -{ - ABORT_ON(perf_pmu__new_format(format, name, - PERF_PMU_FORMAT_VALUE_CONFIG2, - $3)); + $2, + $4)); } bits: -- cgit From a9e17d3d74d14e5fd10d54f0a07e0fce4e5f80dd Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Fri, 14 Oct 2022 13:40:42 -0300 Subject: cifs: fix static checker warning Remove unnecessary NULL check of oparam->cifs_sb when parsing symlink error response as it's already set by all smb2_open_file() callers and deferenced earlier. This fixes below report: fs/cifs/smb2file.c:126 smb2_open_file() warn: variable dereferenced before check 'oparms->cifs_sb' (see line 112) Link: https://lore.kernel.org/r/Y0kt42j2tdpYakRu@kili Reported-by: Dan Carpenter Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/smb2file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 4992b43616a7..ffbd9a99fc12 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -123,7 +123,7 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 if (unlikely(!err_iov.iov_base || err_buftype == CIFS_NO_BUFFER)) rc = -ENOMEM; - else if (hdr->Status == STATUS_STOPPED_ON_SYMLINK && oparms->cifs_sb) { + else if (hdr->Status == STATUS_STOPPED_ON_SYMLINK) { rc = smb2_parse_symlink_response(oparms->cifs_sb, &err_iov, &data->symlink_target); if (!rc) { -- cgit From 34314cd615af5036e582fad14f2bb13e4383bfe1 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 13 Oct 2022 23:19:15 +0100 Subject: parisc: Fix spelling mistake "mis-match" -> "mismatch" in eisa driver There are several spelling mistakes in kernel error messages. Fix them. Signed-off-by: Colin Ian King Signed-off-by: Helge Deller --- drivers/parisc/eisa_enumerator.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/parisc/eisa_enumerator.c b/drivers/parisc/eisa_enumerator.c index f54a6f450391..f0cb31198a8f 100644 --- a/drivers/parisc/eisa_enumerator.c +++ b/drivers/parisc/eisa_enumerator.c @@ -393,7 +393,7 @@ static int parse_slot_config(int slot, } if (p0 + function_len < pos) { - printk(KERN_ERR "eisa_enumerator: function %d length mis-match " + printk(KERN_ERR "eisa_enumerator: function %d length mismatch " "got %d, expected %d\n", num_func, pos-p0, function_len); res=-1; @@ -407,13 +407,13 @@ static int parse_slot_config(int slot, } if (pos != es->config_data_length) { - printk(KERN_ERR "eisa_enumerator: config data length mis-match got %d, expected %d\n", + printk(KERN_ERR "eisa_enumerator: config data length mismatch got %d, expected %d\n", pos, es->config_data_length); res=-1; } if (num_func != es->num_functions) { - printk(KERN_ERR "eisa_enumerator: number of functions mis-match got %d, expected %d\n", + printk(KERN_ERR "eisa_enumerator: number of functions mismatch got %d, expected %d\n", num_func, es->num_functions); res=-2; } @@ -451,7 +451,7 @@ static int init_slot(int slot, struct eeprom_eisa_slot_info *es) } if (es->eisa_slot_id != id) { print_eisa_id(id_string, id); - printk(KERN_ERR "EISA slot %d id mis-match: got %s", + printk(KERN_ERR "EISA slot %d id mismatch: got %s", slot, id_string); print_eisa_id(id_string, es->eisa_slot_id); -- cgit From 2130b87b2273389cafe6765bf09ef564cda01407 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 14 Oct 2022 08:21:03 -0700 Subject: drm/amd/display: Fix build breakage with CONFIG_DEBUG_FS=n MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After commit 8799c0be89eb ("drm/amd/display: Fix vblank refcount in vrr transition"), a build with CONFIG_DEBUG_FS=n is broken due to a misplaced brace, along the lines of: In file included from drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_trace.h:39, from drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:41: drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c: At top level: ./include/drm/drm_atomic.h:864:9: error: expected identifier or ‘(’ before ‘for’ 864 | for ((__i) = 0; \ | ^~~ drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:8317:9: note: in expansion of macro ‘for_each_new_crtc_in_state’ 8317 | for_each_new_crtc_in_state(state, crtc, new_crtc_state, j) | ^~~~~~~~~~~~~~~~~~~~~~~~~~ Move the brace within the #ifdef so that the file can be built with or without CONFIG_DEBUG_FS. Fixes: 8799c0be89eb ("drm/amd/display: Fix vblank refcount in vrr transition") Signed-off-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f6a9e8fdd87d..c053cb79cd06 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8310,8 +8310,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) crtc, dm_new_crtc_state, cur_crc_src)) DRM_DEBUG_DRIVER("Failed to configure crc source"); } -#endif } +#endif } for_each_new_crtc_in_state(state, crtc, new_crtc_state, j) -- cgit From 5632e2beaf9d5dda694c0572684dea783d8a9492 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 14 Oct 2022 13:45:45 -0500 Subject: Revert "PCI: Distribute available resources for root buses, too" This reverts commit e96e27fc6f7971380283768e9a734af16b1716ee. Jonathan reported that this commit broke this topology, where all the space available on bus 02 was assigned to the 02:00.0 bridge window, leaving none for the e1000 device at 02:00.1: pci 0000:00:04.0: bridge window [mem 0x10200000-0x103fffff] to [bus 02-04] pci 0000:02:00.0: bridge window [mem 0x10200000-0x103fffff] to [bus 03-04] pci 0000:02:00.1: BAR 0: failed to assign [mem size 0x00020000] e1000 0000:02:00.1: can't ioremap BAR 0: [??? 0x00000000 flags 0x0] Link: https://lore.kernel.org/r/20221014124553.0000696f@huawei.com Reported-by: Jonathan Cameron Signed-off-by: Bjorn Helgaas --- drivers/pci/setup-bus.c | 62 +------------------------------------------------ 1 file changed, 1 insertion(+), 61 deletions(-) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index dc6a30ee6edf..b4096598dbcb 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -1768,10 +1768,7 @@ static void adjust_bridge_window(struct pci_dev *bridge, struct resource *res, } res->end = res->start + new_size - 1; - - /* If the resource is part of the add_list remove it now */ - if (add_list) - remove_from_list(add_list, res); + remove_from_list(add_list, res); } static void pci_bus_distribute_available_resources(struct pci_bus *bus, @@ -1926,8 +1923,6 @@ static void pci_bridge_distribute_available_resources(struct pci_dev *bridge, if (!bridge->is_hotplug_bridge) return; - pci_dbg(bridge, "distributing available resources\n"); - /* Take the initial extra resources from the hotplug port */ available_io = bridge->resource[PCI_BRIDGE_IO_WINDOW]; available_mmio = bridge->resource[PCI_BRIDGE_MEM_WINDOW]; @@ -1939,59 +1934,6 @@ static void pci_bridge_distribute_available_resources(struct pci_dev *bridge, available_mmio_pref); } -static bool pci_bridge_resources_not_assigned(struct pci_dev *dev) -{ - const struct resource *r; - - /* - * Check the child device's resources and if they are not yet - * assigned it means we are configuring them (not the boot - * firmware) so we should be able to extend the upstream - * bridge's (that's the hotplug downstream PCIe port) resources - * in the same way we do with the normal hotplug case. - */ - r = &dev->resource[PCI_BRIDGE_IO_WINDOW]; - if (!r->flags || !(r->flags & IORESOURCE_STARTALIGN)) - return false; - r = &dev->resource[PCI_BRIDGE_MEM_WINDOW]; - if (!r->flags || !(r->flags & IORESOURCE_STARTALIGN)) - return false; - r = &dev->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; - if (!r->flags || !(r->flags & IORESOURCE_STARTALIGN)) - return false; - - return true; -} - -static void pci_root_bus_distribute_available_resources(struct pci_bus *bus, - struct list_head *add_list) -{ - struct pci_dev *dev, *bridge = bus->self; - - for_each_pci_bridge(dev, bus) { - struct pci_bus *b; - - b = dev->subordinate; - if (!b) - continue; - - /* - * Need to check "bridge" here too because it is NULL - * in case of root bus. - */ - if (bridge && pci_bridge_resources_not_assigned(dev)) { - pci_bridge_distribute_available_resources(bridge, add_list); - /* - * There is only PCIe upstream port on the bus - * so we don't need to go futher. - */ - return; - } - - pci_root_bus_distribute_available_resources(b, add_list); - } -} - /* * First try will not touch PCI bridge res. * Second and later try will clear small leaf bridge res. @@ -2031,8 +1973,6 @@ again: */ __pci_bus_size_bridges(bus, add_list); - pci_root_bus_distribute_available_resources(bus, add_list); - /* Depth last, allocate resources and update the hardware. */ __pci_bus_assign_resources(bus, add_list, &fail_head); if (add_list) -- cgit From c67a85bee78db74c6889a5ca645c3763ad23d863 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 14 Oct 2022 09:53:02 -0700 Subject: kbuild: add -fno-discard-value-names to cmd_cc_ll_c When debugging LLVM IR, it can be handy for clang to not discard value names used for local variables and parameters. Compare the generated IR. -fdiscard-value-names: define i32 @core_sys_select(i32 %0, ptr %1, ptr %2, ptr %3, ptr %4) { %6 = alloca i64 %7 = alloca %struct.poll_wqueues %8 = alloca [64 x i32] -fno-discard-value-names: define i32 @core_sys_select(i32 %n, ptr %inp, ptr %outp, ptr %exp, ptr %end_time) { %expire.i = alloca i64 %table.i = alloca %struct.poll_wqueues %stack_fds = alloca [64 x i32] The rule for generating human readable LLVM IR (.ll) is only useful as a debugging feature: $ make LLVM=1 fs/select.ll As Fangrui notes: A LLVM_ENABLE_ASSERTIONS=off build of Clang defaults to -fdiscard-value-names. A LLVM_ENABLE_ASSERTIONS=on build of Clang defaults to -fno-discard-value-names. Explicitly enable -fno-discard-value-names so that the IR always contains value names regardless of whether assertions were enabled or not. Assertions generally are not enabled in releases of clang packaged by distributions. Link: https://github.com/ClangBuiltLinux/linux/issues/1467 Reviewed-by: Nathan Chancellor Reviewed-by: Fangrui Song Signed-off-by: Nick Desaulniers Signed-off-by: Masahiro Yamada --- scripts/Makefile.build | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 22adbf89cb31..41f3602fc8de 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -140,7 +140,7 @@ $(obj)/%.symtypes : $(src)/%.c FORCE # LLVM assembly # Generate .ll files from .c quiet_cmd_cc_ll_c = CC $(quiet_modtag) $@ - cmd_cc_ll_c = $(CC) $(c_flags) -emit-llvm -S -o $@ $< + cmd_cc_ll_c = $(CC) $(c_flags) -emit-llvm -S -fno-discard-value-names -o $@ $< $(obj)/%.ll: $(src)/%.c FORCE $(call if_changed_dep,cc_ll_c) -- cgit From b05ea3314390e9cb3c27cf2928d48e38fef97050 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Tue, 11 Oct 2022 15:55:48 +0200 Subject: clk: mediatek: clk-mux: Add .determine_rate() callback Since commit 262ca38f4b6e ("clk: Stop forwarding clk_rate_requests to the parent"), the clk_rate_request is .. as the title says, not forwarded anymore to the parent: this produces an issue with the MediaTek clock MUX driver during GPU DVFS on MT8195, but not on MT8192 or others. This is because, differently from others, like MT8192 where all of the clocks in the MFG parents tree are of mtk_mux type, but in the parent tree of MT8195's MFG clock, we have one mtk_mux clock and one (clk framework generic) mux clock, like so: names: mfg_bg3d -> mfg_ck_fast_ref -> top_mfg_core_tmp (or) mfgpll types: mtk_gate -> mux -> mtk_mux (or) mtk_pll To solve this issue and also keep the GPU DVFS clocks code working as expected, wire up a .determine_rate() callback for the mtk_mux ops; for that, the standard clk_mux_determine_rate_flags() was used as it was possible to. This commit was successfully tested on MT6795 Xperia M5, MT8173 Elm, MT8192 Spherion and MT8195 Tomato; no regressions were seen. For the sake of some more documentation about this issue here's the trace of it: [ 12.211587] ------------[ cut here ]------------ [ 12.211589] WARNING: CPU: 6 PID: 78 at drivers/clk/clk.c:1462 clk_core_init_rate_req+0x84/0x90 [ 12.211593] Modules linked in: stp crct10dif_ce mtk_adsp_common llc rfkill snd_sof_xtensa_dsp panfrost(+) sbs_battery cros_ec_lid_angle cros_ec_sensors snd_sof_of cros_ec_sensors_core hid_multitouch cros_usbpd_logger snd_sof gpu_sched snd_sof_utils fuse ipv6 [ 12.211614] CPU: 6 PID: 78 Comm: kworker/u16:2 Tainted: G W 6.0.0-next-20221011+ #58 [ 12.211616] Hardware name: Acer Tomato (rev2) board (DT) [ 12.211617] Workqueue: devfreq_wq devfreq_monitor [ 12.211620] pstate: 40400009 (nZcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 12.211622] pc : clk_core_init_rate_req+0x84/0x90 [ 12.211625] lr : clk_core_forward_rate_req+0xa4/0xe4 [ 12.211627] sp : ffff80000893b8e0 [ 12.211628] x29: ffff80000893b8e0 x28: ffffdddf92f9b000 x27: ffff46a2c0e8bc05 [ 12.211632] x26: ffff46a2c1041200 x25: 0000000000000000 x24: 00000000173eed80 [ 12.211636] x23: ffff80000893b9c0 x22: ffff80000893b940 x21: 0000000000000000 [ 12.211641] x20: ffff46a2c1039f00 x19: ffff46a2c1039f00 x18: 0000000000000000 [ 12.211645] x17: 0000000000000038 x16: 000000000000d904 x15: 0000000000000003 [ 12.211649] x14: ffffdddf9357ce48 x13: ffffdddf935e71c8 x12: 000000000004803c [ 12.211653] x11: 00000000a867d7ad x10: 00000000a867d7ad x9 : ffffdddf90c28df4 [ 12.211657] x8 : ffffdddf9357a980 x7 : 0000000000000000 x6 : 0000000000000004 [ 12.211661] x5 : ffffffffffffffc8 x4 : 00000000173eed80 x3 : ffff80000893b940 [ 12.211665] x2 : 00000000173eed80 x1 : ffff80000893b940 x0 : 0000000000000000 [ 12.211669] Call trace: [ 12.211670] clk_core_init_rate_req+0x84/0x90 [ 12.211673] clk_core_round_rate_nolock+0xe8/0x10c [ 12.211675] clk_mux_determine_rate_flags+0x174/0x1f0 [ 12.211677] clk_mux_determine_rate+0x1c/0x30 [ 12.211680] clk_core_determine_round_nolock+0x74/0x130 [ 12.211682] clk_core_round_rate_nolock+0x58/0x10c [ 12.211684] clk_core_round_rate_nolock+0xf4/0x10c [ 12.211686] clk_core_set_rate_nolock+0x194/0x2ac [ 12.211688] clk_set_rate+0x40/0x94 [ 12.211691] _opp_config_clk_single+0x38/0xa0 [ 12.211693] _set_opp+0x1b0/0x500 [ 12.211695] dev_pm_opp_set_rate+0x120/0x290 [ 12.211697] panfrost_devfreq_target+0x3c/0x50 [panfrost] [ 12.211705] devfreq_set_target+0x8c/0x2d0 [ 12.211707] devfreq_update_target+0xcc/0xf4 [ 12.211708] devfreq_monitor+0x40/0x1d0 [ 12.211710] process_one_work+0x294/0x664 [ 12.211712] worker_thread+0x7c/0x45c [ 12.211713] kthread+0x104/0x110 [ 12.211716] ret_from_fork+0x10/0x20 [ 12.211718] irq event stamp: 7102 [ 12.211719] hardirqs last enabled at (7101): [] finish_task_switch.isra.0+0xec/0x2f0 [ 12.211723] hardirqs last disabled at (7102): [] el1_dbg+0x24/0x90 [ 12.211726] softirqs last enabled at (6716): [] __do_softirq+0x414/0x588 [ 12.211728] softirqs last disabled at (6507): [] ____do_softirq+0x18/0x24 [ 12.211730] ---[ end trace 0000000000000000 ]--- Fixes: 262ca38f4b6e ("clk: Stop forwarding clk_rate_requests to the parent") Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20221011135548.318323-1-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mux.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/clk/mediatek/clk-mux.c b/drivers/clk/mediatek/clk-mux.c index cd5f9fd8cb98..5d217f7377ee 100644 --- a/drivers/clk/mediatek/clk-mux.c +++ b/drivers/clk/mediatek/clk-mux.c @@ -128,9 +128,18 @@ static int mtk_clk_mux_set_parent_setclr_lock(struct clk_hw *hw, u8 index) return 0; } +static int mtk_clk_mux_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + struct mtk_clk_mux *mux = to_mtk_clk_mux(hw); + + return clk_mux_determine_rate_flags(hw, req, mux->data->flags); +} + const struct clk_ops mtk_mux_clr_set_upd_ops = { .get_parent = mtk_clk_mux_get_parent, .set_parent = mtk_clk_mux_set_parent_setclr_lock, + .determine_rate = mtk_clk_mux_determine_rate, }; EXPORT_SYMBOL_GPL(mtk_mux_clr_set_upd_ops); @@ -140,6 +149,7 @@ const struct clk_ops mtk_mux_gate_clr_set_upd_ops = { .is_enabled = mtk_clk_mux_is_enabled, .get_parent = mtk_clk_mux_get_parent, .set_parent = mtk_clk_mux_set_parent_setclr_lock, + .determine_rate = mtk_clk_mux_determine_rate, }; EXPORT_SYMBOL_GPL(mtk_mux_gate_clr_set_upd_ops); -- cgit From 8c7bc6ca3740959edc6abe5d8214e5c84aa8a853 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 13 Oct 2022 16:07:45 +0200 Subject: clk: qcom: gcc-msm8660: Drop hardcoded fixed board clocks These two clocks are now registered in the device tree as fixed clocks, causing a regression in the driver as the clock already exists with e.g. the name "pxo_board" as the MSM8660 GCC driver probes. Fix this by just not hard-coding this anymore and everything works like a charm. Cc: Dmitry Baryshkov Fixes: baecbda52933 ("ARM: dts: qcom: msm8660: fix node names for fixed clocks") Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20221013140745.7801-1-linus.walleij@linaro.org Signed-off-by: Stephen Boyd --- drivers/clk/qcom/gcc-msm8660.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/drivers/clk/qcom/gcc-msm8660.c b/drivers/clk/qcom/gcc-msm8660.c index 657e1154bb9b..a9eb6a9ac445 100644 --- a/drivers/clk/qcom/gcc-msm8660.c +++ b/drivers/clk/qcom/gcc-msm8660.c @@ -2767,17 +2767,6 @@ MODULE_DEVICE_TABLE(of, gcc_msm8660_match_table); static int gcc_msm8660_probe(struct platform_device *pdev) { - int ret; - struct device *dev = &pdev->dev; - - ret = qcom_cc_register_board_clk(dev, "cxo_board", "cxo", 19200000); - if (ret) - return ret; - - ret = qcom_cc_register_board_clk(dev, "pxo_board", "pxo", 27000000); - if (ret) - return ret; - return qcom_cc_probe(pdev, &gcc_msm8660_desc); } -- cgit From 57d849636a04a12713dd3a10a97cb9658ec7edf6 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 12 Oct 2022 11:06:35 +0800 Subject: clk: at91: fix the build with binutils 2.27 There is an issue when build with older versions of binutils 2.27.0, arch/arm/mach-at91/pm_suspend.S: Assembler messages: arch/arm/mach-at91/pm_suspend.S:1086: Error: garbage following instruction -- `ldr tmp1,=0x00020010UL' Use UL() macro to fix the issue in assembly file. Fixes: 4fd36e458392 ("ARM: at91: pm: add plla disable/enable support for sam9x60") Signed-off-by: Kefeng Wang Link: https://lore.kernel.org/r/20221012030635.13140-1-wangkefeng.wang@huawei.com Signed-off-by: Stephen Boyd --- include/linux/clk/at91_pmc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 3484309b59bf..7af499bdbecb 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -12,6 +12,8 @@ #ifndef AT91_PMC_H #define AT91_PMC_H +#include + #define AT91_PMC_V1 (1) /* PMC version 1 */ #define AT91_PMC_V2 (2) /* PMC version 2 [SAM9X60] */ @@ -45,8 +47,8 @@ #define AT91_PMC_PCSR 0x18 /* Peripheral Clock Status Register */ #define AT91_PMC_PLL_ACR 0x18 /* PLL Analog Control Register [for SAM9X60] */ -#define AT91_PMC_PLL_ACR_DEFAULT_UPLL 0x12020010UL /* Default PLL ACR value for UPLL */ -#define AT91_PMC_PLL_ACR_DEFAULT_PLLA 0x00020010UL /* Default PLL ACR value for PLLA */ +#define AT91_PMC_PLL_ACR_DEFAULT_UPLL UL(0x12020010) /* Default PLL ACR value for UPLL */ +#define AT91_PMC_PLL_ACR_DEFAULT_PLLA UL(0x00020010) /* Default PLL ACR value for PLLA */ #define AT91_PMC_PLL_ACR_UTMIVR (1 << 12) /* UPLL Voltage regulator Control */ #define AT91_PMC_PLL_ACR_UTMIBG (1 << 13) /* UPLL Bandgap Control */ -- cgit From c461c677a8cb19026fd06741a23ff32d0759342b Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Mon, 10 Oct 2022 11:00:46 +0100 Subject: clk: tegra: Fix Tegra PWM parent clock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 8c193f4714df ("pwm: tegra: Optimize period calculation") updated the period calculation in the Tegra PWM driver and now returns an error if the period requested is less than minimum period supported. This is breaking PWM support on various Tegra platforms. For example, on the Tegra210 Jetson Nano platform this is breaking the PWM fan support and probing the PWM fan driver now fails ... pwm-fan pwm-fan: Failed to configure PWM: -22 pwm-fan: probe of pwm-fan failed with error -22 The problem is that the default parent clock for the PWM on Tegra210 is a 32kHz clock and is unable to support the requested PWM period. Fix PWM support on Tegra20, Tegra30, Tegra114, Tegra124 and Tegra210 by updating the parent clock for the PWM to be the PLL_P. Fixes: 8c193f4714df ("pwm: tegra: Optimize period calculation") Signed-off-by: Jon Hunter Tested-by: Robert Eckelmann # TF101 T20 Tested-by: Antoni Aloy Torrens # TF101 T20 Tested-by: Svyatoslav Ryhel # TF201 T30 Tested-by: Andreas Westman Dorcsak # TF700T T3 Link: https://lore.kernel.org/r/20221010100046.6477-1-jonathanh@nvidia.com Acked-by: Uwe Kleine-König Signed-off-by: Stephen Boyd --- drivers/clk/tegra/clk-tegra114.c | 1 + drivers/clk/tegra/clk-tegra124.c | 1 + drivers/clk/tegra/clk-tegra20.c | 1 + drivers/clk/tegra/clk-tegra210.c | 1 + drivers/clk/tegra/clk-tegra30.c | 1 + 5 files changed, 5 insertions(+) diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c index f7405a58877e..73303458e886 100644 --- a/drivers/clk/tegra/clk-tegra114.c +++ b/drivers/clk/tegra/clk-tegra114.c @@ -1166,6 +1166,7 @@ static struct tegra_clk_init_table init_table[] __initdata = { { TEGRA114_CLK_I2S3_SYNC, TEGRA114_CLK_CLK_MAX, 24000000, 0 }, { TEGRA114_CLK_I2S4_SYNC, TEGRA114_CLK_CLK_MAX, 24000000, 0 }, { TEGRA114_CLK_VIMCLK_SYNC, TEGRA114_CLK_CLK_MAX, 24000000, 0 }, + { TEGRA114_CLK_PWM, TEGRA114_CLK_PLL_P, 408000000, 0 }, /* must be the last entry */ { TEGRA114_CLK_CLK_MAX, TEGRA114_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c index a9d4efcef2d4..6c46592d794e 100644 --- a/drivers/clk/tegra/clk-tegra124.c +++ b/drivers/clk/tegra/clk-tegra124.c @@ -1330,6 +1330,7 @@ static struct tegra_clk_init_table common_init_table[] __initdata = { { TEGRA124_CLK_I2S3_SYNC, TEGRA124_CLK_CLK_MAX, 24576000, 0 }, { TEGRA124_CLK_I2S4_SYNC, TEGRA124_CLK_CLK_MAX, 24576000, 0 }, { TEGRA124_CLK_VIMCLK_SYNC, TEGRA124_CLK_CLK_MAX, 24576000, 0 }, + { TEGRA124_CLK_PWM, TEGRA124_CLK_PLL_P, 408000000, 0 }, /* must be the last entry */ { TEGRA124_CLK_CLK_MAX, TEGRA124_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index 8a4514f6d503..422d78247553 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -1044,6 +1044,7 @@ static struct tegra_clk_init_table init_table[] = { { TEGRA20_CLK_GR2D, TEGRA20_CLK_PLL_C, 300000000, 0 }, { TEGRA20_CLK_GR3D, TEGRA20_CLK_PLL_C, 300000000, 0 }, { TEGRA20_CLK_VDE, TEGRA20_CLK_PLL_C, 300000000, 0 }, + { TEGRA20_CLK_PWM, TEGRA20_CLK_PLL_P, 48000000, 0 }, /* must be the last entry */ { TEGRA20_CLK_CLK_MAX, TEGRA20_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index 499f999e91e1..a3488aaac3f7 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -3597,6 +3597,7 @@ static struct tegra_clk_init_table init_table[] __initdata = { { TEGRA210_CLK_VIMCLK_SYNC, TEGRA210_CLK_CLK_MAX, 24576000, 0 }, { TEGRA210_CLK_HDA, TEGRA210_CLK_PLL_P, 51000000, 0 }, { TEGRA210_CLK_HDA2CODEC_2X, TEGRA210_CLK_PLL_P, 48000000, 0 }, + { TEGRA210_CLK_PWM, TEGRA210_CLK_PLL_P, 48000000, 0 }, /* This MUST be the last entry. */ { TEGRA210_CLK_CLK_MAX, TEGRA210_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c index 168c07d5a5f2..60f1534711f1 100644 --- a/drivers/clk/tegra/clk-tegra30.c +++ b/drivers/clk/tegra/clk-tegra30.c @@ -1237,6 +1237,7 @@ static struct tegra_clk_init_table init_table[] = { { TEGRA30_CLK_VIMCLK_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 }, { TEGRA30_CLK_HDA, TEGRA30_CLK_PLL_P, 102000000, 0 }, { TEGRA30_CLK_HDA2CODEC_2X, TEGRA30_CLK_PLL_P, 48000000, 0 }, + { TEGRA30_CLK_PWM, TEGRA30_CLK_PLL_P, 48000000, 0 }, /* must be the last entry */ { TEGRA30_CLK_CLK_MAX, TEGRA30_CLK_CLK_MAX, 0, 0 }, }; -- cgit From a8aed7b35becfd21f22a77c7014029ea837b018f Mon Sep 17 00:00:00 2001 From: Jonathan Cooper Date: Thu, 13 Oct 2022 10:55:53 +0100 Subject: sfc: Change VF mac via PF as first preference if available. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Changing a VF's mac address through the VF (rather than via the PF) fails with EPERM because the latter part of efx_ef10_set_mac_address attempts to change the vport mac address list as the VF. Even with this fixed it still fails with EBUSY because the vadaptor is still assigned on the VF - the vadaptor reassignment must be within a section where the VF has torn down its state. A major reason this has broken is because we have two functions that ostensibly do the same thing - have a PF and VF cooperate to change a VF mac address. Rather than do this, if we are changing the mac of a VF that has a link to the PF in the same VM then simply call sriov_set_vf_mac instead, which is a proven working function that does that. If there is no PF available, or that fails non-fatally, then attempt to change the VF's mac address as we would a PF, without updating the PF's data. Test case: Create a VF: echo 1 > /sys/class/net//device/sriov_numvfs Set the mac address of the VF directly: ip link set addr 00:11:22:33:44:55 Set the MAC address of the VF via the PF: ip link set vf 0 mac 00:11:22:33:44:66 Without this patch the last command will fail with ENOENT. Signed-off-by: Jonathan Cooper Reported-by: Íñigo Huguet Fixes: 910c8789a777 ("set the MAC address using MC_CMD_VADAPTOR_SET_MAC") Acked-by: Edward Cree Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/ef10.c | 58 +++++++++++++++++------------------------ 1 file changed, 24 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index d1e1aa19a68e..7022fb2005a2 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3277,6 +3277,30 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx) bool was_enabled = efx->port_enabled; int rc; +#ifdef CONFIG_SFC_SRIOV + /* If this function is a VF and we have access to the parent PF, + * then use the PF control path to attempt to change the VF MAC address. + */ + if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) { + struct efx_nic *efx_pf = pci_get_drvdata(efx->pci_dev->physfn); + struct efx_ef10_nic_data *nic_data = efx->nic_data; + u8 mac[ETH_ALEN]; + + /* net_dev->dev_addr can be zeroed by efx_net_stop in + * efx_ef10_sriov_set_vf_mac, so pass in a copy. + */ + ether_addr_copy(mac, efx->net_dev->dev_addr); + + rc = efx_ef10_sriov_set_vf_mac(efx_pf, nic_data->vf_index, mac); + if (!rc) + return 0; + + netif_dbg(efx, drv, efx->net_dev, + "Updating VF mac via PF failed (%d), setting directly\n", + rc); + } +#endif + efx_device_detach_sync(efx); efx_net_stop(efx->net_dev); @@ -3297,40 +3321,6 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx) efx_net_open(efx->net_dev); efx_device_attach_if_not_resetting(efx); -#ifdef CONFIG_SFC_SRIOV - if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) { - struct efx_ef10_nic_data *nic_data = efx->nic_data; - struct pci_dev *pci_dev_pf = efx->pci_dev->physfn; - - if (rc == -EPERM) { - struct efx_nic *efx_pf; - - /* Switch to PF and change MAC address on vport */ - efx_pf = pci_get_drvdata(pci_dev_pf); - - rc = efx_ef10_sriov_set_vf_mac(efx_pf, - nic_data->vf_index, - efx->net_dev->dev_addr); - } else if (!rc) { - struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf); - struct efx_ef10_nic_data *nic_data = efx_pf->nic_data; - unsigned int i; - - /* MAC address successfully changed by VF (with MAC - * spoofing) so update the parent PF if possible. - */ - for (i = 0; i < efx_pf->vf_count; ++i) { - struct ef10_vf *vf = nic_data->vf + i; - - if (vf->efx == efx) { - ether_addr_copy(vf->mac, - efx->net_dev->dev_addr); - return 0; - } - } - } - } else -#endif if (rc == -EPERM) { netif_err(efx, drv, efx->net_dev, "Cannot change MAC address; use sfboot to enable" -- cgit From d8bde3bf7f82dac5fc68a62c2816793a12cafa2a Mon Sep 17 00:00:00 2001 From: Xiaobo Liu Date: Fri, 14 Oct 2022 10:05:40 +0800 Subject: net/atm: fix proc_mpc_write incorrect return value Then the input contains '\0' or '\n', proc_mpc_write has read them, so the return value needs +1. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Xiaobo Liu Signed-off-by: David S. Miller --- net/atm/mpoa_proc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 829db9eba0cb..aaf64b953915 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -219,11 +219,12 @@ static ssize_t proc_mpc_write(struct file *file, const char __user *buff, if (!page) return -ENOMEM; - for (p = page, len = 0; len < nbytes; p++, len++) { + for (p = page, len = 0; len < nbytes; p++) { if (get_user(*p, buff++)) { free_page((unsigned long)page); return -EFAULT; } + len += 1; if (*p == '\0' || *p == '\n') break; } -- cgit From 017e42540639a46fdf7c7f5ee647e0b7806c9013 Mon Sep 17 00:00:00 2001 From: Cezar Bulinaru Date: Thu, 13 Oct 2022 22:45:03 -0400 Subject: net: hv_netvsc: Fix a warning triggered by memcpy in rndis_filter memcpy: detected field-spanning write (size 168) of single field "(void *)&request->response_msg + (sizeof(struct rndis_message) - sizeof(union rndis_message_container)) + sizeof(*req_id)" at drivers/net/hyperv/rndis_filter.c:338 (size 40) RSP: 0018:ffffc90000144de0 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff8881766b4000 RCX: 0000000000000000 RDX: 0000000000000102 RSI: 0000000000009ffb RDI: 00000000ffffffff RBP: ffffc90000144e38 R08: 0000000000000000 R09: 00000000ffffdfff R10: ffffc90000144c48 R11: ffffffff82f56ac8 R12: ffff8881766b403c R13: 00000000000000a8 R14: ffff888100b75000 R15: ffff888179301d00 FS: 0000000000000000(0000) GS:ffff8884d6280000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055f8b024c418 CR3: 0000000176548001 CR4: 00000000003706e0 Call Trace: ? _raw_spin_unlock_irqrestore+0x27/0x50 netvsc_poll+0x556/0x940 [hv_netvsc] __napi_poll+0x2e/0x170 net_rx_action+0x299/0x2f0 __do_softirq+0xed/0x2ef __irq_exit_rcu+0x9f/0x110 irq_exit_rcu+0xe/0x20 sysvec_hyperv_callback+0xb0/0xd0 asm_sysvec_hyperv_callback+0x1b/0x20 RIP: 0010:native_safe_halt+0xb/0x10 Fixes: A warning triggered when the response message len exceeds the size of rndis_message. Inside the rndis_request structure these fields are however followed by a RNDIS_EXT_LEN padding so it is safe to use unsafe_memcpy. Reviewed-by: Michael Kelley Signed-off-by: Cezar Bulinaru Signed-off-by: David S. Miller --- drivers/net/hyperv/rndis_filter.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 11f767a20444..eea777ec2541 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "hyperv_net.h" #include "netvsc_trace.h" @@ -335,9 +336,10 @@ static void rndis_filter_receive_response(struct net_device *ndev, if (resp->msg_len <= sizeof(struct rndis_message) + RNDIS_EXT_LEN) { memcpy(&request->response_msg, resp, RNDIS_HEADER_SIZE + sizeof(*req_id)); - memcpy((void *)&request->response_msg + RNDIS_HEADER_SIZE + sizeof(*req_id), + unsafe_memcpy((void *)&request->response_msg + RNDIS_HEADER_SIZE + sizeof(*req_id), data + RNDIS_HEADER_SIZE + sizeof(*req_id), - resp->msg_len - RNDIS_HEADER_SIZE - sizeof(*req_id)); + resp->msg_len - RNDIS_HEADER_SIZE - sizeof(*req_id), + "request->response_msg is followed by a padding of RNDIS_EXT_LEN inside rndis_request"); if (request->request_msg.ndis_msg_type == RNDIS_MSG_QUERY && request->request_msg.msg. query_req.oid == RNDIS_OID_GEN_MEDIA_CONNECT_STATUS) -- cgit From 0c9efbd5c50c64ead434960a404c9c9a097b0403 Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Fri, 14 Oct 2022 12:17:35 +0530 Subject: net: phy: dp83867: Extend RX strap quirk for SGMII mode When RX strap in HW is not set to MODE 3 or 4, bit 7 and 8 in CF4 register should be set. The former is already handled in dp83867_config_init; add the latter in SGMII specific initialization. Fixes: 2a10154abcb7 ("net: phy: dp83867: Add TI dp83867 phy") Signed-off-by: Harini Katakam Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/dp83867.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 6939563d3b7c..417527f8bbf5 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -853,6 +853,14 @@ static int dp83867_config_init(struct phy_device *phydev) else val &= ~DP83867_SGMII_TYPE; phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_SGMIICTL, val); + + /* This is a SW workaround for link instability if RX_CTRL is + * not strapped to mode 3 or 4 in HW. This is required for SGMII + * in addition to clearing bit 7, handled above. + */ + if (dp83867->rxctrl_strap_quirk) + phy_set_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, + BIT(8)); } val = phy_read(phydev, DP83867_CFG3); -- cgit From bdee15e8c58b450ad736a2b62ef8c7a12548b704 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 14 Oct 2022 12:34:36 +0300 Subject: net/smc: Fix an error code in smc_lgr_create() If smc_wr_alloc_lgr_mem() fails then return an error code. Don't return success. Fixes: 8799e310fb3f ("net/smc: add v2 support to the work request layer") Signed-off-by: Dan Carpenter Reviewed-by: Wenjia Zhang Signed-off-by: David S. Miller --- net/smc/smc_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index e6ee797640b4..c305d8dd23f8 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -896,7 +896,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) } memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1], SMC_MAX_PNETID_LEN); - if (smc_wr_alloc_lgr_mem(lgr)) + rc = smc_wr_alloc_lgr_mem(lgr); + if (rc) goto free_wq; smc_llc_lgr_init(lgr, smc); -- cgit From 9408f3d321ed2286b9722bceff08ca28b741c026 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 14 Oct 2022 17:33:02 +0300 Subject: sunhme: Uninitialized variable in happy_meal_init() The "burst" string is only initialized for CONFIG_SPARC. It should be set to "64" because that's what is used by PCI. Fixes: 24cddbc3ef11 ("sunhme: Combine continued messages") Signed-off-by: Dan Carpenter Reviewed-by: Sean Anderson Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/sunhme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 91f10f746dff..1c16548415cd 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1328,7 +1328,7 @@ static int happy_meal_init(struct happy_meal *hp) void __iomem *erxregs = hp->erxregs; void __iomem *bregs = hp->bigmacregs; void __iomem *tregs = hp->tcvregs; - const char *bursts; + const char *bursts = "64"; u32 regtmp, rxcfg; /* If auto-negotiation timer is running, kill it. */ -- cgit From 0a6d58a70a39d9a74882af6d00ec6df0737503ff Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 14 Oct 2022 18:08:39 +0300 Subject: net: dsa: uninitialized variable in dsa_slave_netdevice_event() Return zero if both dsa_slave_dev_check() and netdev_uses_dsa() are false. Fixes: acc43b7bf52a ("net: dsa: allow masters to join a LAG") Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- net/dsa/slave.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1a59918d3b30..a9fde48cffd4 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -3145,7 +3145,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, case NETDEV_CHANGELOWERSTATE: { struct netdev_notifier_changelowerstate_info *info = ptr; struct dsa_port *dp; - int err; + int err = 0; if (dsa_slave_dev_check(dev)) { dp = dsa_slave_to_port(dev); -- cgit From fc8695eb11f07d936a4a9dbd15d7797986bc8b89 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 14 Oct 2022 09:07:46 -0700 Subject: Revert "net: fix cpu_max_bits_warn() usage in netif_attrmask_next{,_and}" This reverts commit 854701ba4c39afae2362ba19a580c461cb183e4f. We have more violations around, which leads to: WARNING: CPU: 2 PID: 1 at include/linux/cpumask.h:110 __netif_set_xps_queue+0x14e/0x770 Let's back this out and retry with a larger clean up in -next. Fixes: 854701ba4c39 ("net: fix cpu_max_bits_warn() usage in netif_attrmask_next{,_and}") Link: https://lore.kernel.org/all/20221014030459.3272206-2-guoren@kernel.org/ Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a36edb0ec199..eddf8ee270e7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3663,8 +3663,9 @@ static inline bool netif_attr_test_online(unsigned long j, static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) { - /* n is a prior cpu */ - cpu_max_bits_warn(n + 1, nr_bits); + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); if (srcp) return find_next_bit(srcp, nr_bits, n + 1); @@ -3685,8 +3686,9 @@ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, unsigned int nr_bits) { - /* n is a prior cpu */ - cpu_max_bits_warn(n + 1, nr_bits); + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); if (src1p && src2p) return find_next_and_bit(src1p, src2p, nr_bits, n + 1); -- cgit From 96de900ae78e7dbedc937fd91bafe2934579c65a Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Fri, 14 Oct 2022 09:47:28 -0500 Subject: net: phylink: add mac_managed_pm in phylink_config structure The recent commit 'commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")' requires the MAC driver explicitly tell the phy driver who is managing the PM, otherwise you will see warning during resume stage. Add a boolean property in the phylink_config structure so that the MAC driver can use it to tell the PHY driver if it wants to manage the PM. Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state") Signed-off-by: Shenwei Wang Acked-by: Florian Fainelli Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 3 +++ include/linux/phylink.h | 2 ++ 2 files changed, 5 insertions(+) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 75464df191ef..6547b6cc6cbe 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1661,6 +1661,9 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, if (phy_interrupt_is_valid(phy)) phy_request_interrupt(phy); + if (pl->config->mac_managed_pm) + phy->mac_managed_pm = true; + return 0; } diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 664dd409feb9..3f01ac8017e0 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -122,6 +122,7 @@ enum phylink_op_type { * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. + * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. @@ -134,6 +135,7 @@ struct phylink_config { enum phylink_op_type type; bool legacy_pre_march2020; bool poll_fixed_state; + bool mac_managed_pm; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); -- cgit From f151c147b3afcf92dedff53f5f0e965414e4fd2c Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Fri, 14 Oct 2022 09:47:29 -0500 Subject: net: stmmac: Enable mac_managed_pm phylink config Enable the mac_managed_pm configuration in the phylink_config structure to avoid the kernel warning during system resume. Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state") Signed-off-by: Shenwei Wang Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 65c96773c6d2..8273e6a175c8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1214,6 +1214,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) if (priv->plat->tx_queues_to_use > 1) priv->phylink_config.mac_capabilities &= ~(MAC_10HD | MAC_100HD | MAC_1000HD); + priv->phylink_config.mac_managed_pm = true; phylink = phylink_create(&priv->phylink_config, fwnode, mode, &stmmac_phylink_mac_ops); -- cgit From e4080492877d3125ffd0c6dd3e3c997fbe0ebe6d Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 14 Oct 2022 20:08:59 +0300 Subject: perf test: test_intel_pt.sh: Fix return checking again count_result() does not always reset ret=0 which means the value can spill into the next test result. Fix by explicitly setting it to zero between tests. Committer testing: # perf test "Miscellaneous Intel PT testing" 110: Miscellaneous Intel PT testing : Ok # Tested as well with: # perf test -v "Miscellaneous Intel PT testing" Fixes: fd9b45e39cfaf885 ("perf test: test_intel_pt.sh: Fix return checking") Tested-by: Arnaldo Carvalho de Melo Signed-off-by: Adrian Hunter Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20221014170905.64069-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_intel_pt.sh | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index efaad9566c34..4609a24c9340 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -265,13 +265,12 @@ count_result() return fi err_cnt=$((err_cnt + 1)) - ret=0 } ret=0 -test_system_wide_side_band || ret=$? ; count_result $ret -test_per_thread "" "" || ret=$? ; count_result $ret -test_per_thread "k" "(incl. kernel) " || ret=$? ; count_result $ret +test_system_wide_side_band || ret=$? ; count_result $ret ; ret=0 +test_per_thread "" "" || ret=$? ; count_result $ret ; ret=0 +test_per_thread "k" "(incl. kernel) " || ret=$? ; count_result $ret ; ret=0 cleanup -- cgit From 5021d82bca4f5335b29de71f0533b93c6c15007e Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 14 Oct 2022 20:09:00 +0300 Subject: perf test: test_intel_pt.sh: Tidy some perf record options When not decoding, the options "-B -N --no-bpf-event" speed up perf record. Make a common function for them. Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20221014170905.64069-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_intel_pt.sh | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 4609a24c9340..334836f92bdc 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -42,6 +42,14 @@ trap_cleanup() trap trap_cleanup EXIT TERM INT +# perf record for testing without decoding +perf_record_no_decode() +{ + # Options to speed up recording: no post-processing, no build-id cache update, + # and no BPF events. + perf record -B -N --no-bpf-event "$@" +} + have_workload=false cat << _end_of_file_ | /usr/bin/cc -o "${workload}" -xc - -pthread && have_workload=true #include @@ -76,7 +84,7 @@ _end_of_file_ can_cpu_wide() { echo "Checking for CPU-wide recording on CPU $1" - if ! perf record -o "${tmpfile}" -B -N --no-bpf-event -e dummy:u -C "$1" true >/dev/null 2>&1 ; then + if ! perf_record_no_decode -o "${tmpfile}" -e dummy:u -C "$1" true >/dev/null 2>&1 ; then echo "No so skipping" return 2 fi @@ -93,7 +101,7 @@ test_system_wide_side_band() can_cpu_wide 1 || return $? # Record on CPU 0 a task running on CPU 1 - perf record -B -N --no-bpf-event -o "${perfdatafile}" -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname + perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u -C 0 -- taskset --cpu-list 1 uname # Should get MMAP events from CPU 1 because they can be needed to decode mmap_cnt=$(perf script -i "${perfdatafile}" --no-itrace --show-mmap-events -C 1 2>/dev/null | grep -c MMAP) @@ -109,7 +117,7 @@ test_system_wide_side_band() can_kernel() { - perf record -o "${tmpfile}" -B -N --no-bpf-event -e dummy:k true >/dev/null 2>&1 || return 2 + perf_record_no_decode -o "${tmpfile}" -e dummy:k true >/dev/null 2>&1 || return 2 return 0 } @@ -235,7 +243,7 @@ test_per_thread() wait_for_threads ${w1} 2 wait_for_threads ${w2} 2 - perf record -B -N --no-bpf-event -o "${perfdatafile}" -e intel_pt//u"${k}" -vvv --per-thread -p "${w1},${w2}" 2>"${errfile}" >"${outfile}" & + perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u"${k}" -vvv --per-thread -p "${w1},${w2}" 2>"${errfile}" >"${outfile}" & ppid=$! echo "perf PID is $ppid" wait_for_perf_to_start ${ppid} "${errfile}" || return 1 -- cgit From 9637bf8ff0f050cfb9fe84f5734af633e7902796 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 14 Oct 2022 20:09:01 +0300 Subject: perf test: test_intel_pt.sh: Print a message when skipping kernel tracing Messages display with the perf test -v option. Add a message to show when skipping a test because the user cannot do kernel tracing. Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20221014170905.64069-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_intel_pt.sh | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 334836f92bdc..9c746ff1c4d2 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -117,7 +117,14 @@ test_system_wide_side_band() can_kernel() { - perf_record_no_decode -o "${tmpfile}" -e dummy:k true >/dev/null 2>&1 || return 2 + if [ -z "${can_kernel_trace}" ] ; then + can_kernel_trace=0 + perf_record_no_decode -o "${tmpfile}" -e dummy:k true >/dev/null 2>&1 && can_kernel_trace=1 + fi + if [ ${can_kernel_trace} -eq 0 ] ; then + echo "SKIP: no kernel tracing" + return 2 + fi return 0 } -- cgit From 40053a4b7ebd227e923eb996f5e3e328a647db93 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 14 Oct 2022 20:09:02 +0300 Subject: perf test: test_intel_pt.sh: Tidy some alignment Tidy alignment of test function lines to make them more readable. Signed-off-by: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20221014170905.64069-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_intel_pt.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 9c746ff1c4d2..79dde57b561d 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -283,9 +283,9 @@ count_result() } ret=0 -test_system_wide_side_band || ret=$? ; count_result $ret ; ret=0 -test_per_thread "" "" || ret=$? ; count_result $ret ; ret=0 -test_per_thread "k" "(incl. kernel) " || ret=$? ; count_result $ret ; ret=0 +test_system_wide_side_band || ret=$? ; count_result $ret ; ret=0 +test_per_thread "" "" || ret=$? ; count_result $ret ; ret=0 +test_per_thread "k" "(incl. kernel) " || ret=$? ; count_result $ret ; ret=0 cleanup -- cgit From 973db24079fc6b292e896b3b9c057a0a6c0d8e93 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 14 Oct 2022 20:09:03 +0300 Subject: perf test: test_intel_pt.sh: Add jitdump test Add a test for decoding self-modifying code using a jitdump file. The test creates a workload that uses self-modifying code and generates its own jitdump file. The result is processed with perf inject --jit and checked for decoding errors. Note the test will fail without patch "perf inject: Fix GEN_ELF_TEXT_OFFSET for jit" applied. Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20221014170905.64069-6-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_intel_pt.sh | 162 ++++++++++++++++++++++++++++++++ 1 file changed, 162 insertions(+) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 79dde57b561d..e0bf75981b9c 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -22,6 +22,7 @@ outfile="${temp_dir}/test-out.txt" errfile="${temp_dir}/test-err.txt" workload="${temp_dir}/workload" awkscript="${temp_dir}/awkscript" +jitdump_workload="${temp_dir}/jitdump_workload" cleanup() { @@ -50,6 +51,13 @@ perf_record_no_decode() perf record -B -N --no-bpf-event "$@" } +# perf record for testing should not need BPF events +perf_record_no_bpf() +{ + # Options for no BPF events + perf record --no-bpf-event "$@" +} + have_workload=false cat << _end_of_file_ | /usr/bin/cc -o "${workload}" -xc - -pthread && have_workload=true #include @@ -269,6 +277,159 @@ test_per_thread() return 0 } +test_jitdump() +{ + echo "--- Test tracing self-modifying code that uses jitdump ---" + + script_path=$(realpath "$0") + script_dir=$(dirname "$script_path") + jitdump_incl_dir="${script_dir}/../../util" + jitdump_h="${jitdump_incl_dir}/jitdump.h" + + if [ ! -e "${jitdump_h}" ] ; then + echo "SKIP: Include file jitdump.h not found" + return 2 + fi + + if [ -z "${have_jitdump_workload}" ] ; then + have_jitdump_workload=false + # Create a workload that uses self-modifying code and generates its own jitdump file + cat <<- "_end_of_file_" | /usr/bin/cc -o "${jitdump_workload}" -I "${jitdump_incl_dir}" -xc - -pthread && have_jitdump_workload=true + #define _GNU_SOURCE + #include + #include + #include + #include + #include + #include + #include + + #include "jitdump.h" + + #define CHK_BYTE 0x5a + + static inline uint64_t rdtsc(void) + { + unsigned int low, high; + + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + + return low | ((uint64_t)high) << 32; + } + + static FILE *open_jitdump(void) + { + struct jitheader header = { + .magic = JITHEADER_MAGIC, + .version = JITHEADER_VERSION, + .total_size = sizeof(header), + .pid = getpid(), + .timestamp = rdtsc(), + .flags = JITDUMP_FLAGS_ARCH_TIMESTAMP, + }; + char filename[256]; + FILE *f; + void *m; + + snprintf(filename, sizeof(filename), "jit-%d.dump", getpid()); + f = fopen(filename, "w+"); + if (!f) + goto err; + /* Create an MMAP event for the jitdump file. That is how perf tool finds it. */ + m = mmap(0, 4096, PROT_READ | PROT_EXEC, MAP_PRIVATE, fileno(f), 0); + if (m == MAP_FAILED) + goto err_close; + munmap(m, 4096); + if (fwrite(&header,sizeof(header),1,f) != 1) + goto err_close; + return f; + + err_close: + fclose(f); + err: + return NULL; + } + + static int write_jitdump(FILE *f, void *addr, const uint8_t *dat, size_t sz, uint64_t *idx) + { + struct jr_code_load rec = { + .p.id = JIT_CODE_LOAD, + .p.total_size = sizeof(rec) + sz, + .p.timestamp = rdtsc(), + .pid = getpid(), + .tid = gettid(), + .vma = (unsigned long)addr, + .code_addr = (unsigned long)addr, + .code_size = sz, + .code_index = ++*idx, + }; + + if (fwrite(&rec,sizeof(rec),1,f) != 1 || + fwrite(dat, sz, 1, f) != 1) + return -1; + return 0; + } + + static void close_jitdump(FILE *f) + { + fclose(f); + } + + int main() + { + /* Get a memory page to store executable code */ + void *addr = mmap(0, 4096, PROT_WRITE | PROT_EXEC, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + /* Code to execute: mov CHK_BYTE, %eax ; ret */ + uint8_t dat[] = {0xb8, CHK_BYTE, 0x00, 0x00, 0x00, 0xc3}; + FILE *f = open_jitdump(); + uint64_t idx = 0; + int ret = 1; + + if (!f) + return 1; + /* Copy executable code to executable memory page */ + memcpy(addr, dat, sizeof(dat)); + /* Record it in the jitdump file */ + if (write_jitdump(f, addr, dat, sizeof(dat), &idx)) + goto out_close; + /* Call it */ + ret = ((int (*)(void))addr)() - CHK_BYTE; + out_close: + close_jitdump(f); + return ret; + } + _end_of_file_ + fi + + if ! $have_jitdump_workload ; then + echo "SKIP: No jitdump workload" + return 2 + fi + + # Change to temp_dir so jitdump collateral files go there + cd "${temp_dir}" + perf_record_no_bpf -o "${tmpfile}" -e intel_pt//u "${jitdump_workload}" + perf inject -i "${tmpfile}" -o "${perfdatafile}" --jit + decode_br_cnt=$(perf script -i "${perfdatafile}" --itrace=b | wc -l) + # Note that overflow and lost errors are suppressed for the error count + decode_err_cnt=$(perf script -i "${perfdatafile}" --itrace=e-o-l | grep -ci error) + cd - + # Should be thousands of branches + if [ "${decode_br_cnt}" -lt 1000 ] ; then + echo "Decode failed, only ${decode_br_cnt} branches" + return 1 + fi + # Should be no errors + if [ "${decode_err_cnt}" -ne 0 ] ; then + echo "Decode failed, ${decode_err_cnt} errors" + perf script -i "${perfdatafile}" --itrace=e-o-l + return 1 + fi + + echo OK + return 0 +} + count_result() { if [ "$1" -eq 2 ] ; then @@ -286,6 +447,7 @@ ret=0 test_system_wide_side_band || ret=$? ; count_result $ret ; ret=0 test_per_thread "" "" || ret=$? ; count_result $ret ; ret=0 test_per_thread "k" "(incl. kernel) " || ret=$? ; count_result $ret ; ret=0 +test_jitdump || ret=$? ; count_result $ret ; ret=0 cleanup -- cgit From 89b15d00527b7825ff19130ed83478e80e3fae99 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 14 Oct 2022 20:09:04 +0300 Subject: perf inject: Fix GEN_ELF_TEXT_OFFSET for jit When a program header was added, it moved the text section but GEN_ELF_TEXT_OFFSET was not updated. Fix by adding the program header size and aligning. Fixes: babd04386b1df8c3 ("perf jit: Include program header in ELF files") Signed-off-by: Adrian Hunter Tested-by: Arnaldo Carvalho de Melo Cc: Ian Rogers Cc: Jiri Olsa Cc: Lieven Hey Cc: Namhyung Kim Link: https://lore.kernel.org/r/20221014170905.64069-7-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/genelf.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index b5c909546e3f..6af062d1c452 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -2,6 +2,8 @@ #ifndef __GENELF_H__ #define __GENELF_H__ +#include + /* genelf.c */ int jit_write_elf(int fd, uint64_t code_addr, const char *sym, const void *code, int csize, void *debug, int nr_debug_entries, @@ -76,6 +78,6 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #endif /* The .text section is directly after the ELF header */ -#define GEN_ELF_TEXT_OFFSET sizeof(Elf_Ehdr) +#define GEN_ELF_TEXT_OFFSET round_up(sizeof(Elf_Ehdr) + sizeof(Elf_Phdr), 16) #endif -- cgit From f77811a0f62577d2d51e57c5740a4fbd53dd3331 Mon Sep 17 00:00:00 2001 From: Ammy Yi Date: Fri, 14 Oct 2022 20:09:05 +0300 Subject: perf test: test_intel_pt.sh: Add 9 tests Add tests: Test with MTC and TSC disabled Test with branches disabled Test with/without CYC Test recording with sample mode Test with kernel trace Test virtual LBR Test power events Test with TNT packets disabled Test with event_trace These tests mostly check that perf record works with the corresponding Intel PT config terms, sometimes also checking that certain packets do or do not appear in the resulting trace as appropriate. The "Test virtual LBR" is slightly trickier, using a Python script to check that branch stacks are actually synthesized. Signed-off-by: Ammy Yi Tested-by: Arnaldo Carvalho de Melo Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20221014170905.64069-8-adrian.hunter@intel.com Signed-off-by: Adrian Hunter Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_intel_pt.sh | 195 +++++++++++++++++++++++++++++++- 1 file changed, 194 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index e0bf75981b9c..4c0aabbe33bd 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -23,6 +23,7 @@ errfile="${temp_dir}/test-err.txt" workload="${temp_dir}/workload" awkscript="${temp_dir}/awkscript" jitdump_workload="${temp_dir}/jitdump_workload" +maxbrstack="${temp_dir}/maxbrstack.py" cleanup() { @@ -422,7 +423,7 @@ test_jitdump() # Should be no errors if [ "${decode_err_cnt}" -ne 0 ] ; then echo "Decode failed, ${decode_err_cnt} errors" - perf script -i "${perfdatafile}" --itrace=e-o-l + perf script -i "${perfdatafile}" --itrace=e-o-l --show-mmap-events | cat return 1 fi @@ -430,6 +431,189 @@ test_jitdump() return 0 } +test_packet_filter() +{ + echo "--- Test with MTC and TSC disabled ---" + # Disable MTC and TSC + perf_record_no_decode -o "${perfdatafile}" -e intel_pt/mtc=0,tsc=0/u uname + # Should not get MTC packet + mtc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "MTC 0x") + if [ "${mtc_cnt}" -ne 0 ] ; then + echo "Failed to filter with mtc=0" + return 1 + fi + # Should not get TSC package + tsc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TSC 0x") + if [ "${tsc_cnt}" -ne 0 ] ; then + echo "Failed to filter with tsc=0" + return 1 + fi + echo OK + return 0 +} + +test_disable_branch() +{ + echo "--- Test with branches disabled ---" + # Disable branch + perf_record_no_decode -o "${perfdatafile}" -e intel_pt/branch=0/u uname + # Should not get branch related packets + tnt_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TNT 0x") + tip_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "TIP 0x") + fup_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "FUP 0x") + if [ "${tnt_cnt}" -ne 0 ] || [ "${tip_cnt}" -ne 0 ] || [ "${fup_cnt}" -ne 0 ] ; then + echo "Failed to disable branches" + return 1 + fi + echo OK + return 0 +} + +test_time_cyc() +{ + echo "--- Test with/without CYC ---" + # Check if CYC is supported + cyc=$(cat /sys/bus/event_source/devices/intel_pt/caps/psb_cyc) + if [ "${cyc}" != "1" ] ; then + echo "SKIP: CYC is not supported" + return 2 + fi + # Enable CYC + perf_record_no_decode -o "${perfdatafile}" -e intel_pt/cyc/u uname + # should get CYC packets + cyc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "CYC 0x") + if [ "${cyc_cnt}" = "0" ] ; then + echo "Failed to get CYC packet" + return 1 + fi + # Without CYC + perf_record_no_decode -o "${perfdatafile}" -e intel_pt//u uname + # Should not get CYC packets + cyc_cnt=$(perf script -i "${perfdatafile}" -D 2>/dev/null | grep -c "CYC 0x") + if [ "${cyc_cnt}" -gt 0 ] ; then + echo "Still get CYC packet without cyc" + return 1 + fi + echo OK + return 0 +} + +test_sample() +{ + echo "--- Test recording with sample mode ---" + # Check if recording with sample mode is working + if ! perf_record_no_decode -o "${perfdatafile}" --aux-sample=8192 -e '{intel_pt//u,branch-misses:u}' uname ; then + echo "perf record failed with --aux-sample" + return 1 + fi + echo OK + return 0 +} + +test_kernel_trace() +{ + echo "--- Test with kernel trace ---" + # Check if recording with kernel trace is working + can_kernel || return 2 + if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt//k -m1,128 uname ; then + echo "perf record failed with intel_pt//k" + return 1 + fi + echo OK + return 0 +} + +test_virtual_lbr() +{ + echo "--- Test virtual LBR ---" + + # Python script to determine the maximum size of branch stacks + cat << "_end_of_file_" > "${maxbrstack}" +from __future__ import print_function + +bmax = 0 + +def process_event(param_dict): + if "brstack" in param_dict: + brstack = param_dict["brstack"] + n = len(brstack) + global bmax + if n > bmax: + bmax = n + +def trace_end(): + print("max brstack", bmax) +_end_of_file_ + + # Check if virtual lbr is working + perf_record_no_bpf -o "${perfdatafile}" --aux-sample -e '{intel_pt//,cycles}:u' uname + times_val=$(perf script -i "${perfdatafile}" --itrace=L -s "${maxbrstack}" 2>/dev/null | grep "max brstack " | cut -d " " -f 3) + case "${times_val}" in + [0-9]*) ;; + *) times_val=0;; + esac + if [ "${times_val}" -lt 2 ] ; then + echo "Failed with virtual lbr" + return 1 + fi + echo OK + return 0 +} + +test_power_event() +{ + echo "--- Test power events ---" + # Check if power events are supported + power_event=$(cat /sys/bus/event_source/devices/intel_pt/caps/power_event_trace) + if [ "${power_event}" != "1" ] ; then + echo "SKIP: power_event_trace is not supported" + return 2 + fi + if ! perf_record_no_decode -o "${perfdatafile}" -a -e intel_pt/pwr_evt/u uname ; then + echo "perf record failed with pwr_evt" + return 1 + fi + echo OK + return 0 +} + +test_no_tnt() +{ + echo "--- Test with TNT packets disabled ---" + # Check if TNT disable is supported + notnt=$(cat /sys/bus/event_source/devices/intel_pt/caps/tnt_disable) + if [ "${notnt}" != "1" ] ; then + echo "SKIP: tnt_disable is not supported" + return 2 + fi + perf_record_no_decode -o "${perfdatafile}" -e intel_pt/notnt/u uname + # Should be no TNT packets + tnt_cnt=$(perf script -i "${perfdatafile}" -D | grep -c TNT) + if [ "${tnt_cnt}" -ne 0 ] ; then + echo "TNT packets still there after notnt" + return 1 + fi + echo OK + return 0 +} + +test_event_trace() +{ + echo "--- Test with event_trace ---" + # Check if event_trace is supported + event_trace=$(cat /sys/bus/event_source/devices/intel_pt/caps/event_trace) + if [ "${event_trace}" != 1 ] ; then + echo "SKIP: event_trace is not supported" + return 2 + fi + if ! perf_record_no_decode -o "${perfdatafile}" -e intel_pt/event/u uname ; then + echo "perf record failed with event trace" + return 1 + fi + echo OK + return 0 +} + count_result() { if [ "$1" -eq 2 ] ; then @@ -448,6 +632,15 @@ test_system_wide_side_band || ret=$? ; count_result $ret ; ret=0 test_per_thread "" "" || ret=$? ; count_result $ret ; ret=0 test_per_thread "k" "(incl. kernel) " || ret=$? ; count_result $ret ; ret=0 test_jitdump || ret=$? ; count_result $ret ; ret=0 +test_packet_filter || ret=$? ; count_result $ret ; ret=0 +test_disable_branch || ret=$? ; count_result $ret ; ret=0 +test_time_cyc || ret=$? ; count_result $ret ; ret=0 +test_sample || ret=$? ; count_result $ret ; ret=0 +test_kernel_trace || ret=$? ; count_result $ret ; ret=0 +test_virtual_lbr || ret=$? ; count_result $ret ; ret=0 +test_power_event || ret=$? ; count_result $ret ; ret=0 +test_no_tnt || ret=$? ; count_result $ret ; ret=0 +test_event_trace || ret=$? ; count_result $ret ; ret=0 cleanup -- cgit From e28039667cea2cbea72aeb19665a1c57c6756253 Mon Sep 17 00:00:00 2001 From: James Clark Date: Wed, 12 Oct 2022 10:46:32 +0100 Subject: perf test: Fix attr tests for PERF_FORMAT_LOST Since PERF_FORMAT_LOST was added, the default read format has that bit set, so add it to the tests. Keep the old value as well so that the test still passes on older kernels. This fixes the following failure: expected read_format=0|4, got 20 FAILED './tests/attr/test-record-C0' - match failure Fixes: 85b425f31c8866e0 ("perf record: Set PERF_FORMAT_LOST by default") Signed-off-by: James Clark Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20221012094633.21669-2-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr/base-record | 2 +- tools/perf/tests/attr/system-wide-dummy | 2 +- tools/perf/tests/attr/test-record-group | 4 ++-- tools/perf/tests/attr/test-record-group-sampling | 6 +++--- tools/perf/tests/attr/test-record-group1 | 4 ++-- tools/perf/tests/attr/test-record-group2 | 4 ++-- 6 files changed, 11 insertions(+), 11 deletions(-) diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 8c10955eff93..3ef07a12aa14 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -9,7 +9,7 @@ size=128 config=0 sample_period=* sample_type=263 -read_format=0|4 +read_format=0|4|20 disabled=1 inherit=1 pinned=0 diff --git a/tools/perf/tests/attr/system-wide-dummy b/tools/perf/tests/attr/system-wide-dummy index 86a15dd359d9..8fec06eda5f9 100644 --- a/tools/perf/tests/attr/system-wide-dummy +++ b/tools/perf/tests/attr/system-wide-dummy @@ -11,7 +11,7 @@ size=128 config=9 sample_period=4000 sample_type=455 -read_format=4 +read_format=4|20 # Event will be enabled right away. disabled=0 inherit=1 diff --git a/tools/perf/tests/attr/test-record-group b/tools/perf/tests/attr/test-record-group index 14ee60fd3f41..6c1cff8aae8b 100644 --- a/tools/perf/tests/attr/test-record-group +++ b/tools/perf/tests/attr/test-record-group @@ -7,14 +7,14 @@ ret = 1 fd=1 group_fd=-1 sample_type=327 -read_format=4 +read_format=4|20 [event-2:base-record] fd=2 group_fd=1 config=1 sample_type=327 -read_format=4 +read_format=4|20 mmap=0 comm=0 task=0 diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index 300b9f7e6d69..97e7e64a38f0 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -7,7 +7,7 @@ ret = 1 fd=1 group_fd=-1 sample_type=343 -read_format=12 +read_format=12|28 inherit=0 [event-2:base-record] @@ -21,8 +21,8 @@ config=3 # default | PERF_SAMPLE_READ sample_type=343 -# PERF_FORMAT_ID | PERF_FORMAT_GROUP -read_format=12 +# PERF_FORMAT_ID | PERF_FORMAT_GROUP | PERF_FORMAT_LOST +read_format=12|28 task=0 mmap=0 comm=0 diff --git a/tools/perf/tests/attr/test-record-group1 b/tools/perf/tests/attr/test-record-group1 index 3ffe246e0228..eeb1db392bc9 100644 --- a/tools/perf/tests/attr/test-record-group1 +++ b/tools/perf/tests/attr/test-record-group1 @@ -7,7 +7,7 @@ ret = 1 fd=1 group_fd=-1 sample_type=327 -read_format=4 +read_format=4|20 [event-2:base-record] fd=2 @@ -15,7 +15,7 @@ group_fd=1 type=0 config=1 sample_type=327 -read_format=4 +read_format=4|20 mmap=0 comm=0 task=0 diff --git a/tools/perf/tests/attr/test-record-group2 b/tools/perf/tests/attr/test-record-group2 index 6b9f8d182ce1..cebdaa8e64e4 100644 --- a/tools/perf/tests/attr/test-record-group2 +++ b/tools/perf/tests/attr/test-record-group2 @@ -9,7 +9,7 @@ group_fd=-1 config=0|1 sample_period=1234000 sample_type=87 -read_format=12 +read_format=12|28 inherit=0 freq=0 @@ -19,7 +19,7 @@ group_fd=1 config=0|1 sample_period=6789000 sample_type=87 -read_format=12 +read_format=12|28 disabled=0 inherit=0 mmap=0 -- cgit From 5a3d47071f0ced0431ef82a5fb6bd077ed9493db Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 12 Oct 2022 11:22:58 +0300 Subject: perf intel-pt: Fix segfault in intel_pt_print_info() with uClibc uClibc segfaulted because NULL was passed as the format to fprintf(). That happened because one of the format strings was missing and intel_pt_print_info() didn't check that before calling fprintf(). Add the missing format string, and check format is not NULL before calling fprintf(). Fixes: 11fa7cb86b56d361 ("perf tools: Pass Intel PT information for decoding MTC and CYC") Signed-off-by: Adrian Hunter Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221012082259.22394-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index b34cb3dec1aa..e3548ddef254 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -4046,6 +4046,7 @@ static const char * const intel_pt_info_fmts[] = { [INTEL_PT_SNAPSHOT_MODE] = " Snapshot mode %"PRId64"\n", [INTEL_PT_PER_CPU_MMAPS] = " Per-cpu maps %"PRId64"\n", [INTEL_PT_MTC_BIT] = " MTC bit %#"PRIx64"\n", + [INTEL_PT_MTC_FREQ_BITS] = " MTC freq bits %#"PRIx64"\n", [INTEL_PT_TSC_CTC_N] = " TSC:CTC numerator %"PRIu64"\n", [INTEL_PT_TSC_CTC_D] = " TSC:CTC denominator %"PRIu64"\n", [INTEL_PT_CYC_BIT] = " CYC bit %#"PRIx64"\n", @@ -4060,8 +4061,12 @@ static void intel_pt_print_info(__u64 *arr, int start, int finish) if (!dump_trace) return; - for (i = start; i <= finish; i++) - fprintf(stdout, intel_pt_info_fmts[i], arr[i]); + for (i = start; i <= finish; i++) { + const char *fmt = intel_pt_info_fmts[i]; + + if (fmt) + fprintf(stdout, fmt, arr[i]); + } } static void intel_pt_print_info_str(const char *name, const char *str) -- cgit From 6cef7dab3e2e5cb23a13569c3880c0532326748c Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 12 Oct 2022 11:22:59 +0300 Subject: perf intel-pt: Fix system_wide dummy event for hybrid User space tasks can migrate between CPUs, so when tracing selected CPUs, system-wide sideband is still needed, however evlist->core.has_user_cpus is not set in the hybrid case, so check the target cpu_list instead. Fixes: 7d189cadbeebc778 ("perf intel-pt: Track sideband system-wide when needed") Signed-off-by: Adrian Hunter Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221012082259.22394-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/intel-pt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 793b35f2221a..af102f471e9f 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -866,7 +866,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * User space tasks can migrate between CPUs, so when tracing * selected CPUs, sideband for all CPUs is still needed. */ - need_system_wide_tracking = evlist->core.has_user_cpus && + need_system_wide_tracking = opts->target.cpu_list && !intel_pt_evsel->core.attr.exclude_user; tracking_evsel = evlist__add_aux_dummy(evlist, need_system_wide_tracking); -- cgit From cd400f6f18421b75e64e4aa7bc359d2606033412 Mon Sep 17 00:00:00 2001 From: Athira Rajeev Date: Thu, 6 Oct 2022 21:21:48 +0530 Subject: perf tests stat+csv_output: Include sanity check for topology Testcase stat+csv_output.sh fails in powerpc: 84: perf stat CSV output linter: FAILED! The testcase "stat+csv_output.sh" verifies perf stat CSV output. The test covers aggregation modes like per-socket, per-core, per-die, -A (no_aggr mode) along with few other tests. It counts expected fields for various commands. For example say -A (i.e, AGGR_NONE mode), expects 7 fields in the output having "CPU" as first field. Same way, for per-socket, it expects the first field in result to point to socket id. The testcases compares the result with expected count. The values for socket, die, core and cpu are fetched from topology directory: /sys/devices/system/cpu/cpu*/topology. For example, socket value is fetched from "physical_package_id" file of topology directory. (cpu__get_topology_int() in util/cpumap.c) If a platform fails to fetch the topology information, values will be set to -1. For example, incase of pSeries platform of powerpc, value for "physical_package_id" is restricted and not exposed. So, -1 will be assigned. Perf code has a checks for valid cpu id in "aggr_printout" (stat-display.c), which displays the fields. So, in cases where topology values not exposed, first field of the output displaying will be empty. This cause the testcase to fail, as it counts number of fields in the output. Incase of -A (AGGR_NONE mode,), testcase expects 7 fields in the output, becos of -1 value obtained from topology files for some, only 6 fields are printed. Hence a testcase failure reported due to mismatch in number of fields in the output. Patch here adds a sanity check in the testcase for topology. Check will help to skip the test if -1 value found. Fixes: 7473ee56dbc91c98 ("perf test: Add checking for perf stat CSV output.") Reported-by: Disha Goel Suggested-by: Ian Rogers Suggested-by: James Clark Signed-off-by: Athira Jajeev Cc: Claire Jensen Cc: Jiri Olsa Cc: Kajol Jain Cc: linuxppc-dev@lists.ozlabs.org Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Nageswara R Sastry Link: https://lore.kernel.org/r/20221006155149.67205-1-atrajeev@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat+csv_output.sh | 43 ++++++++++++++++++++++++++++--- 1 file changed, 39 insertions(+), 4 deletions(-) diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index eb5196f58190..b7f050aa6210 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -6,6 +6,8 @@ set -e +skip_test=0 + function commachecker() { local -i cnt=0 @@ -156,14 +158,47 @@ check_per_socket() echo "[Success]" } +# The perf stat options for per-socket, per-core, per-die +# and -A ( no_aggr mode ) uses the info fetched from this +# directory: "/sys/devices/system/cpu/cpu*/topology". For +# example, socket value is fetched from "physical_package_id" +# file in topology directory. +# Reference: cpu__get_topology_int in util/cpumap.c +# If the platform doesn't expose topology information, values +# will be set to -1. For example, incase of pSeries platform +# of powerpc, value for "physical_package_id" is restricted +# and set to -1. Check here validates the socket-id read from +# topology file before proceeding further + +FILE_LOC="/sys/devices/system/cpu/cpu*/topology/" +FILE_NAME="physical_package_id" + +check_for_topology() +{ + if ! ParanoidAndNotRoot 0 + then + socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1` + [ -z $socket_file ] && return 0 + socket_id=`cat $socket_file` + [ $socket_id == -1 ] && skip_test=1 + return 0 + fi +} + +check_for_topology check_no_args check_system_wide -check_system_wide_no_aggr check_interval check_event -check_per_core check_per_thread -check_per_die check_per_node -check_per_socket +if [ $skip_test -ne 1 ] +then + check_system_wide_no_aggr + check_per_core + check_per_die + check_per_socket +else + echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid" +fi exit 0 -- cgit From 58d4802a5eaab55e174f4d31262daada6665aa22 Mon Sep 17 00:00:00 2001 From: Athira Rajeev Date: Thu, 6 Oct 2022 21:21:49 +0530 Subject: perf tests stat+json_output: Include sanity check for topology Testcase stat+json_output.sh fails in powerpc: 86: perf stat JSON output linter : FAILED! The testcase "stat+json_output.sh" verifies perf stat JSON output. The test covers aggregation modes like per-socket, per-core, per-die, -A (no_aggr mode) along with few other tests. It counts expected fields for various commands. For example say -A (i.e, AGGR_NONE mode), expects 7 fields in the output having "CPU" as first field. Same way, for per-socket, it expects the first field in result to point to socket id. The testcases compares the result with expected count. The values for socket, die, core and cpu are fetched from topology directory: /sys/devices/system/cpu/cpu*/topology. For example, socket value is fetched from "physical_package_id" file of topology directory. (cpu__get_topology_int() in util/cpumap.c) If a platform fails to fetch the topology information, values will be set to -1. For example, incase of pSeries platform of powerpc, value for "physical_package_id" is restricted and not exposed. So, -1 will be assigned. Perf code has a checks for valid cpu id in "aggr_printout" (stat-display.c), which displays the fields. So, in cases where topology values not exposed, first field of the output displaying will be empty. This cause the testcase to fail, as it counts number of fields in the output. Incase of -A (AGGR_NONE mode,), testcase expects 7 fields in the output, becos of -1 value obtained from topology files for some, only 6 fields are printed. Hence a testcase failure reported due to mismatch in number of fields in the output. Patch here adds a sanity check in the testcase for topology. Check will help to skip the test if -1 value found. Fixes: 0c343af2a2f82844 ("perf test: JSON format checking") Reported-by: Disha Goel Suggested-by: Ian Rogers Suggested-by: James Clark Signed-off-by: Athira Jajeev Cc: Claire Jensen Cc: Jiri Olsa Cc: Kajol Jain Cc: linuxppc-dev@lists.ozlabs.org Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Nageswara R Sastry Link: https://lore.kernel.org/r/20221006155149.67205-2-atrajeev@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat+json_output.sh | 43 +++++++++++++++++++++++++++--- 1 file changed, 39 insertions(+), 4 deletions(-) diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh index ea8714a36051..2c4212c641ed 100755 --- a/tools/perf/tests/shell/stat+json_output.sh +++ b/tools/perf/tests/shell/stat+json_output.sh @@ -6,6 +6,8 @@ set -e +skip_test=0 + pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py if [ "x$PYTHON" == "x" ] then @@ -134,14 +136,47 @@ check_per_socket() echo "[Success]" } +# The perf stat options for per-socket, per-core, per-die +# and -A ( no_aggr mode ) uses the info fetched from this +# directory: "/sys/devices/system/cpu/cpu*/topology". For +# example, socket value is fetched from "physical_package_id" +# file in topology directory. +# Reference: cpu__get_topology_int in util/cpumap.c +# If the platform doesn't expose topology information, values +# will be set to -1. For example, incase of pSeries platform +# of powerpc, value for "physical_package_id" is restricted +# and set to -1. Check here validates the socket-id read from +# topology file before proceeding further + +FILE_LOC="/sys/devices/system/cpu/cpu*/topology/" +FILE_NAME="physical_package_id" + +check_for_topology() +{ + if ! ParanoidAndNotRoot 0 + then + socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1` + [ -z $socket_file ] && return 0 + socket_id=`cat $socket_file` + [ $socket_id == -1 ] && skip_test=1 + return 0 + fi +} + +check_for_topology check_no_args check_system_wide -check_system_wide_no_aggr check_interval check_event -check_per_core check_per_thread -check_per_die check_per_node -check_per_socket +if [ $skip_test -ne 1 ] +then + check_system_wide_no_aggr + check_per_core + check_per_die + check_per_socket +else + echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid" +fi exit 0 -- cgit From 45a3975f8e4c56829ada20f7a6a29095ca05e375 Mon Sep 17 00:00:00 2001 From: Qi Liu Date: Tue, 27 Sep 2022 16:13:58 +0800 Subject: perf auxtrace arm: Refactor event list iteration in auxtrace_record__init() Add find_pmu_for_event() and use to simplify logic in auxtrace_record_init(). find_pmu_for_event() will be reused in subsequent patches. Reviewed-by: John Garry Reviewed-by: Jonathan Cameron Reviewed-by: Leo Yan Signed-off-by: Qi Liu Signed-off-by: Yicong Yang Cc: Alexander Shishkin Cc: Bjorn Helgaas Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: James Clark Cc: Lorenzo Pieralisi Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Peter Zijlstra Cc: Qi Liu Cc: Shameerali Kolothum Thodi Cc: Shaokun Zhang Cc: Suzuki Poulouse Cc: Will Deacon Cc: Zeng Prime Cc: linux-arm-kernel@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: linuxarm@huawei.com Link: https://lore.kernel.org/r/20220927081400.14364-2-yangyicong@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/auxtrace.c | 53 ++++++++++++++++++++++++------------- 1 file changed, 34 insertions(+), 19 deletions(-) diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 5fc6a2a3dbc5..384c7cfda0fd 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -50,16 +50,32 @@ static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) return arm_spe_pmus; } +static struct perf_pmu *find_pmu_for_event(struct perf_pmu **pmus, + int pmu_nr, struct evsel *evsel) +{ + int i; + + if (!pmus) + return NULL; + + for (i = 0; i < pmu_nr; i++) { + if (evsel->core.attr.type == pmus[i]->type) + return pmus[i]; + } + + return NULL; +} + struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int *err) { - struct perf_pmu *cs_etm_pmu; + struct perf_pmu *cs_etm_pmu = NULL; + struct perf_pmu **arm_spe_pmus = NULL; struct evsel *evsel; - bool found_etm = false; + struct perf_pmu *found_etm = NULL; struct perf_pmu *found_spe = NULL; - struct perf_pmu **arm_spe_pmus = NULL; + int auxtrace_event_cnt = 0; int nr_spes = 0; - int i = 0; if (!evlist) return NULL; @@ -68,24 +84,23 @@ struct auxtrace_record arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err); evlist__for_each_entry(evlist, evsel) { - if (cs_etm_pmu && - evsel->core.attr.type == cs_etm_pmu->type) - found_etm = true; - - if (!nr_spes || found_spe) - continue; - - for (i = 0; i < nr_spes; i++) { - if (evsel->core.attr.type == arm_spe_pmus[i]->type) { - found_spe = arm_spe_pmus[i]; - break; - } - } + if (cs_etm_pmu && !found_etm) + found_etm = find_pmu_for_event(&cs_etm_pmu, 1, evsel); + + if (arm_spe_pmus && !found_spe) + found_spe = find_pmu_for_event(arm_spe_pmus, nr_spes, evsel); } + free(arm_spe_pmus); - if (found_etm && found_spe) { - pr_err("Concurrent ARM Coresight ETM and SPE operation not currently supported\n"); + if (found_etm) + auxtrace_event_cnt++; + + if (found_spe) + auxtrace_event_cnt++; + + if (auxtrace_event_cnt > 1) { + pr_err("Concurrent AUX trace operation not currently supported\n"); *err = -EOPNOTSUPP; return NULL; } -- cgit From 057381a7ece1b2726509ce47cdb9c1a111acfce9 Mon Sep 17 00:00:00 2001 From: Qi Liu Date: Tue, 27 Sep 2022 16:13:59 +0800 Subject: perf auxtrace arm64: Add support for HiSilicon PCIe Tune and Trace device driver HiSilicon PCIe tune and trace device (PTT) could dynamically tune the PCIe link's events, and trace the TLP headers). This patch add support for PTT device in perf tool, so users could use 'perf record' to get TLP headers trace data. Reviewed-by: Leo Yan Signed-off-by: Qi Liu Signed-off-by: Yicong Yang Acked-by: John Garry Cc: Alexander Shishkin Cc: Bjorn Helgaas Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: James Clark Cc: Jonathan Cameron Cc: Lorenzo Pieralisi Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Peter Zijlstra Cc: Qi Liu Cc: Shameerali Kolothum Thodi Cc: Shaokun Zhang Cc: Suzuki Poulouse Cc: Will Deacon Cc: Zeng Prime Cc: linux-arm-kernel@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: linuxarm@huawei.com Link: https://lore.kernel.org/r/20220927081400.14364-3-yangyicong@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/auxtrace.c | 63 ++++++++++++ tools/perf/arch/arm/util/pmu.c | 3 + tools/perf/arch/arm64/util/Build | 2 +- tools/perf/arch/arm64/util/hisi-ptt.c | 188 ++++++++++++++++++++++++++++++++++ tools/perf/util/auxtrace.c | 1 + tools/perf/util/auxtrace.h | 1 + tools/perf/util/hisi-ptt.h | 16 +++ 7 files changed, 273 insertions(+), 1 deletion(-) create mode 100644 tools/perf/arch/arm64/util/hisi-ptt.c create mode 100644 tools/perf/util/hisi-ptt.h diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c index 384c7cfda0fd..deeb163999ce 100644 --- a/tools/perf/arch/arm/util/auxtrace.c +++ b/tools/perf/arch/arm/util/auxtrace.c @@ -4,9 +4,11 @@ * Author: Mathieu Poirier */ +#include #include #include #include +#include #include "../../../util/auxtrace.h" #include "../../../util/debug.h" @@ -14,6 +16,7 @@ #include "../../../util/pmu.h" #include "cs-etm.h" #include "arm-spe.h" +#include "hisi-ptt.h" static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) { @@ -50,6 +53,52 @@ static struct perf_pmu **find_all_arm_spe_pmus(int *nr_spes, int *err) return arm_spe_pmus; } +static struct perf_pmu **find_all_hisi_ptt_pmus(int *nr_ptts, int *err) +{ + const char *sysfs = sysfs__mountpoint(); + struct perf_pmu **hisi_ptt_pmus = NULL; + struct dirent *dent; + char path[PATH_MAX]; + DIR *dir = NULL; + int idx = 0; + + snprintf(path, PATH_MAX, "%s" EVENT_SOURCE_DEVICE_PATH, sysfs); + dir = opendir(path); + if (!dir) { + pr_err("can't read directory '%s'\n", EVENT_SOURCE_DEVICE_PATH); + *err = -EINVAL; + return NULL; + } + + while ((dent = readdir(dir))) { + if (strstr(dent->d_name, HISI_PTT_PMU_NAME)) + (*nr_ptts)++; + } + + if (!(*nr_ptts)) + goto out; + + hisi_ptt_pmus = zalloc(sizeof(struct perf_pmu *) * (*nr_ptts)); + if (!hisi_ptt_pmus) { + pr_err("hisi_ptt alloc failed\n"); + *err = -ENOMEM; + goto out; + } + + rewinddir(dir); + while ((dent = readdir(dir))) { + if (strstr(dent->d_name, HISI_PTT_PMU_NAME) && idx < *nr_ptts) { + hisi_ptt_pmus[idx] = perf_pmu__find(dent->d_name); + if (hisi_ptt_pmus[idx]) + idx++; + } + } + +out: + closedir(dir); + return hisi_ptt_pmus; +} + static struct perf_pmu *find_pmu_for_event(struct perf_pmu **pmus, int pmu_nr, struct evsel *evsel) { @@ -71,17 +120,21 @@ struct auxtrace_record { struct perf_pmu *cs_etm_pmu = NULL; struct perf_pmu **arm_spe_pmus = NULL; + struct perf_pmu **hisi_ptt_pmus = NULL; struct evsel *evsel; struct perf_pmu *found_etm = NULL; struct perf_pmu *found_spe = NULL; + struct perf_pmu *found_ptt = NULL; int auxtrace_event_cnt = 0; int nr_spes = 0; + int nr_ptts = 0; if (!evlist) return NULL; cs_etm_pmu = perf_pmu__find(CORESIGHT_ETM_PMU_NAME); arm_spe_pmus = find_all_arm_spe_pmus(&nr_spes, err); + hisi_ptt_pmus = find_all_hisi_ptt_pmus(&nr_ptts, err); evlist__for_each_entry(evlist, evsel) { if (cs_etm_pmu && !found_etm) @@ -89,9 +142,13 @@ struct auxtrace_record if (arm_spe_pmus && !found_spe) found_spe = find_pmu_for_event(arm_spe_pmus, nr_spes, evsel); + + if (hisi_ptt_pmus && !found_ptt) + found_ptt = find_pmu_for_event(hisi_ptt_pmus, nr_ptts, evsel); } free(arm_spe_pmus); + free(hisi_ptt_pmus); if (found_etm) auxtrace_event_cnt++; @@ -99,6 +156,9 @@ struct auxtrace_record if (found_spe) auxtrace_event_cnt++; + if (found_ptt) + auxtrace_event_cnt++; + if (auxtrace_event_cnt > 1) { pr_err("Concurrent AUX trace operation not currently supported\n"); *err = -EOPNOTSUPP; @@ -111,6 +171,9 @@ struct auxtrace_record #if defined(__aarch64__) if (found_spe) return arm_spe_recording_init(err, found_spe); + + if (found_ptt) + return hisi_ptt_recording_init(err, found_ptt); #endif /* diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index b8b23b9dc598..887c8addc491 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -10,6 +10,7 @@ #include #include "arm-spe.h" +#include "hisi-ptt.h" #include "../../../util/pmu.h" struct perf_event_attr @@ -22,6 +23,8 @@ struct perf_event_attr #if defined(__aarch64__) } else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) { return arm_spe_pmu_default_config(pmu); + } else if (strstarts(pmu->name, HISI_PTT_PMU_NAME)) { + pmu->selectable = true; #endif } diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index 9fcb4e68add9..337aa9bdf905 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -11,4 +11,4 @@ perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \ ../../arm/util/auxtrace.o \ ../../arm/util/cs-etm.o \ - arm-spe.o mem-events.o + arm-spe.o mem-events.o hisi-ptt.o diff --git a/tools/perf/arch/arm64/util/hisi-ptt.c b/tools/perf/arch/arm64/util/hisi-ptt.c new file mode 100644 index 000000000000..ba97c8a562a0 --- /dev/null +++ b/tools/perf/arch/arm64/util/hisi-ptt.c @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#include +#include +#include +#include +#include +#include + +#include // page_size +#include "../../../util/auxtrace.h" +#include "../../../util/cpumap.h" +#include "../../../util/debug.h" +#include "../../../util/event.h" +#include "../../../util/evlist.h" +#include "../../../util/evsel.h" +#include "../../../util/hisi-ptt.h" +#include "../../../util/pmu.h" +#include "../../../util/record.h" +#include "../../../util/session.h" +#include "../../../util/tsc.h" + +#define KiB(x) ((x) * 1024) +#define MiB(x) ((x) * 1024 * 1024) + +struct hisi_ptt_recording { + struct auxtrace_record itr; + struct perf_pmu *hisi_ptt_pmu; + struct evlist *evlist; +}; + +static size_t +hisi_ptt_info_priv_size(struct auxtrace_record *itr __maybe_unused, + struct evlist *evlist __maybe_unused) +{ + return HISI_PTT_AUXTRACE_PRIV_SIZE; +} + +static int hisi_ptt_info_fill(struct auxtrace_record *itr, + struct perf_session *session, + struct perf_record_auxtrace_info *auxtrace_info, + size_t priv_size) +{ + struct hisi_ptt_recording *pttr = + container_of(itr, struct hisi_ptt_recording, itr); + struct perf_pmu *hisi_ptt_pmu = pttr->hisi_ptt_pmu; + + if (priv_size != HISI_PTT_AUXTRACE_PRIV_SIZE) + return -EINVAL; + + if (!session->evlist->core.nr_mmaps) + return -EINVAL; + + auxtrace_info->type = PERF_AUXTRACE_HISI_PTT; + auxtrace_info->priv[0] = hisi_ptt_pmu->type; + + return 0; +} + +static int hisi_ptt_set_auxtrace_mmap_page(struct record_opts *opts) +{ + bool privileged = perf_event_paranoid_check(-1); + + if (!opts->full_auxtrace) + return 0; + + if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { + if (privileged) { + opts->auxtrace_mmap_pages = MiB(16) / page_size; + } else { + opts->auxtrace_mmap_pages = KiB(128) / page_size; + if (opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + } + } + + /* Validate auxtrace_mmap_pages */ + if (opts->auxtrace_mmap_pages) { + size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; + size_t min_sz = KiB(8); + + if (sz < min_sz || !is_power_of_2(sz)) { + pr_err("Invalid mmap size for HISI PTT: must be at least %zuKiB and a power of 2\n", + min_sz / 1024); + return -EINVAL; + } + } + + return 0; +} + +static int hisi_ptt_recording_options(struct auxtrace_record *itr, + struct evlist *evlist, + struct record_opts *opts) +{ + struct hisi_ptt_recording *pttr = + container_of(itr, struct hisi_ptt_recording, itr); + struct perf_pmu *hisi_ptt_pmu = pttr->hisi_ptt_pmu; + struct evsel *evsel, *hisi_ptt_evsel = NULL; + struct evsel *tracking_evsel; + int err; + + pttr->evlist = evlist; + evlist__for_each_entry(evlist, evsel) { + if (evsel->core.attr.type == hisi_ptt_pmu->type) { + if (hisi_ptt_evsel) { + pr_err("There may be only one " HISI_PTT_PMU_NAME "x event\n"); + return -EINVAL; + } + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; + evsel->needs_auxtrace_mmap = true; + hisi_ptt_evsel = evsel; + opts->full_auxtrace = true; + } + } + + err = hisi_ptt_set_auxtrace_mmap_page(opts); + if (err) + return err; + /* + * To obtain the auxtrace buffer file descriptor, the auxtrace event + * must come first. + */ + evlist__to_front(evlist, hisi_ptt_evsel); + evsel__set_sample_bit(hisi_ptt_evsel, TIME); + + /* Add dummy event to keep tracking */ + err = parse_event(evlist, "dummy:u"); + if (err) + return err; + + tracking_evsel = evlist__last(evlist); + evlist__set_tracking_event(evlist, tracking_evsel); + + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; + evsel__set_sample_bit(tracking_evsel, TIME); + + return 0; +} + +static u64 hisi_ptt_reference(struct auxtrace_record *itr __maybe_unused) +{ + return rdtsc(); +} + +static void hisi_ptt_recording_free(struct auxtrace_record *itr) +{ + struct hisi_ptt_recording *pttr = + container_of(itr, struct hisi_ptt_recording, itr); + + free(pttr); +} + +struct auxtrace_record *hisi_ptt_recording_init(int *err, + struct perf_pmu *hisi_ptt_pmu) +{ + struct hisi_ptt_recording *pttr; + + if (!hisi_ptt_pmu) { + *err = -ENODEV; + return NULL; + } + + pttr = zalloc(sizeof(*pttr)); + if (!pttr) { + *err = -ENOMEM; + return NULL; + } + + pttr->hisi_ptt_pmu = hisi_ptt_pmu; + pttr->itr.pmu = hisi_ptt_pmu; + pttr->itr.recording_options = hisi_ptt_recording_options; + pttr->itr.info_priv_size = hisi_ptt_info_priv_size; + pttr->itr.info_fill = hisi_ptt_info_fill; + pttr->itr.free = hisi_ptt_recording_free; + pttr->itr.reference = hisi_ptt_reference; + pttr->itr.read_finish = auxtrace_record__read_finish; + pttr->itr.alignment = 0; + + *err = 0; + return &pttr->itr; +} diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index b59c278fe9ed..0e53b796c5d5 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1320,6 +1320,7 @@ int perf_event__process_auxtrace_info(struct perf_session *session, case PERF_AUXTRACE_S390_CPUMSF: err = s390_cpumsf_process_auxtrace_info(event, session); break; + case PERF_AUXTRACE_HISI_PTT: case PERF_AUXTRACE_UNKNOWN: default: return -EINVAL; diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index cb8e0a01abb6..6a0f9b98f059 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -48,6 +48,7 @@ enum auxtrace_type { PERF_AUXTRACE_CS_ETM, PERF_AUXTRACE_ARM_SPE, PERF_AUXTRACE_S390_CPUMSF, + PERF_AUXTRACE_HISI_PTT, }; enum itrace_period_type { diff --git a/tools/perf/util/hisi-ptt.h b/tools/perf/util/hisi-ptt.h new file mode 100644 index 000000000000..82283c81b4c1 --- /dev/null +++ b/tools/perf/util/hisi-ptt.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#ifndef INCLUDE__PERF_HISI_PTT_H__ +#define INCLUDE__PERF_HISI_PTT_H__ + +#define HISI_PTT_PMU_NAME "hisi_ptt" +#define HISI_PTT_AUXTRACE_PRIV_SIZE sizeof(u64) + +struct auxtrace_record *hisi_ptt_recording_init(int *err, + struct perf_pmu *hisi_ptt_pmu); + +#endif -- cgit From 5e91e57e68090c0e8ab0acecdbb309af8417d415 Mon Sep 17 00:00:00 2001 From: Qi Liu Date: Tue, 27 Sep 2022 16:14:00 +0800 Subject: perf auxtrace arm64: Add support for parsing HiSilicon PCIe Trace packet Add support for using 'perf report --dump-raw-trace' to parse PTT packet. Example usage: Output will contain raw PTT data and its textual representation, such as (8DW format): 0 0 0x5810 [0x30]: PERF_RECORD_AUXTRACE size: 0x400000 offset: 0 ref: 0xa5d50c725 idx: 0 tid: -1 cpu: 0 . . ... HISI PTT data: size 4194304 bytes . 00000000: 00 00 00 00 Prefix . 00000004: 08 20 00 60 Header DW0 . 00000008: ff 02 00 01 Header DW1 . 0000000c: 20 08 00 00 Header DW2 . 00000010: 10 e7 44 ab Header DW3 . 00000014: 2a a8 1e 01 Time . 00000020: 00 00 00 00 Prefix . 00000024: 01 00 00 60 Header DW0 . 00000028: 0f 1e 00 01 Header DW1 . 0000002c: 04 00 00 00 Header DW2 . 00000030: 40 00 81 02 Header DW3 . 00000034: ee 02 00 00 Time .... This patch only add basic parsing support according to the definition of the PTT packet described in Documentation/trace/hisi-ptt.rst. And the fields of each packet can be further decoded following the PCIe Spec's definition of TLP packet. Signed-off-by: Qi Liu Signed-off-by: Yicong Yang Cc: Alexander Shishkin Cc: Bjorn Helgaas Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: James Clark Cc: John Garry Cc: Jonathan Cameron Cc: Leo Yan Cc: Lorenzo Pieralisi Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Peter Zijlstra Cc: Qi Liu Cc: Shameerali Kolothum Thodi Cc: Shaokun Zhang Cc: Suzuki Poulouse Cc: Will Deacon Cc: Zeng Prime Cc: linux-arm-kernel@lists.infradead.org Cc: linux-pci@vger.kernel.org Cc: linuxarm@huawei.com Link: https://lore.kernel.org/r/20220927081400.14364-4-yangyicong@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 2 + tools/perf/util/auxtrace.c | 3 + tools/perf/util/hisi-ptt-decoder/Build | 1 + .../util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c | 164 ++++++++++++++++++ .../util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h | 31 ++++ tools/perf/util/hisi-ptt.c | 192 +++++++++++++++++++++ tools/perf/util/hisi-ptt.h | 3 + 7 files changed, 396 insertions(+) create mode 100644 tools/perf/util/hisi-ptt-decoder/Build create mode 100644 tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c create mode 100644 tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h create mode 100644 tools/perf/util/hisi-ptt.c diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 815d235466d0..e315ecaec323 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -118,6 +118,8 @@ perf-$(CONFIG_AUXTRACE) += intel-pt.o perf-$(CONFIG_AUXTRACE) += intel-bts.o perf-$(CONFIG_AUXTRACE) += arm-spe.o perf-$(CONFIG_AUXTRACE) += arm-spe-decoder/ +perf-$(CONFIG_AUXTRACE) += hisi-ptt.o +perf-$(CONFIG_AUXTRACE) += hisi-ptt-decoder/ perf-$(CONFIG_AUXTRACE) += s390-cpumsf.o ifdef CONFIG_LIBOPENCSD diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 0e53b796c5d5..60d8beb662aa 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -52,6 +52,7 @@ #include "intel-pt.h" #include "intel-bts.h" #include "arm-spe.h" +#include "hisi-ptt.h" #include "s390-cpumsf.h" #include "util/mmap.h" @@ -1321,6 +1322,8 @@ int perf_event__process_auxtrace_info(struct perf_session *session, err = s390_cpumsf_process_auxtrace_info(event, session); break; case PERF_AUXTRACE_HISI_PTT: + err = hisi_ptt_process_auxtrace_info(event, session); + break; case PERF_AUXTRACE_UNKNOWN: default: return -EINVAL; diff --git a/tools/perf/util/hisi-ptt-decoder/Build b/tools/perf/util/hisi-ptt-decoder/Build new file mode 100644 index 000000000000..db3db8b75033 --- /dev/null +++ b/tools/perf/util/hisi-ptt-decoder/Build @@ -0,0 +1 @@ +perf-$(CONFIG_AUXTRACE) += hisi-ptt-pkt-decoder.o diff --git a/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c new file mode 100644 index 000000000000..a17c423a526d --- /dev/null +++ b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "../color.h" +#include "hisi-ptt-pkt-decoder.h" + +/* + * For 8DW format, the bit[31:11] of DW0 is always 0x1fffff, which can be + * used to distinguish the data format. + * 8DW format is like: + * bits [ 31:11 ][ 10:0 ] + * |---------------------------------------|-------------------| + * DW0 [ 0x1fffff ][ Reserved (0x7ff) ] + * DW1 [ Prefix ] + * DW2 [ Header DW0 ] + * DW3 [ Header DW1 ] + * DW4 [ Header DW2 ] + * DW5 [ Header DW3 ] + * DW6 [ Reserved (0x0) ] + * DW7 [ Time ] + * + * 4DW format is like: + * bits [31:30] [ 29:25 ][24][23][22][21][ 20:11 ][ 10:0 ] + * |-----|---------|---|---|---|---|-------------|-------------| + * DW0 [ Fmt ][ Type ][T9][T8][TH][SO][ Length ][ Time ] + * DW1 [ Header DW1 ] + * DW2 [ Header DW2 ] + * DW3 [ Header DW3 ] + */ + +enum hisi_ptt_8dw_pkt_field_type { + HISI_PTT_8DW_CHK_AND_RSV0, + HISI_PTT_8DW_PREFIX, + HISI_PTT_8DW_HEAD0, + HISI_PTT_8DW_HEAD1, + HISI_PTT_8DW_HEAD2, + HISI_PTT_8DW_HEAD3, + HISI_PTT_8DW_RSV1, + HISI_PTT_8DW_TIME, + HISI_PTT_8DW_TYPE_MAX +}; + +enum hisi_ptt_4dw_pkt_field_type { + HISI_PTT_4DW_HEAD1, + HISI_PTT_4DW_HEAD2, + HISI_PTT_4DW_HEAD3, + HISI_PTT_4DW_TYPE_MAX +}; + +static const char * const hisi_ptt_8dw_pkt_field_name[] = { + [HISI_PTT_8DW_PREFIX] = "Prefix", + [HISI_PTT_8DW_HEAD0] = "Header DW0", + [HISI_PTT_8DW_HEAD1] = "Header DW1", + [HISI_PTT_8DW_HEAD2] = "Header DW2", + [HISI_PTT_8DW_HEAD3] = "Header DW3", + [HISI_PTT_8DW_TIME] = "Time" +}; + +static const char * const hisi_ptt_4dw_pkt_field_name[] = { + [HISI_PTT_4DW_HEAD1] = "Header DW1", + [HISI_PTT_4DW_HEAD2] = "Header DW2", + [HISI_PTT_4DW_HEAD3] = "Header DW3", +}; + +union hisi_ptt_4dw { + struct { + uint32_t format : 2; + uint32_t type : 5; + uint32_t t9 : 1; + uint32_t t8 : 1; + uint32_t th : 1; + uint32_t so : 1; + uint32_t len : 10; + uint32_t time : 11; + }; + uint32_t value; +}; + +static void hisi_ptt_print_pkt(const unsigned char *buf, int pos, const char *desc) +{ + const char *color = PERF_COLOR_BLUE; + int i; + + printf("."); + color_fprintf(stdout, color, " %08x: ", pos); + for (i = 0; i < HISI_PTT_FIELD_LENTH; i++) + color_fprintf(stdout, color, "%02x ", buf[pos + i]); + for (i = 0; i < HISI_PTT_MAX_SPACE_LEN; i++) + color_fprintf(stdout, color, " "); + color_fprintf(stdout, color, " %s\n", desc); +} + +static int hisi_ptt_8dw_kpt_desc(const unsigned char *buf, int pos) +{ + int i; + + for (i = 0; i < HISI_PTT_8DW_TYPE_MAX; i++) { + /* Do not show 8DW check field and reserved fields */ + if (i == HISI_PTT_8DW_CHK_AND_RSV0 || i == HISI_PTT_8DW_RSV1) { + pos += HISI_PTT_FIELD_LENTH; + continue; + } + + hisi_ptt_print_pkt(buf, pos, hisi_ptt_8dw_pkt_field_name[i]); + pos += HISI_PTT_FIELD_LENTH; + } + + return hisi_ptt_pkt_size[HISI_PTT_8DW_PKT]; +} + +static void hisi_ptt_4dw_print_dw0(const unsigned char *buf, int pos) +{ + const char *color = PERF_COLOR_BLUE; + union hisi_ptt_4dw dw0; + int i; + + dw0.value = *(uint32_t *)(buf + pos); + printf("."); + color_fprintf(stdout, color, " %08x: ", pos); + for (i = 0; i < HISI_PTT_FIELD_LENTH; i++) + color_fprintf(stdout, color, "%02x ", buf[pos + i]); + for (i = 0; i < HISI_PTT_MAX_SPACE_LEN; i++) + color_fprintf(stdout, color, " "); + + color_fprintf(stdout, color, + " %s %x %s %x %s %x %s %x %s %x %s %x %s %x %s %x\n", + "Format", dw0.format, "Type", dw0.type, "T9", dw0.t9, + "T8", dw0.t8, "TH", dw0.th, "SO", dw0.so, "Length", + dw0.len, "Time", dw0.time); +} + +static int hisi_ptt_4dw_kpt_desc(const unsigned char *buf, int pos) +{ + int i; + + hisi_ptt_4dw_print_dw0(buf, pos); + pos += HISI_PTT_FIELD_LENTH; + + for (i = 0; i < HISI_PTT_4DW_TYPE_MAX; i++) { + hisi_ptt_print_pkt(buf, pos, hisi_ptt_4dw_pkt_field_name[i]); + pos += HISI_PTT_FIELD_LENTH; + } + + return hisi_ptt_pkt_size[HISI_PTT_4DW_PKT]; +} + +int hisi_ptt_pkt_desc(const unsigned char *buf, int pos, enum hisi_ptt_pkt_type type) +{ + if (type == HISI_PTT_8DW_PKT) + return hisi_ptt_8dw_kpt_desc(buf, pos); + + return hisi_ptt_4dw_kpt_desc(buf, pos); +} diff --git a/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h new file mode 100644 index 000000000000..e78f1b5bc836 --- /dev/null +++ b/tools/perf/util/hisi-ptt-decoder/hisi-ptt-pkt-decoder.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#ifndef INCLUDE__HISI_PTT_PKT_DECODER_H__ +#define INCLUDE__HISI_PTT_PKT_DECODER_H__ + +#include +#include + +#define HISI_PTT_8DW_CHECK_MASK GENMASK(31, 11) +#define HISI_PTT_IS_8DW_PKT GENMASK(31, 11) +#define HISI_PTT_MAX_SPACE_LEN 10 +#define HISI_PTT_FIELD_LENTH 4 + +enum hisi_ptt_pkt_type { + HISI_PTT_4DW_PKT, + HISI_PTT_8DW_PKT, + HISI_PTT_PKT_MAX +}; + +static int hisi_ptt_pkt_size[] = { + [HISI_PTT_4DW_PKT] = 16, + [HISI_PTT_8DW_PKT] = 32, +}; + +int hisi_ptt_pkt_desc(const unsigned char *buf, int pos, enum hisi_ptt_pkt_type type); + +#endif diff --git a/tools/perf/util/hisi-ptt.c b/tools/perf/util/hisi-ptt.c new file mode 100644 index 000000000000..45b614bb73bf --- /dev/null +++ b/tools/perf/util/hisi-ptt.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * HiSilicon PCIe Trace and Tuning (PTT) support + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "auxtrace.h" +#include "color.h" +#include "debug.h" +#include "evsel.h" +#include "hisi-ptt.h" +#include "hisi-ptt-decoder/hisi-ptt-pkt-decoder.h" +#include "machine.h" +#include "session.h" +#include "tool.h" +#include + +struct hisi_ptt { + struct auxtrace auxtrace; + u32 auxtrace_type; + struct perf_session *session; + struct machine *machine; + u32 pmu_type; +}; + +struct hisi_ptt_queue { + struct hisi_ptt *ptt; + struct auxtrace_buffer *buffer; +}; + +static enum hisi_ptt_pkt_type hisi_ptt_check_packet_type(unsigned char *buf) +{ + uint32_t head = *(uint32_t *)buf; + + if ((HISI_PTT_8DW_CHECK_MASK & head) == HISI_PTT_IS_8DW_PKT) + return HISI_PTT_8DW_PKT; + + return HISI_PTT_4DW_PKT; +} + +static void hisi_ptt_dump(struct hisi_ptt *ptt __maybe_unused, + unsigned char *buf, size_t len) +{ + const char *color = PERF_COLOR_BLUE; + enum hisi_ptt_pkt_type type; + size_t pos = 0; + int pkt_len; + + type = hisi_ptt_check_packet_type(buf); + len = round_down(len, hisi_ptt_pkt_size[type]); + color_fprintf(stdout, color, ". ... HISI PTT data: size %zu bytes\n", + len); + + while (len > 0) { + pkt_len = hisi_ptt_pkt_desc(buf, pos, type); + if (!pkt_len) + color_fprintf(stdout, color, " Bad packet!\n"); + + pos += pkt_len; + len -= pkt_len; + } +} + +static void hisi_ptt_dump_event(struct hisi_ptt *ptt, unsigned char *buf, + size_t len) +{ + printf(".\n"); + + hisi_ptt_dump(ptt, buf, len); +} + +static int hisi_ptt_process_event(struct perf_session *session __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct perf_tool *tool __maybe_unused) +{ + return 0; +} + +static int hisi_ptt_process_auxtrace_event(struct perf_session *session, + union perf_event *event, + struct perf_tool *tool __maybe_unused) +{ + struct hisi_ptt *ptt = container_of(session->auxtrace, struct hisi_ptt, + auxtrace); + int fd = perf_data__fd(session->data); + int size = event->auxtrace.size; + void *data = malloc(size); + off_t data_offset; + int err; + + if (!data) + return -errno; + + if (perf_data__is_pipe(session->data)) { + data_offset = 0; + } else { + data_offset = lseek(fd, 0, SEEK_CUR); + if (data_offset == -1) + return -errno; + } + + err = readn(fd, data, size); + if (err != (ssize_t)size) { + free(data); + return -errno; + } + + if (dump_trace) + hisi_ptt_dump_event(ptt, data, size); + + return 0; +} + +static int hisi_ptt_flush(struct perf_session *session __maybe_unused, + struct perf_tool *tool __maybe_unused) +{ + return 0; +} + +static void hisi_ptt_free_events(struct perf_session *session __maybe_unused) +{ +} + +static void hisi_ptt_free(struct perf_session *session) +{ + struct hisi_ptt *ptt = container_of(session->auxtrace, struct hisi_ptt, + auxtrace); + + session->auxtrace = NULL; + free(ptt); +} + +static bool hisi_ptt_evsel_is_auxtrace(struct perf_session *session, + struct evsel *evsel) +{ + struct hisi_ptt *ptt = container_of(session->auxtrace, struct hisi_ptt, auxtrace); + + return evsel->core.attr.type == ptt->pmu_type; +} + +static void hisi_ptt_print_info(__u64 type) +{ + if (!dump_trace) + return; + + fprintf(stdout, " PMU Type %" PRId64 "\n", (s64) type); +} + +int hisi_ptt_process_auxtrace_info(union perf_event *event, + struct perf_session *session) +{ + struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; + struct hisi_ptt *ptt; + + if (auxtrace_info->header.size < HISI_PTT_AUXTRACE_PRIV_SIZE + + sizeof(struct perf_record_auxtrace_info)) + return -EINVAL; + + ptt = zalloc(sizeof(*ptt)); + if (!ptt) + return -ENOMEM; + + ptt->session = session; + ptt->machine = &session->machines.host; /* No kvm support */ + ptt->auxtrace_type = auxtrace_info->type; + ptt->pmu_type = auxtrace_info->priv[0]; + + ptt->auxtrace.process_event = hisi_ptt_process_event; + ptt->auxtrace.process_auxtrace_event = hisi_ptt_process_auxtrace_event; + ptt->auxtrace.flush_events = hisi_ptt_flush; + ptt->auxtrace.free_events = hisi_ptt_free_events; + ptt->auxtrace.free = hisi_ptt_free; + ptt->auxtrace.evsel_is_auxtrace = hisi_ptt_evsel_is_auxtrace; + session->auxtrace = &ptt->auxtrace; + + hisi_ptt_print_info(auxtrace_info->priv[0]); + + return 0; +} diff --git a/tools/perf/util/hisi-ptt.h b/tools/perf/util/hisi-ptt.h index 82283c81b4c1..2db9b4056214 100644 --- a/tools/perf/util/hisi-ptt.h +++ b/tools/perf/util/hisi-ptt.h @@ -13,4 +13,7 @@ struct auxtrace_record *hisi_ptt_recording_init(int *err, struct perf_pmu *hisi_ptt_pmu); +int hisi_ptt_process_auxtrace_info(union perf_event *event, + struct perf_session *session); + #endif -- cgit From a3a365655a28f12f07eddf4f3fd596987b175e1d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 7 Aug 2020 08:45:47 -0300 Subject: tools arch x86: Sync the msr-index.h copy with the kernel sources To pick up the changes in: b8d1d163604bd1e6 ("x86/apic: Don't disable x2APIC if locked") ca5b7c0d9621702e ("perf/x86/amd/lbr: Add LbrExtV2 branch record support") Addressing these tools/perf build warnings: diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' That makes the beautification scripts to pick some new entries: $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after $ diff -u before after --- before 2022-10-14 18:06:34.294561729 -0300 +++ after 2022-10-14 18:06:41.285744044 -0300 @@ -264,6 +264,7 @@ [0xc0000102 - x86_64_specific_MSRs_offset] = "KERNEL_GS_BASE", [0xc0000103 - x86_64_specific_MSRs_offset] = "TSC_AUX", [0xc0000104 - x86_64_specific_MSRs_offset] = "AMD64_TSC_RATIO", + [0xc000010e - x86_64_specific_MSRs_offset] = "AMD64_LBR_SELECT", [0xc000010f - x86_64_specific_MSRs_offset] = "AMD_DBG_EXTN_CFG", [0xc0000300 - x86_64_specific_MSRs_offset] = "AMD64_PERF_CNTR_GLOBAL_STATUS", [0xc0000301 - x86_64_specific_MSRs_offset] = "AMD64_PERF_CNTR_GLOBAL_CTL", $ Now one can trace systemwide asking to see backtraces to where that MSR is being read/written, see this example with a previous update: # perf trace -e msr:*_msr/max-stack=32/ --filter="msr>=IA32_U_CET && msr<=IA32_INT_SSP_TAB" ^C# If we use -v (verbose mode) we can see what it does behind the scenes: # perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr>=IA32_U_CET && msr<=IA32_INT_SSP_TAB" Using CPUID AuthenticAMD-25-21-0 0x6a0 0x6a8 New filter for msr:read_msr: (msr>=0x6a0 && msr<=0x6a8) && (common_pid != 597499 && common_pid != 3313) 0x6a0 0x6a8 New filter for msr:write_msr: (msr>=0x6a0 && msr<=0x6a8) && (common_pid != 597499 && common_pid != 3313) mmap size 528384B ^C# Example with a frequent msr: # perf trace -v -e msr:*_msr/max-stack=32/ --filter="msr==IA32_SPEC_CTRL" --max-events 2 Using CPUID AuthenticAMD-25-21-0 0x48 New filter for msr:read_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841) 0x48 New filter for msr:write_msr: (msr==0x48) && (common_pid != 2612129 && common_pid != 3841) mmap size 528384B Looking at the vmlinux_path (8 entries long) symsrc__init: build id mismatch for vmlinux. Using /proc/kcore for kernel data Using /proc/kallsyms for symbols 0.000 Timer/2525383 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6) do_trace_write_msr ([kernel.kallsyms]) do_trace_write_msr ([kernel.kallsyms]) __switch_to_xtra ([kernel.kallsyms]) __switch_to ([kernel.kallsyms]) __schedule ([kernel.kallsyms]) schedule ([kernel.kallsyms]) futex_wait_queue_me ([kernel.kallsyms]) futex_wait ([kernel.kallsyms]) do_futex ([kernel.kallsyms]) __x64_sys_futex ([kernel.kallsyms]) do_syscall_64 ([kernel.kallsyms]) entry_SYSCALL_64_after_hwframe ([kernel.kallsyms]) __futex_abstimed_wait_common64 (/usr/lib64/libpthread-2.33.so) 0.030 :0/0 msr:write_msr(msr: IA32_SPEC_CTRL, val: 2) do_trace_write_msr ([kernel.kallsyms]) do_trace_write_msr ([kernel.kallsyms]) __switch_to_xtra ([kernel.kallsyms]) __switch_to ([kernel.kallsyms]) __schedule ([kernel.kallsyms]) schedule_idle ([kernel.kallsyms]) do_idle ([kernel.kallsyms]) cpu_startup_entry ([kernel.kallsyms]) secondary_startup_64_no_verify ([kernel.kallsyms]) # Cc: Adrian Hunter Cc: Daniel Sneddon Cc: Dave Hansen Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sandipan Das Link: https://lore.kernel.org/lkml/Y0nQkz2TUJxwfXJd@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 6674bdb096f3..10ac52705892 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -155,6 +155,11 @@ * Return Stack Buffer Predictions. */ +#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* + * IA32_XAPIC_DISABLE_STATUS MSR + * supported + */ + #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* * Writeback and invalidate the @@ -585,6 +590,9 @@ #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL 0xc0000301 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR 0xc0000302 +/* AMD Last Branch Record MSRs */ +#define MSR_AMD64_LBR_SELECT 0xc000010e + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 @@ -756,6 +764,8 @@ #define MSR_AMD_DBG_EXTN_CFG 0xc000010f #define MSR_AMD_SAMP_BR_FROM 0xc0010300 +#define DBG_EXTN_CFG_LBRV2EN BIT_ULL(6) + #define MSR_IA32_MPERF 0x000000e7 #define MSR_IA32_APERF 0x000000e8 @@ -1054,4 +1064,12 @@ #define MSR_IA32_HW_FEEDBACK_PTR 0x17d0 #define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1 +/* x2APIC locked status */ +#define MSR_IA32_XAPIC_DISABLE_STATUS 0xBD +#define LEGACY_XAPIC_DISABLED BIT(0) /* + * x2APIC mode is locked and + * disabling x2APIC will cause + * a #GP + */ + #endif /* _ASM_X86_MSR_INDEX_H */ -- cgit From b854b4ee66437e6e1622fda90529c814978cb4ca Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Fri, 14 Oct 2022 17:14:54 -0300 Subject: cifs: fix double-fault crash during ntlmssp The crash occurred because we were calling memzero_explicit() on an already freed sess_data::iov[1] (ntlmsspblob) in sess_free_buffer(). Fix this by not calling memzero_explicit() on sess_data::iov[1] as it's already by handled by callers. Fixes: a4e430c8c8ba ("cifs: replace kfree() with kfree_sensitive() for sensitive data") Reviewed-by: Enzo Matsumiya Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/sess.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index c9edec7081de..0435d1dfa9e1 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -1208,16 +1208,18 @@ out_free_smb_buf: static void sess_free_buffer(struct sess_data *sess_data) { - int i; + struct kvec *iov = sess_data->iov; - /* zero the session data before freeing, as it might contain sensitive info (keys, etc) */ - for (i = 0; i < 3; i++) - if (sess_data->iov[i].iov_base) - memzero_explicit(sess_data->iov[i].iov_base, sess_data->iov[i].iov_len); + /* + * Zero the session data before freeing, as it might contain sensitive info (keys, etc). + * Note that iov[1] is already freed by caller. + */ + if (sess_data->buf0_type != CIFS_NO_BUFFER && iov[0].iov_base) + memzero_explicit(iov[0].iov_base, iov[0].iov_len); - free_rsp_buf(sess_data->buf0_type, sess_data->iov[0].iov_base); + free_rsp_buf(sess_data->buf0_type, iov[0].iov_base); sess_data->buf0_type = CIFS_NO_BUFFER; - kfree(sess_data->iov[2].iov_base); + kfree_sensitive(iov[2].iov_base); } static int -- cgit From f09bd695af3b8ab46fc24e5d6954a24104c38387 Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 14 Oct 2022 18:50:20 -0500 Subject: smb3: must initialize two ACL struct fields to zero Coverity spotted that we were not initalizing Stbz1 and Stbz2 to zero in create_sd_buf. Addresses-Coverity: 1513848 ("Uninitialized scalar variable") Cc: Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index e1162217ad1a..f8f89ff96c5d 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2420,7 +2420,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) unsigned int acelen, acl_size, ace_count; unsigned int owner_offset = 0; unsigned int group_offset = 0; - struct smb3_acl acl; + struct smb3_acl acl = {}; *len = round_up(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8); @@ -2493,6 +2493,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ acl.AclSize = cpu_to_le16(acl_size); acl.AceCount = cpu_to_le16(ace_count); + /* acl.Sbz1 and Sbz2 MBZ so are not set here, but initialized above */ memcpy(aclptr, &acl, sizeof(struct smb3_acl)); buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); -- cgit From 625b60d4f9517903ad499633776825e67fdb0c16 Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 14 Oct 2022 19:18:32 -0500 Subject: cifs: lease key is uninitialized in smb1 paths It is cleaner to set lease key to zero in the places where leases are not supported (smb1 can not return lease keys so the field was uninitialized). Addresses-Coverity: 1513994 ("Uninitialized scalar variable") Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index cbd46ac59cd2..a5c73c2af3a2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -413,7 +413,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, struct tcon_link *tlink; struct cifs_tcon *tcon; struct TCP_Server_Info *server; - struct cifs_fid fid; + struct cifs_fid fid = {}; struct cifs_pending_open open; __u32 oplock; struct cifsFileInfo *file_info; -- cgit From 2bff0659338e58a3a24698a35e7dcb2b62199ba4 Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 14 Oct 2022 20:00:32 -0500 Subject: cifs: lease key is uninitialized in two additional functions when smb1 cifs_open and _cifsFileInfo_put also end up with lease_key uninitialized in smb1 mounts. It is cleaner to set lease key to zero in these places where leases are not supported (smb1 can not return lease keys so the field was uninitialized). Addresses-Coverity: 1514207 ("Uninitialized scalar variable") Addresses-Coverity: 1514331 ("Uninitialized scalar variable") Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index dcec1690312b..f6ffee514c34 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -489,7 +489,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, struct cifsInodeInfo *cifsi = CIFS_I(inode); struct super_block *sb = inode->i_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - struct cifs_fid fid; + struct cifs_fid fid = {}; struct cifs_pending_open open; bool oplock_break_cancelled; @@ -571,7 +571,7 @@ int cifs_open(struct inode *inode, struct file *file) void *page; const char *full_path; bool posix_open_ok = false; - struct cifs_fid fid; + struct cifs_fid fid = {}; struct cifs_pending_open open; struct cifs_open_info_data data = {}; -- cgit From e3e9463414f610e91528f2b920b8cb655f4bae33 Mon Sep 17 00:00:00 2001 From: Steve French Date: Sat, 15 Oct 2022 00:43:22 -0500 Subject: smb3: improve SMB3 change notification support Change notification is a commonly supported feature by most servers, but the current ioctl to request notification when a directory is changed does not return the information about what changed (even though it is returned by the server in the SMB3 change notify response), it simply returns when there is a change. This ioctl improves upon CIFS_IOC_NOTIFY by returning the notify information structure which includes the name of the file(s) that changed and why. See MS-SMB2 2.2.35 for details on the individual filter flags and the file_notify_information structure returned. To use this simply pass in the following (with enough space to fit at least one file_notify_information structure) struct __attribute__((__packed__)) smb3_notify { uint32_t completion_filter; bool watch_tree; uint32_t data_len; uint8_t data[]; } __packed; using CIFS_IOC_NOTIFY_INFO 0xc009cf0b or equivalently _IOWR(CIFS_IOCTL_MAGIC, 11, struct smb3_notify_info) The ioctl will block until the server detects a change to that directory or its subdirectories (if watch_tree is set). Acked-by: Paulo Alcantara (SUSE) Acked-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/cifs_ioctl.h | 8 ++++++++ fs/cifs/cifsglob.h | 2 +- fs/cifs/ioctl.c | 25 ++++++++++++++++++++++++- fs/cifs/smb2ops.c | 35 ++++++++++++++++++++++++++++------- fs/cifs/smb2pdu.c | 30 +++++++++++++++++++++++++++--- fs/cifs/smb2proto.h | 3 ++- 6 files changed, 90 insertions(+), 13 deletions(-) diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index b87cbbe6d2d4..d86d78d5bfdc 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -91,6 +91,13 @@ struct smb3_notify { bool watch_tree; } __packed; +struct smb3_notify_info { + __u32 completion_filter; + bool watch_tree; + __u32 data_len; /* size of notify data below */ + __u8 notify_data[]; +} __packed; + #define CIFS_IOCTL_MAGIC 0xCF #define CIFS_IOC_COPYCHUNK_FILE _IOW(CIFS_IOCTL_MAGIC, 3, int) #define CIFS_IOC_SET_INTEGRITY _IO(CIFS_IOCTL_MAGIC, 4) @@ -100,6 +107,7 @@ struct smb3_notify { #define CIFS_DUMP_KEY _IOWR(CIFS_IOCTL_MAGIC, 8, struct smb3_key_debug_info) #define CIFS_IOC_NOTIFY _IOW(CIFS_IOCTL_MAGIC, 9, struct smb3_notify) #define CIFS_DUMP_FULL_KEY _IOWR(CIFS_IOCTL_MAGIC, 10, struct smb3_full_key_debug_info) +#define CIFS_IOC_NOTIFY_INFO _IOWR(CIFS_IOCTL_MAGIC, 11, struct smb3_notify_info) #define CIFS_IOC_SHUTDOWN _IOR ('X', 125, __u32) /* diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 9c0253835f1c..1420acf987f0 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -454,7 +454,7 @@ struct smb_version_operations { int (*enum_snapshots)(const unsigned int xid, struct cifs_tcon *tcon, struct cifsFileInfo *src_file, void __user *); int (*notify)(const unsigned int xid, struct file *pfile, - void __user *pbuf); + void __user *pbuf, bool return_changes); int (*query_mf_symlink)(unsigned int, struct cifs_tcon *, struct cifs_sb_info *, const unsigned char *, char *, unsigned int *); diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index b6e6e5d6c8dd..89d5fa887364 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -484,12 +484,35 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) tcon = tlink_tcon(tlink); if (tcon && tcon->ses->server->ops->notify) { rc = tcon->ses->server->ops->notify(xid, - filep, (void __user *)arg); + filep, (void __user *)arg, + false /* no ret data */); cifs_dbg(FYI, "ioctl notify rc %d\n", rc); } else rc = -EOPNOTSUPP; cifs_put_tlink(tlink); break; + case CIFS_IOC_NOTIFY_INFO: + if (!S_ISDIR(inode->i_mode)) { + /* Notify can only be done on directories */ + rc = -EOPNOTSUPP; + break; + } + cifs_sb = CIFS_SB(inode->i_sb); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + break; + } + tcon = tlink_tcon(tlink); + if (tcon && tcon->ses->server->ops->notify) { + rc = tcon->ses->server->ops->notify(xid, + filep, (void __user *)arg, + true /* return details */); + cifs_dbg(FYI, "ioctl notify info rc %d\n", rc); + } else + rc = -EOPNOTSUPP; + cifs_put_tlink(tlink); + break; case CIFS_IOC_SHUTDOWN: rc = cifs_shutdown(inode->i_sb, arg); break; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index b907d1fab8d9..17b25153cb68 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2018,9 +2018,10 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, static int smb3_notify(const unsigned int xid, struct file *pfile, - void __user *ioc_buf) + void __user *ioc_buf, bool return_changes) { - struct smb3_notify notify; + struct smb3_notify_info notify; + struct smb3_notify_info __user *pnotify_buf; struct dentry *dentry = pfile->f_path.dentry; struct inode *inode = file_inode(pfile); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); @@ -2028,10 +2029,12 @@ smb3_notify(const unsigned int xid, struct file *pfile, struct cifs_fid fid; struct cifs_tcon *tcon; const unsigned char *path; + char *returned_ioctl_info = NULL; void *page = alloc_dentry_path(); __le16 *utf16_path = NULL; u8 oplock = SMB2_OPLOCK_LEVEL_NONE; int rc = 0; + __u32 ret_len = 0; path = build_path_from_dentry(dentry, page); if (IS_ERR(path)) { @@ -2045,9 +2048,17 @@ smb3_notify(const unsigned int xid, struct file *pfile, goto notify_exit; } - if (copy_from_user(¬ify, ioc_buf, sizeof(struct smb3_notify))) { - rc = -EFAULT; - goto notify_exit; + if (return_changes) { + if (copy_from_user(¬ify, ioc_buf, sizeof(struct smb3_notify_info))) { + rc = -EFAULT; + goto notify_exit; + } + } else { + if (copy_from_user(¬ify, ioc_buf, sizeof(struct smb3_notify))) { + rc = -EFAULT; + goto notify_exit; + } + notify.data_len = 0; } tcon = cifs_sb_master_tcon(cifs_sb); @@ -2064,12 +2075,22 @@ smb3_notify(const unsigned int xid, struct file *pfile, goto notify_exit; rc = SMB2_change_notify(xid, tcon, fid.persistent_fid, fid.volatile_fid, - notify.watch_tree, notify.completion_filter); + notify.watch_tree, notify.completion_filter, + notify.data_len, &returned_ioctl_info, &ret_len); SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); cifs_dbg(FYI, "change notify for path %s rc %d\n", path, rc); - + if (return_changes && (ret_len > 0) && (notify.data_len > 0)) { + if (ret_len > notify.data_len) + ret_len = notify.data_len; + pnotify_buf = (struct smb3_notify_info __user *)ioc_buf; + if (copy_to_user(pnotify_buf->notify_data, returned_ioctl_info, ret_len)) + rc = -EFAULT; + else if (copy_to_user(&pnotify_buf->data_len, &ret_len, sizeof(ret_len))) + rc = -EFAULT; + } + kfree(returned_ioctl_info); notify_exit: free_dentry_path(page); kfree(utf16_path); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index f8f89ff96c5d..a2384509ea84 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3710,11 +3710,13 @@ SMB2_notify_init(const unsigned int xid, struct smb_rqst *rqst, int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, bool watch_tree, - u32 completion_filter) + u32 completion_filter, u32 max_out_data_len, char **out_data, + u32 *plen /* returned data len */) { struct cifs_ses *ses = tcon->ses; struct TCP_Server_Info *server = cifs_pick_channel(ses); struct smb_rqst rqst; + struct smb2_change_notify_rsp *smb_rsp; struct kvec iov[1]; struct kvec rsp_iov = {NULL, 0}; int resp_buftype = CIFS_NO_BUFFER; @@ -3730,6 +3732,9 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, memset(&rqst, 0, sizeof(struct smb_rqst)); memset(&iov, 0, sizeof(iov)); + if (plen) + *plen = 0; + rqst.rq_iov = iov; rqst.rq_nvec = 1; @@ -3748,9 +3753,28 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, cifs_stats_fail_inc(tcon, SMB2_CHANGE_NOTIFY_HE); trace_smb3_notify_err(xid, persistent_fid, tcon->tid, ses->Suid, (u8)watch_tree, completion_filter, rc); - } else + } else { trace_smb3_notify_done(xid, persistent_fid, tcon->tid, - ses->Suid, (u8)watch_tree, completion_filter); + ses->Suid, (u8)watch_tree, completion_filter); + /* validate that notify information is plausible */ + if ((rsp_iov.iov_base == NULL) || + (rsp_iov.iov_len < sizeof(struct smb2_change_notify_rsp))) + goto cnotify_exit; + + smb_rsp = (struct smb2_change_notify_rsp *)rsp_iov.iov_base; + + smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset), + le32_to_cpu(smb_rsp->OutputBufferLength), &rsp_iov, + sizeof(struct file_notify_information)); + + *out_data = kmemdup((char *)smb_rsp + le16_to_cpu(smb_rsp->OutputBufferOffset), + le32_to_cpu(smb_rsp->OutputBufferLength), GFP_KERNEL); + if (*out_data == NULL) { + rc = -ENOMEM; + goto cnotify_exit; + } else + *plen = le32_to_cpu(smb_rsp->OutputBufferLength); + } cnotify_exit: if (rqst.rq_iov) diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 7818d0b83567..be21b5d26f67 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -144,7 +144,8 @@ extern int SMB2_ioctl_init(struct cifs_tcon *tcon, extern void SMB2_ioctl_free(struct smb_rqst *rqst); extern int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, bool watch_tree, - u32 completion_filter); + u32 completion_filter, u32 max_out_data_len, + char **out_data, u32 *plen /* returned data len */); extern int __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, -- cgit From 34a0bac084e49324c29e6d0984d24096e02c6314 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Thu, 13 Oct 2022 14:46:37 -0700 Subject: MAINTAINERS: git://github -> https://github.com for openrisc Github deprecated the git:// links about a year ago, so let's move to the https:// URLs instead. Reported-by: Conor Dooley Link: https://github.blog/2021-09-01-improving-git-protocol-security-github/ Signed-off-by: Palmer Dabbelt Signed-off-by: Stafford Horne --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index f5ca4aefd184..4c6699909166 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15240,7 +15240,7 @@ M: Stafford Horne L: openrisc@lists.librecores.org S: Maintained W: http://openrisc.io -T: git git://github.com/openrisc/linux.git +T: git https://github.com/openrisc/linux.git F: Documentation/devicetree/bindings/openrisc/ F: Documentation/openrisc/ F: arch/openrisc/ -- cgit From e36ce448a08d43de69e7449eb225805a7a8addf8 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Sat, 15 Oct 2022 13:34:29 +0900 Subject: mm/slab: use kmalloc_node() for off slab freelist_idx_t array allocation After commit d6a71648dbc0 ("mm/slab: kmalloc: pass requests larger than order-1 page to page allocator"), SLAB passes large ( > PAGE_SIZE * 2) requests to buddy like SLUB does. SLAB has been using kmalloc caches to allocate freelist_idx_t array for off slab caches. But after the commit, freelist_size can be bigger than KMALLOC_MAX_CACHE_SIZE. Instead of using pointer to kmalloc cache, use kmalloc_node() and only check if the kmalloc cache is off slab during calculate_slab_order(). If freelist_size > KMALLOC_MAX_CACHE_SIZE, no looping condition happens as it allocates freelist_idx_t array directly from buddy. Link: https://lore.kernel.org/all/20221014205818.GA1428667@roeck-us.net/ Reported-and-tested-by: Guenter Roeck Fixes: d6a71648dbc0 ("mm/slab: kmalloc: pass requests larger than order-1 page to page allocator") Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Vlastimil Babka --- include/linux/slab_def.h | 1 - mm/slab.c | 37 +++++++++++++++++++------------------ 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index e24c9aff6fed..f0ffad6a3365 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -33,7 +33,6 @@ struct kmem_cache { size_t colour; /* cache colouring range */ unsigned int colour_off; /* colour offset */ - struct kmem_cache *freelist_cache; unsigned int freelist_size; /* constructor func */ diff --git a/mm/slab.c b/mm/slab.c index a5486ff8362a..d1f6e2c64c2e 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1619,7 +1619,7 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slab) * although actual page can be freed in rcu context */ if (OFF_SLAB(cachep)) - kmem_cache_free(cachep->freelist_cache, freelist); + kfree(freelist); } /* @@ -1671,21 +1671,27 @@ static size_t calculate_slab_order(struct kmem_cache *cachep, if (flags & CFLGS_OFF_SLAB) { struct kmem_cache *freelist_cache; size_t freelist_size; + size_t freelist_cache_size; freelist_size = num * sizeof(freelist_idx_t); - freelist_cache = kmalloc_slab(freelist_size, 0u); - if (!freelist_cache) - continue; - - /* - * Needed to avoid possible looping condition - * in cache_grow_begin() - */ - if (OFF_SLAB(freelist_cache)) - continue; + if (freelist_size > KMALLOC_MAX_CACHE_SIZE) { + freelist_cache_size = PAGE_SIZE << get_order(freelist_size); + } else { + freelist_cache = kmalloc_slab(freelist_size, 0u); + if (!freelist_cache) + continue; + freelist_cache_size = freelist_cache->size; + + /* + * Needed to avoid possible looping condition + * in cache_grow_begin() + */ + if (OFF_SLAB(freelist_cache)) + continue; + } /* check if off slab has enough benefit */ - if (freelist_cache->size > cachep->size / 2) + if (freelist_cache_size > cachep->size / 2) continue; } @@ -2061,11 +2067,6 @@ done: cachep->flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); #endif - if (OFF_SLAB(cachep)) { - cachep->freelist_cache = - kmalloc_slab(cachep->freelist_size, 0u); - } - err = setup_cpu_cache(cachep, gfp); if (err) { __kmem_cache_release(cachep); @@ -2292,7 +2293,7 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep, freelist = NULL; else if (OFF_SLAB(cachep)) { /* Slab management obj is off-slab. */ - freelist = kmem_cache_alloc_node(cachep->freelist_cache, + freelist = kmalloc_node(cachep->freelist_size, local_flags, nodeid); } else { /* We will use last bytes at the slab for freelist */ -- cgit From 3753af778dd9d0d5199d6a7d01b0ead33135d095 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sat, 15 Oct 2022 05:18:11 +0900 Subject: kbuild: fix single directory build Commit f110e5a250e3 ("kbuild: refactor single builds of *.ko") was wrong. KBUILD_MODULES _is_ needed for single builds. Otherwise, "make foo/bar/baz/" does not build module objects at all. Fixes: f110e5a250e3 ("kbuild: refactor single builds of *.ko") Reported-by: David Sterba Signed-off-by: Masahiro Yamada Tested-by: David Sterba --- Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Makefile b/Makefile index 85a63a1d29b3..48a005fc69ca 100644 --- a/Makefile +++ b/Makefile @@ -1978,6 +1978,8 @@ endif single-goals := $(addprefix $(build-dir)/, $(single-no-ko)) +KBUILD_MODULES := 1 + endif # Preset locale variables to speed up the build process. Limit locale -- cgit From 0a6de78cff600cb991f2a1b7ed376935871796a0 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 14 Oct 2022 13:42:11 -0700 Subject: lib/Kconfig.debug: Add check for non-constant .{s,u}leb128 support to DWARF5 When building with a RISC-V kernel with DWARF5 debug info using clang and the GNU assembler, several instances of the following error appear: /tmp/vgettimeofday-48aa35.s:2963: Error: non-constant .uleb128 is not supported Dumping the .s file reveals these .uleb128 directives come from .debug_loc and .debug_ranges: .Ldebug_loc0: .byte 4 # DW_LLE_offset_pair .uleb128 .Lfunc_begin0-.Lfunc_begin0 # starting offset .uleb128 .Ltmp1-.Lfunc_begin0 # ending offset .byte 1 # Loc expr size .byte 90 # DW_OP_reg10 .byte 0 # DW_LLE_end_of_list .Ldebug_ranges0: .byte 4 # DW_RLE_offset_pair .uleb128 .Ltmp6-.Lfunc_begin0 # starting offset .uleb128 .Ltmp27-.Lfunc_begin0 # ending offset .byte 4 # DW_RLE_offset_pair .uleb128 .Ltmp28-.Lfunc_begin0 # starting offset .uleb128 .Ltmp30-.Lfunc_begin0 # ending offset .byte 0 # DW_RLE_end_of_list There is an outstanding binutils issue to support a non-constant operand to .sleb128 and .uleb128 in GAS for RISC-V but there does not appear to be any movement on it, due to concerns over how it would work with linker relaxation. To avoid these build errors, prevent DWARF5 from being selected when using clang and an assembler that does not have support for these symbol deltas, which can be easily checked in Kconfig with as-instr plus the small test program from the dwz test suite from the binutils issue. Link: https://sourceware.org/bugzilla/show_bug.cgi?id=27215 Link: https://github.com/ClangBuiltLinux/linux/issues/1719 Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Masahiro Yamada --- lib/Kconfig.debug | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index db8d9271cabf..5c1c63575895 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -231,6 +231,11 @@ config DEBUG_INFO in the "Debug information" choice below, indicating that debug information will be generated for build targets. +# Clang is known to generate .{s,u}leb128 with symbol deltas with DWARF5, which +# some targets may not support: https://sourceware.org/bugzilla/show_bug.cgi?id=27215 +config AS_HAS_NON_CONST_LEB128 + def_bool $(as-instr,.uleb128 .Lexpr_end4 - .Lexpr_start3\n.Lexpr_start3:\n.Lexpr_end4:) + choice prompt "Debug information" depends on DEBUG_KERNEL @@ -253,7 +258,7 @@ config DEBUG_INFO_NONE config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT bool "Rely on the toolchain's implicit default DWARF version" select DEBUG_INFO - depends on !CC_IS_CLANG || AS_IS_LLVM || CLANG_VERSION < 140000 || (AS_IS_GNU && AS_VERSION >= 23502) + depends on !CC_IS_CLANG || AS_IS_LLVM || CLANG_VERSION < 140000 || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_LEB128) help The implicit default version of DWARF debug info produced by a toolchain changes over time. @@ -277,7 +282,7 @@ config DEBUG_INFO_DWARF4 config DEBUG_INFO_DWARF5 bool "Generate DWARF Version 5 debuginfo" select DEBUG_INFO - depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502) + depends on !CC_IS_CLANG || AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502 && AS_HAS_NON_CONST_LEB128) help Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc 5.0+ accepts the -gdwarf-5 flag but only had partial support for some -- cgit From 80493877d7d0ae0cbe62921d748682811c58026f Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sun, 16 Oct 2022 00:53:51 +0900 Subject: Revert "cpumask: fix checking valid cpu range". This reverts commit 78e5a3399421 ("cpumask: fix checking valid cpu range"). syzbot is hitting WARN_ON_ONCE(cpu >= nr_cpumask_bits) warning at cpu_max_bits_warn() [1], for commit 78e5a3399421 ("cpumask: fix checking valid cpu range") is broken. Obviously that patch hits WARN_ON_ONCE() when e.g. reading /proc/cpuinfo because passing "cpu + 1" instead of "cpu" will trivially hit cpu == nr_cpumask_bits condition. Although syzbot found this problem in linux-next.git on 2022/09/27 [2], this problem was not fixed immediately. As a result, that patch was sent to linux.git before the patch author recognizes this problem, and syzbot started failing to test changes in linux.git since 2022/10/10 [3]. Andrew Jones proposed a fix for x86 and riscv architectures [4]. But [2] and [5] indicate that affected locations are not limited to arch code. More delay before we find and fix affected locations, less tested kernel (and more difficult to bisect and fix) before release. We should have inspected and fixed basically all cpumask users before applying that patch. We should not crash kernels in order to ask existing cpumask users to update their code, even if limited to CONFIG_DEBUG_PER_CPU_MAPS=y case. Link: https://syzkaller.appspot.com/bug?extid=d0fd2bf0dd6da72496dd [1] Link: https://syzkaller.appspot.com/bug?extid=21da700f3c9f0bc40150 [2] Link: https://syzkaller.appspot.com/bug?extid=51a652e2d24d53e75734 [3] Link: https://lkml.kernel.org/r/20221014155845.1986223-1-ajones@ventanamicro.com [4] Link: https://syzkaller.appspot.com/bug?extid=4d46c43d81c3bd155060 [5] Reported-by: Andrew Jones Reported-by: syzbot+d0fd2bf0dd6da72496dd@syzkaller.appspotmail.com Signed-off-by: Tetsuo Handa Cc: Yury Norov Cc: Borislav Petkov Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 2f065ad97541..c2aa0aa26b45 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -174,8 +174,9 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } @@ -188,8 +189,9 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp) */ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } @@ -229,8 +231,9 @@ static inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { - /* n is a prior cpu */ - cpumask_check(n + 1); + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits, n + 1); } @@ -260,8 +263,8 @@ static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); - /* n is a prior cpu */ - cpumask_check(n + 1); + if (n != -1) + cpumask_check(n); /* * Return the first available CPU when wrapping, or when starting before cpu0, -- cgit From 2d1f274b95c6e4ba6a813b3b8e7a1a38d54a0a08 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 15 Oct 2022 21:24:41 +0000 Subject: skmsg: pass gfp argument to alloc_sk_msg() syzbot found that alloc_sk_msg() could be called from a non sleepable context. sk_psock_verdict_recv() uses rcu_read_lock() protection. We need the callers to pass a gfp_t argument to avoid issues. syzbot report was: BUG: sleeping function called from invalid context at include/linux/sched/mm.h:274 in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 3613, name: syz-executor414 preempt_count: 0, expected: 0 RCU nest depth: 1, expected: 0 INFO: lockdep is turned off. CPU: 0 PID: 3613 Comm: syz-executor414 Not tainted 6.0.0-syzkaller-09589-g55be6084c8e0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e3/0x2cb lib/dump_stack.c:106 __might_resched+0x538/0x6a0 kernel/sched/core.c:9877 might_alloc include/linux/sched/mm.h:274 [inline] slab_pre_alloc_hook mm/slab.h:700 [inline] slab_alloc_node mm/slub.c:3162 [inline] slab_alloc mm/slub.c:3256 [inline] kmem_cache_alloc_trace+0x59/0x310 mm/slub.c:3287 kmalloc include/linux/slab.h:600 [inline] kzalloc include/linux/slab.h:733 [inline] alloc_sk_msg net/core/skmsg.c:507 [inline] sk_psock_skb_ingress_self+0x5c/0x330 net/core/skmsg.c:600 sk_psock_verdict_apply+0x395/0x440 net/core/skmsg.c:1014 sk_psock_verdict_recv+0x34d/0x560 net/core/skmsg.c:1201 tcp_read_skb+0x4a1/0x790 net/ipv4/tcp.c:1770 tcp_rcv_established+0x129d/0x1a10 net/ipv4/tcp_input.c:5971 tcp_v4_do_rcv+0x479/0xac0 net/ipv4/tcp_ipv4.c:1681 sk_backlog_rcv include/net/sock.h:1109 [inline] __release_sock+0x1d8/0x4c0 net/core/sock.c:2906 release_sock+0x5d/0x1c0 net/core/sock.c:3462 tcp_sendmsg+0x36/0x40 net/ipv4/tcp.c:1483 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] __sys_sendto+0x46d/0x5f0 net/socket.c:2117 __do_sys_sendto net/socket.c:2129 [inline] __se_sys_sendto net/socket.c:2125 [inline] __x64_sys_sendto+0xda/0xf0 net/socket.c:2125 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 43312915b5ba ("skmsg: Get rid of unncessary memset()") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Cong Wang Cc: Daniel Borkmann Cc: John Fastabend Signed-off-by: David S. Miller --- net/core/skmsg.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ca70525621c7..1efdc47a999b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -500,11 +500,11 @@ bool sk_msg_is_readable(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_msg_is_readable); -static struct sk_msg *alloc_sk_msg(void) +static struct sk_msg *alloc_sk_msg(gfp_t gfp) { struct sk_msg *msg; - msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_KERNEL); + msg = kzalloc(sizeof(*msg), gfp | __GFP_NOWARN); if (unlikely(!msg)) return NULL; sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS); @@ -520,7 +520,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, if (!sk_rmem_schedule(sk, skb, skb->truesize)) return NULL; - return alloc_sk_msg(); + return alloc_sk_msg(GFP_KERNEL); } static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, @@ -597,7 +597,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len) { - struct sk_msg *msg = alloc_sk_msg(); + struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC); struct sock *sk = psock->sk; int err; -- cgit From 9abf2313adc1ca1b6180c508c25f22f9395cc780 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 16 Oct 2022 15:36:24 -0700 Subject: Linux 6.1-rc1 --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index c690361b393f..f41ec8c8426b 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 -PATCHLEVEL = 0 +PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* -- cgit From 664609e49f1c84fc97987b2bf64544e586b8849c Mon Sep 17 00:00:00 2001 From: Yue Hu Date: Wed, 5 Oct 2022 09:35:28 +0800 Subject: erofs: fix illegal unmapped accesses in z_erofs_fill_inode_lazy() Note that we are still accessing 'h_idata_size' and 'h_fragmentoff' after calling erofs_put_metabuf(), that is not correct. Fix it. Fixes: ab92184ff8f1 ("erofs: add on-disk compressed tail-packing inline support") Fixes: b15b2e307c3a ("erofs: support on-disk compressed fragments data") Signed-off-by: Yue Hu Reviewed-by: Gao Xiang Reviewed-by: Chao Yu Link: https://lore.kernel.org/r/20221005013528.62977-1-zbestahu@163.com Signed-off-by: Gao Xiang --- fs/erofs/zmap.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 44c27ef39c43..0bb66927e3d0 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -57,8 +57,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize + vi->xattr_isize, 8); - kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), - EROFS_KMAP_ATOMIC); + kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP); if (IS_ERR(kaddr)) { err = PTR_ERR(kaddr); goto out_unlock; @@ -73,7 +72,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) vi->z_advise = Z_EROFS_ADVISE_FRAGMENT_PCLUSTER; vi->z_fragmentoff = le64_to_cpu(*(__le64 *)h) ^ (1ULL << 63); vi->z_tailextent_headlcn = 0; - goto unmap_done; + goto done; } vi->z_advise = le16_to_cpu(h->h_advise); vi->z_algorithmtype[0] = h->h_algorithmtype & 15; @@ -85,7 +84,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel", headnr + 1, vi->z_algorithmtype[headnr], vi->nid); err = -EOPNOTSUPP; - goto unmap_done; + goto out_put_metabuf; } vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7); @@ -95,7 +94,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu", vi->nid); err = -EFSCORRUPTED; - goto unmap_done; + goto out_put_metabuf; } if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION && !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^ @@ -103,12 +102,8 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu", vi->nid); err = -EFSCORRUPTED; - goto unmap_done; + goto out_put_metabuf; } -unmap_done: - erofs_put_metabuf(&buf); - if (err) - goto out_unlock; if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER) { struct erofs_map_blocks map = { @@ -127,7 +122,7 @@ unmap_done: err = -EFSCORRUPTED; } if (err < 0) - goto out_unlock; + goto out_put_metabuf; } if (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER && @@ -141,11 +136,14 @@ unmap_done: EROFS_GET_BLOCKS_FINDTAIL); erofs_put_metabuf(&map.buf); if (err < 0) - goto out_unlock; + goto out_put_metabuf; } +done: /* paired with smp_mb() at the beginning of the function */ smp_mb(); set_bit(EROFS_I_Z_INITED_BIT, &vi->flags); +out_put_metabuf: + erofs_put_metabuf(&buf); out_unlock: clear_and_wake_up_bit(EROFS_I_BL_Z_BIT, &vi->flags); return err; -- cgit From 63bbb85658ea43dd35dbfde6d4150b47c407fc87 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Wed, 12 Oct 2022 12:50:56 +0800 Subject: erofs: shouldn't churn the mapping page for duplicated copies If other duplicated copies exist in one decompression shot, should leave the old page as is rather than replace it with the new duplicated one. Otherwise, the following cold path to deal with duplicated copies will use the invalid bvec. It impacts compressed data deduplication. Also, shift the onlinepage EIO bit to avoid touching the signed bit. Fixes: 267f2492c8f7 ("erofs: introduce multi-reference pclusters (fully-referenced)") Reviewed-by: Chao Yu Signed-off-by: Gao Xiang Link: https://lore.kernel.org/r/20221012045056.13421-1-hsiangkao@linux.alibaba.com --- fs/erofs/zdata.c | 8 +++----- fs/erofs/zdata.h | 6 +++--- 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 559380a535af..4553be650968 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -888,15 +888,13 @@ static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be, if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK)) { unsigned int pgnr; - struct page *oldpage; pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT; DBG_BUGON(pgnr >= be->nr_pages); - oldpage = be->decompressed_pages[pgnr]; - be->decompressed_pages[pgnr] = bvec->page; - - if (!oldpage) + if (!be->decompressed_pages[pgnr]) { + be->decompressed_pages[pgnr] = bvec->page; return; + } } /* (cold path) one pcluster is requested multiple times */ diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index e7f04c4fbb81..d98c95212985 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -126,10 +126,10 @@ static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl) } /* - * bit 31: I/O error occurred on this page - * bit 0 - 30: remaining parts to complete this page + * bit 30: I/O error occurred on this page + * bit 0 - 29: remaining parts to complete this page */ -#define Z_EROFS_PAGE_EIO (1 << 31) +#define Z_EROFS_PAGE_EIO (1 << 30) static inline void z_erofs_onlinepage_init(struct page *page) { -- cgit From e7933278b442f97809b1ea84264586302bd08a03 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Fri, 14 Oct 2022 14:49:15 +0800 Subject: erofs: fix up inplace decompression success rate Partial decompression should be checked after updating length. It's a new regression when introducing multi-reference pclusters. Fixes: 2bfab9c0edac ("erofs: record the longest decompressed size in this round") Reviewed-by: Chao Yu Signed-off-by: Gao Xiang Link: https://lore.kernel.org/r/20221014064915.8103-1-hsiangkao@linux.alibaba.com --- fs/erofs/zdata.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 4553be650968..c7f24fc7efd5 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -813,15 +813,14 @@ retry: ++spiltted; if (fe->pcl->pageofs_out != (map->m_la & ~PAGE_MASK)) fe->pcl->multibases = true; - - if ((map->m_flags & EROFS_MAP_FULL_MAPPED) && - !(map->m_flags & EROFS_MAP_PARTIAL_REF) && - fe->pcl->length == map->m_llen) - fe->pcl->partial = false; if (fe->pcl->length < offset + end - map->m_la) { fe->pcl->length = offset + end - map->m_la; fe->pcl->pageofs_out = map->m_la & ~PAGE_MASK; } + if ((map->m_flags & EROFS_MAP_FULL_MAPPED) && + !(map->m_flags & EROFS_MAP_PARTIAL_REF) && + fe->pcl->length == map->m_llen) + fe->pcl->partial = false; next_part: /* shorten the remaining extent to update progress */ map->m_llen = offset + cur - map->m_la; -- cgit From 979556f1521a835a059de3b117b9c6c6642c7d58 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Wed, 12 Oct 2022 15:11:05 +0200 Subject: ata: ahci-imx: Fix MODULE_ALIAS 'ahci:' is an invalid prefix, preventing the module from autoloading. Fix this by using the 'platform:' prefix and DRV_NAME. Fixes: 9e54eae23bc9 ("ahci_imx: add ahci sata support on imx platforms") Cc: stable@vger.kernel.org Signed-off-by: Alexander Stein Reviewed-by: Fabio Estevam Signed-off-by: Damien Le Moal --- drivers/ata/ahci_imx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index b734e069034d..632caa301458 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -1235,4 +1235,4 @@ module_platform_driver(imx_ahci_driver); MODULE_DESCRIPTION("Freescale i.MX AHCI SATA platform driver"); MODULE_AUTHOR("Richard Zhu "); MODULE_LICENSE("GPL"); -MODULE_ALIAS("ahci:imx"); +MODULE_ALIAS("platform:" DRV_NAME); -- cgit From 1e41e693f458eef2d5728207dbd327cd3b16580a Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Tue, 11 Oct 2022 10:46:17 +0800 Subject: ata: ahci: Match EM_MAX_SLOTS with SATA_PMP_MAX_PORTS UBSAN complains about array-index-out-of-bounds: [ 1.980703] kernel: UBSAN: array-index-out-of-bounds in /build/linux-9H675w/linux-5.15.0/drivers/ata/libahci.c:968:41 [ 1.980709] kernel: index 15 is out of range for type 'ahci_em_priv [8]' [ 1.980713] kernel: CPU: 0 PID: 209 Comm: scsi_eh_8 Not tainted 5.15.0-25-generic #25-Ubuntu [ 1.980716] kernel: Hardware name: System manufacturer System Product Name/P5Q3, BIOS 1102 06/11/2010 [ 1.980718] kernel: Call Trace: [ 1.980721] kernel: [ 1.980723] kernel: show_stack+0x52/0x58 [ 1.980729] kernel: dump_stack_lvl+0x4a/0x5f [ 1.980734] kernel: dump_stack+0x10/0x12 [ 1.980736] kernel: ubsan_epilogue+0x9/0x45 [ 1.980739] kernel: __ubsan_handle_out_of_bounds.cold+0x44/0x49 [ 1.980742] kernel: ahci_qc_issue+0x166/0x170 [libahci] [ 1.980748] kernel: ata_qc_issue+0x135/0x240 [ 1.980752] kernel: ata_exec_internal_sg+0x2c4/0x580 [ 1.980754] kernel: ? vprintk_default+0x1d/0x20 [ 1.980759] kernel: ata_exec_internal+0x67/0xa0 [ 1.980762] kernel: sata_pmp_read+0x8d/0xc0 [ 1.980765] kernel: sata_pmp_read_gscr+0x3c/0x90 [ 1.980768] kernel: sata_pmp_attach+0x8b/0x310 [ 1.980771] kernel: ata_eh_revalidate_and_attach+0x28c/0x4b0 [ 1.980775] kernel: ata_eh_recover+0x6b6/0xb30 [ 1.980778] kernel: ? ahci_do_hardreset+0x180/0x180 [libahci] [ 1.980783] kernel: ? ahci_stop_engine+0xb0/0xb0 [libahci] [ 1.980787] kernel: ? ahci_do_softreset+0x290/0x290 [libahci] [ 1.980792] kernel: ? trace_event_raw_event_ata_eh_link_autopsy_qc+0xe0/0xe0 [ 1.980795] kernel: sata_pmp_eh_recover.isra.0+0x214/0x560 [ 1.980799] kernel: sata_pmp_error_handler+0x23/0x40 [ 1.980802] kernel: ahci_error_handler+0x43/0x80 [libahci] [ 1.980806] kernel: ata_scsi_port_error_handler+0x2b1/0x600 [ 1.980810] kernel: ata_scsi_error+0x9c/0xd0 [ 1.980813] kernel: scsi_error_handler+0xa1/0x180 [ 1.980817] kernel: ? scsi_unjam_host+0x1c0/0x1c0 [ 1.980820] kernel: kthread+0x12a/0x150 [ 1.980823] kernel: ? set_kthread_struct+0x50/0x50 [ 1.980826] kernel: ret_from_fork+0x22/0x30 [ 1.980831] kernel: This happens because sata_pmp_init_links() initialize link->pmp up to SATA_PMP_MAX_PORTS while em_priv is declared as 8 elements array. I can't find the maximum Enclosure Management ports specified in AHCI spec v1.3.1, but "12.2.1 LED message type" states that "Port Multiplier Information" can utilize 4 bits, which implies it can support up to 16 ports. Hence, use SATA_PMP_MAX_PORTS as EM_MAX_SLOTS to resolve the issue. BugLink: https://bugs.launchpad.net/bugs/1970074 Cc: stable@vger.kernel.org Signed-off-by: Kai-Heng Feng Signed-off-by: Damien Le Moal --- drivers/ata/ahci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index da7ee8bec165..7add8e79912b 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -257,7 +257,7 @@ enum { PCS_7 = 0x94, /* 7+ port PCS (Denverton) */ /* em constants */ - EM_MAX_SLOTS = 8, + EM_MAX_SLOTS = SATA_PMP_MAX_PORTS, EM_MAX_RETRY = 5, /* em_ctl bits */ -- cgit From ce4b815686573bef82d5ee53bf6f509bf20904dc Mon Sep 17 00:00:00 2001 From: Dawei Li Date: Mon, 17 Oct 2022 09:55:53 +0800 Subject: erofs: protect s_inodes with s_inode_list_lock for fscache s_inodes is superblock-specific resource, which should be protected by sb's specific lock s_inode_list_lock. Link: https://lore.kernel.org/r/TYCP286MB23238380DE3B74874E8D78ABCA299@TYCP286MB2323.JPNP286.PROD.OUTLOOK.COM Fixes: 7d41963759fe ("erofs: Support sharing cookies in the same domain") Reviewed-by: Yue Hu Reviewed-by: Jia Zhu Reviewed-by: Jingbo Xu Signed-off-by: Dawei Li Signed-off-by: Gao Xiang --- fs/erofs/fscache.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 998cd26a1b3b..fe05bc51f9f2 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -590,14 +590,17 @@ struct erofs_fscache *erofs_domain_register_cookie(struct super_block *sb, struct super_block *psb = erofs_pseudo_mnt->mnt_sb; mutex_lock(&erofs_domain_cookies_lock); + spin_lock(&psb->s_inode_list_lock); list_for_each_entry(inode, &psb->s_inodes, i_sb_list) { ctx = inode->i_private; if (!ctx || ctx->domain != domain || strcmp(ctx->name, name)) continue; igrab(inode); + spin_unlock(&psb->s_inode_list_lock); mutex_unlock(&erofs_domain_cookies_lock); return ctx; } + spin_unlock(&psb->s_inode_list_lock); ctx = erofs_fscache_domain_init_cookie(sb, name, need_inode); mutex_unlock(&erofs_domain_cookies_lock); return ctx; -- cgit From b3d0d98179d62f9d55635a600679c4fa362baf8d Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 17 Oct 2022 11:51:54 +0800 Subject: net: ethernet: mtk_eth_soc: fix possible memory leak in mtk_probe() If mtk_wed_add_hw() has been called, mtk_wed_exit() needs be called in error path or removing module to free the memory allocated in mtk_wed_add_hw(). Fixes: 804775dfc288 ("net: ethernet: mtk_eth_soc: add support for Wireless Ethernet Dispatch (WED)") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 4fba7cb0144b..7cd381530aa4 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -4060,19 +4060,23 @@ static int mtk_probe(struct platform_device *pdev) eth->irq[i] = platform_get_irq(pdev, i); if (eth->irq[i] < 0) { dev_err(&pdev->dev, "no IRQ%d resource found\n", i); - return -ENXIO; + err = -ENXIO; + goto err_wed_exit; } } for (i = 0; i < ARRAY_SIZE(eth->clks); i++) { eth->clks[i] = devm_clk_get(eth->dev, mtk_clks_source_name[i]); if (IS_ERR(eth->clks[i])) { - if (PTR_ERR(eth->clks[i]) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(eth->clks[i]) == -EPROBE_DEFER) { + err = -EPROBE_DEFER; + goto err_wed_exit; + } if (eth->soc->required_clks & BIT(i)) { dev_err(&pdev->dev, "clock %s not found\n", mtk_clks_source_name[i]); - return -EINVAL; + err = -EINVAL; + goto err_wed_exit; } eth->clks[i] = NULL; } @@ -4083,7 +4087,7 @@ static int mtk_probe(struct platform_device *pdev) err = mtk_hw_init(eth); if (err) - return err; + goto err_wed_exit; eth->hwlro = MTK_HAS_CAPS(eth->soc->caps, MTK_HWLRO); @@ -4179,6 +4183,8 @@ err_free_dev: mtk_free_dev(eth); err_deinit_hw: mtk_hw_deinit(eth); +err_wed_exit: + mtk_wed_exit(); return err; } @@ -4198,6 +4204,7 @@ static int mtk_remove(struct platform_device *pdev) phylink_disconnect_phy(mac->phylink); } + mtk_wed_exit(); mtk_hw_deinit(eth); netif_napi_del(ð->tx_napi); -- cgit From 9d4f20a476ca57e4c9246eb1fa2a61bea2354720 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 17 Oct 2022 11:51:55 +0800 Subject: net: ethernet: mtk_eth_wed: add missing put_device() in mtk_wed_add_hw() After calling get_device() in mtk_wed_add_hw(), in error path, put_device() needs be called. Fixes: 804775dfc288 ("net: ethernet: mtk_eth_soc: add support for Wireless Ethernet Dispatch (WED)") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_wed.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 099b6e0df619..09bbd05bd83c 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1077,11 +1077,11 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, get_device(&pdev->dev); irq = platform_get_irq(pdev, 0); if (irq < 0) - return; + goto err_put_device; regs = syscon_regmap_lookup_by_phandle(np, NULL); if (IS_ERR(regs)) - return; + goto err_put_device; rcu_assign_pointer(mtk_soc_wed_ops, &wed_ops); @@ -1124,8 +1124,14 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, hw_list[index] = hw; + mutex_unlock(&hw_lock); + + return; + unlock: mutex_unlock(&hw_lock); +err_put_device: + put_device(&pdev->dev); } void mtk_wed_exit(void) -- cgit From e0bb4659e235770e6f53b3692e958591f49448f5 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 17 Oct 2022 11:51:56 +0800 Subject: net: ethernet: mtk_eth_wed: add missing of_node_put() The device_node pointer returned by of_parse_phandle() with refcount incremented, when finish using it, the refcount need be decreased. Fixes: 804775dfc288 ("net: ethernet: mtk_eth_soc: add support for Wireless Ethernet Dispatch (WED)") Signed-off-by: Yang Yingliang Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_wed.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 09bbd05bd83c..65e01bf4b4d2 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1072,7 +1072,7 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, pdev = of_find_device_by_node(np); if (!pdev) - return; + goto err_of_node_put; get_device(&pdev->dev); irq = platform_get_irq(pdev, 0); @@ -1132,6 +1132,8 @@ unlock: mutex_unlock(&hw_lock); err_put_device: put_device(&pdev->dev); +err_of_node_put: + of_node_put(np); } void mtk_wed_exit(void) @@ -1152,6 +1154,7 @@ void mtk_wed_exit(void) hw_list[i] = NULL; debugfs_remove(hw->debugfs_dir); put_device(hw->dev); + of_node_put(hw->node); kfree(hw); } } -- cgit From 402fe7a5728789f3a3998d2823b7a110f4cd924e Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Mon, 17 Oct 2022 14:49:20 +0800 Subject: net: ethernet: mediatek: ppe: Remove the unused function mtk_foe_entry_usable() The function mtk_foe_entry_usable() is defined in the mtk_ppe.c file, but not called elsewhere, so delete this unused function. drivers/net/ethernet/mediatek/mtk_ppe.c:400:20: warning: unused function 'mtk_foe_entry_usable'. Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=2409 Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_ppe.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index ae00e572390d..2d8ca99f2467 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -397,12 +397,6 @@ int mtk_foe_entry_set_wdma(struct mtk_eth *eth, struct mtk_foe_entry *entry, return 0; } -static inline bool mtk_foe_entry_usable(struct mtk_foe_entry *entry) -{ - return !(entry->ib1 & MTK_FOE_IB1_STATIC) && - FIELD_GET(MTK_FOE_IB1_STATE, entry->ib1) != MTK_FOE_STATE_BIND; -} - static bool mtk_flow_entry_match(struct mtk_eth *eth, struct mtk_flow_entry *entry, struct mtk_foe_entry *data) -- cgit From 17cc1ee6e83b16989118237294327bd0dd12b1a4 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 13 Oct 2022 17:16:10 +0900 Subject: ata: ahci_st: Fix compilation warning If CONFIG_OF is disabled and the ahci_st driver is builtin (or CONFIG_MODULES is disabled), then using the macro of_match_ptr() results in the st_ahci_match variable being unused, which generates a compilation warning and a compilation error if CONFIG_WERROR is enabled. Fix this by directly assigning st_ahci_match to .of_match_table in the st_ahci_driver platform driver definition. Reported-by: kernel test robot Signed-off-by: Damien Le Moal Acked-by: Arnd Bergmann --- drivers/ata/ahci_st.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c index 5a2cac60a29a..8607b68eee53 100644 --- a/drivers/ata/ahci_st.c +++ b/drivers/ata/ahci_st.c @@ -236,7 +236,7 @@ static struct platform_driver st_ahci_driver = { .driver = { .name = DRV_NAME, .pm = &st_ahci_pm_ops, - .of_match_table = of_match_ptr(st_ahci_match), + .of_match_table = st_ahci_match, }, .probe = st_ahci_probe, .remove = ata_platform_remove_one, -- cgit From 79a818b5087393d5a4cb356d4545d02f55bf1a2f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 17 Oct 2022 08:08:05 -1000 Subject: blkcg: Update MAINTAINERS entry Josef wrote iolatency and iocost is missing from the files list. Let's add Josef as a maintainer and add blk-iocost.c to the files list. Signed-off-by: Tejun Heo Acked-by: Jens Axboe --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 0dc4a769216b..4a5ce3863deb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5256,6 +5256,7 @@ F: tools/testing/selftests/cgroup/ CONTROL GROUP - BLOCK IO CONTROLLER (BLKIO) M: Tejun Heo +M: Josef Bacik M: Jens Axboe L: cgroups@vger.kernel.org L: linux-block@vger.kernel.org @@ -5263,6 +5264,7 @@ T: git git://git.kernel.dk/linux-block F: Documentation/admin-guide/cgroup-v1/blkio-controller.rst F: block/bfq-cgroup.c F: block/blk-cgroup.c +F: block/blk-iocost.c F: block/blk-iolatency.c F: block/blk-throttle.c F: include/linux/blk-cgroup.h -- cgit From 0ffac4727eec1879305c1bda07c0195197937bb2 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 14 Oct 2022 10:38:15 +0900 Subject: ata: sata_rcar: Fix compilation warning When compiling with clang and W=1, the following warning is generated: drivers/ata/sata_rcar.c:878:15: error: cast to smaller integer type 'enum sata_rcar_type' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast] priv->type = (enum sata_rcar_type)of_device_get_match_data(dev); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix this by using a cast to unsigned long to match the "void *" type size returned by of_device_get_match_data(). Signed-off-by: Damien Le Moal Reviewed-by: Geert Uytterhoeven Acked-by: Arnd Bergmann Reviewed-by: Sergey Shtylyov --- drivers/ata/sata_rcar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 590ebea99601..0195eb29f6c2 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -875,7 +875,7 @@ static int sata_rcar_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - priv->type = (enum sata_rcar_type)of_device_get_match_data(dev); + priv->type = (unsigned long)of_device_get_match_data(dev); pm_runtime_enable(dev); ret = pm_runtime_get_sync(dev); -- cgit From 7d7b0c85127cbac45e6c4e0ae0647ace17cadfaf Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 14 Oct 2022 10:42:57 +0900 Subject: ata: ahci_brcm: Fix compilation warning When compiling with clang and W=1, the following warning is generated: drivers/ata/ahci_brcm.c:451:18: error: cast to smaller integer type 'enum brcm_ahci_version' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast] priv->version = (enum brcm_ahci_version)of_id->data; ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix this by using a cast to unsigned long to match the "void *" type size of of_id->data. Signed-off-by: Damien Le Moal Acked-by: Arnd Bergmann Acked-by: Florian Fainelli --- drivers/ata/ahci_brcm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index f61795c546cf..6f216eb25610 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -448,7 +448,7 @@ static int brcm_ahci_probe(struct platform_device *pdev) if (!of_id) return -ENODEV; - priv->version = (enum brcm_ahci_version)of_id->data; + priv->version = (unsigned long)of_id->data; priv->dev = dev; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "top-ctrl"); -- cgit From e8fbdf1855f7f31a8f37df60d7be44d8aabe6288 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 14 Oct 2022 10:45:58 +0900 Subject: ata: ahci_xgene: Fix compilation warning When compiling with clang and W=1, the following warning is generated: drivers/ata/ahci_xgene.c:788:14: error: cast to smaller integer type 'enum xgene_ahci_version' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast] version = (enum xgene_ahci_version) of_devid->data; ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix this by using a cast to unsigned long to match the "void *" type size of of_devid->data. Signed-off-by: Damien Le Moal Acked-by: Arnd Bergmann --- drivers/ata/ahci_xgene.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index 7bb5db17f864..1e08704d5117 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -785,7 +785,7 @@ static int xgene_ahci_probe(struct platform_device *pdev) of_devid = of_match_device(xgene_ahci_of_match, dev); if (of_devid) { if (of_devid->data) - version = (enum xgene_ahci_version) of_devid->data; + version = (unsigned long) of_devid->data; } #ifdef CONFIG_ACPI else { -- cgit From 26d9f48d9981205a7e229e21e183dbf1f13de83e Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 14 Oct 2022 10:48:16 +0900 Subject: ata: ahci_imx: Fix compilation warning When compiling with clang and W=1, the following warning is generated: drivers/ata/ahci_imx.c:1070:18: error: cast to smaller integer type 'enum ahci_imx_type' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast] imxpriv->type = (enum ahci_imx_type)of_id->data; ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix this by using a cast to unsigned long to match the "void *" type size of of_id->data. Signed-off-by: Damien Le Moal Acked-by: Arnd Bergmann --- drivers/ata/ahci_imx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index 632caa301458..a950767f7948 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -1067,7 +1067,7 @@ static int imx_ahci_probe(struct platform_device *pdev) imxpriv->ahci_pdev = pdev; imxpriv->no_device = false; imxpriv->first_time = true; - imxpriv->type = (enum ahci_imx_type)of_id->data; + imxpriv->type = (unsigned long)of_id->data; imxpriv->sata_clk = devm_clk_get(dev, "sata"); if (IS_ERR(imxpriv->sata_clk)) { -- cgit From 2ce3a0bf2010b16c78b78cc35a97fa913f1be0ca Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Fri, 14 Oct 2022 11:03:49 +0900 Subject: ata: ahci_qoriq: Fix compilation warning When compiling with clang and W=1, the following warning is generated: drivers/ata/ahci_qoriq.c:283:22: error: cast to smaller integer type 'enum ahci_qoriq_type' from 'const void *' [-Werror,-Wvoid-pointer-to-enum-cast] qoriq_priv->type = (enum ahci_qoriq_type)of_id->data; ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix this by using a cast to unsigned long to match the "void *" type size of of_id->data. Signed-off-by: Damien Le Moal Acked-by: Arnd Bergmann --- drivers/ata/ahci_qoriq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c index 6cd61842ad48..9cf9bf36a874 100644 --- a/drivers/ata/ahci_qoriq.c +++ b/drivers/ata/ahci_qoriq.c @@ -280,7 +280,7 @@ static int ahci_qoriq_probe(struct platform_device *pdev) return -ENOMEM; if (of_id) - qoriq_priv->type = (enum ahci_qoriq_type)of_id->data; + qoriq_priv->type = (unsigned long)of_id->data; else qoriq_priv->type = (enum ahci_qoriq_type)acpi_id->driver_data; -- cgit From 69421bf98482d089e50799f45e48b25ce4a8d154 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 14 Oct 2022 11:26:25 -0700 Subject: udp: Update reuse->has_conns under reuseport_lock. When we call connect() for a UDP socket in a reuseport group, we have to update sk->sk_reuseport_cb->has_conns to 1. Otherwise, the kernel could select a unconnected socket wrongly for packets sent to the connected socket. However, the current way to set has_conns is illegal and possible to trigger that problem. reuseport_has_conns() changes has_conns under rcu_read_lock(), which upgrades the RCU reader to the updater. Then, it must do the update under the updater's lock, reuseport_lock, but it doesn't for now. For this reason, there is a race below where we fail to set has_conns resulting in the wrong socket selection. To avoid the race, let's split the reader and updater with proper locking. cpu1 cpu2 +----+ +----+ __ip[46]_datagram_connect() reuseport_grow() . . |- reuseport_has_conns(sk, true) |- more_reuse = __reuseport_alloc(more_socks_size) | . | | |- rcu_read_lock() | |- reuse = rcu_dereference(sk->sk_reuseport_cb) | | | | | /* reuse->has_conns == 0 here */ | | |- more_reuse->has_conns = reuse->has_conns | |- reuse->has_conns = 1 | /* more_reuse->has_conns SHOULD BE 1 HERE */ | | | | | |- rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, | | | more_reuse) | `- rcu_read_unlock() `- kfree_rcu(reuse, rcu) | |- sk->sk_state = TCP_ESTABLISHED Note the likely(reuse) in reuseport_has_conns_set() is always true, but we put the test there for ease of review. [0] For the record, usually, sk_reuseport_cb is changed under lock_sock(). The only exception is reuseport_grow() & TCP reqsk migration case. 1) shutdown() TCP listener, which is moved into the latter part of reuse->socks[] to migrate reqsk. 2) New listen() overflows reuse->socks[] and call reuseport_grow(). 3) reuse->max_socks overflows u16 with the new listener. 4) reuseport_grow() pops the old shutdown()ed listener from the array and update its sk->sk_reuseport_cb as NULL without lock_sock(). shutdown()ed TCP sk->sk_reuseport_cb can be changed without lock_sock(), but, reuseport_has_conns_set() is called only for UDP under lock_sock(), so likely(reuse) never be false in reuseport_has_conns_set(). [0]: https://lore.kernel.org/netdev/CANn89iLja=eQHbsM_Ta2sQF0tOGU8vAGrh_izRuuHjuO1ouUag@mail.gmail.com/ Fixes: acdcecc61285 ("udp: correct reuseport selection with connected sockets") Signed-off-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20221014182625.89913-1-kuniyu@amazon.com Signed-off-by: Paolo Abeni --- include/net/sock_reuseport.h | 11 +++++------ net/core/sock_reuseport.c | 16 ++++++++++++++++ net/ipv4/datagram.c | 2 +- net/ipv4/udp.c | 2 +- net/ipv6/datagram.c | 2 +- net/ipv6/udp.c | 2 +- 6 files changed, 25 insertions(+), 10 deletions(-) diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 473b0b0fa4ab..efc9085c6892 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk, extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); -static inline bool reuseport_has_conns(struct sock *sk, bool set) +static inline bool reuseport_has_conns(struct sock *sk) { struct sock_reuseport *reuse; bool ret = false; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); - if (reuse) { - if (set) - reuse->has_conns = 1; - ret = reuse->has_conns; - } + if (reuse && reuse->has_conns) + ret = true; rcu_read_unlock(); return ret; } +void reuseport_has_conns_set(struct sock *sk); + #endif /* _SOCK_REUSEPORT_H */ diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 5daa1fa54249..fb90e1e00773 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -21,6 +21,22 @@ static DEFINE_IDA(reuseport_ida); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany); +void reuseport_has_conns_set(struct sock *sk) +{ + struct sock_reuseport *reuse; + + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return; + + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (likely(reuse)) + reuse->has_conns = 1; + spin_unlock_bh(&reuseport_lock); +} +EXPORT_SYMBOL(reuseport_has_conns_set); + static int reuseport_sock_index(struct sock *sk, const struct sock_reuseport *reuse, bool closed) diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 405a8c2aea64..5e66add7befa 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); inet->inet_id = prandom_u32(); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8126f67d18b3..752b72892a44 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index df665d4e8f0f..5ecb56522f9d 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -256,7 +256,7 @@ ipv4_connected: goto out; } - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8d09f0ea5b8c..129ec5a9b0eb 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -195,7 +195,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; -- cgit From 1ca695207ed2271ecbf8ee6c641970f621c157cc Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 17 Oct 2022 16:03:31 +0800 Subject: ip6mr: fix UAF issue in ip6mr_sk_done() when addrconf_init_net() failed If the initialization fails in calling addrconf_init_net(), devconf_all is the pointer that has been released. Then ip6mr_sk_done() is called to release the net, accessing devconf->mc_forwarding directly causes invalid pointer access. The process is as follows: setup_net() ops_init() addrconf_init_net() all = kmemdup(...) ---> alloc "all" ... net->ipv6.devconf_all = all; __addrconf_sysctl_register() ---> failed ... kfree(all); ---> ipv6.devconf_all invalid ... ops_exit_list() ... ip6mr_sk_done() devconf = net->ipv6.devconf_all; //devconf is invalid pointer if (!devconf || !atomic_read(&devconf->mc_forwarding)) The following is the Call Trace information: BUG: KASAN: use-after-free in ip6mr_sk_done+0x112/0x3a0 Read of size 4 at addr ffff888075508e88 by task ip/14554 Call Trace: dump_stack_lvl+0x8e/0xd1 print_report+0x155/0x454 kasan_report+0xba/0x1f0 kasan_check_range+0x35/0x1b0 ip6mr_sk_done+0x112/0x3a0 rawv6_close+0x48/0x70 inet_release+0x109/0x230 inet6_release+0x4c/0x70 sock_release+0x87/0x1b0 igmp6_net_exit+0x6b/0x170 ops_exit_list+0xb0/0x170 setup_net+0x7ac/0xbd0 copy_net_ns+0x2e6/0x6b0 create_new_namespaces+0x382/0xa50 unshare_nsproxy_namespaces+0xa6/0x1c0 ksys_unshare+0x3a4/0x7e0 __x64_sys_unshare+0x2d/0x40 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f7963322547 Allocated by task 14554: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 __kasan_kmalloc+0xa1/0xb0 __kmalloc_node_track_caller+0x4a/0xb0 kmemdup+0x28/0x60 addrconf_init_net+0x1be/0x840 ops_init+0xa5/0x410 setup_net+0x5aa/0xbd0 copy_net_ns+0x2e6/0x6b0 create_new_namespaces+0x382/0xa50 unshare_nsproxy_namespaces+0xa6/0x1c0 ksys_unshare+0x3a4/0x7e0 __x64_sys_unshare+0x2d/0x40 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Freed by task 14554: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 kasan_save_free_info+0x2a/0x40 ____kasan_slab_free+0x155/0x1b0 slab_free_freelist_hook+0x11b/0x220 __kmem_cache_free+0xa4/0x360 addrconf_init_net+0x623/0x840 ops_init+0xa5/0x410 setup_net+0x5aa/0xbd0 copy_net_ns+0x2e6/0x6b0 create_new_namespaces+0x382/0xa50 unshare_nsproxy_namespaces+0xa6/0x1c0 ksys_unshare+0x3a4/0x7e0 __x64_sys_unshare+0x2d/0x40 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Fixes: 7d9b1b578d67 ("ip6mr: fix use-after-free in ip6mr_sk_done()") Signed-off-by: Zhengchao Shao Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20221017080331.16878-1-shaozhengchao@huawei.com Signed-off-by: Paolo Abeni --- net/ipv6/addrconf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 10ce86bf228e..d5967cba5b56 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -7214,9 +7214,11 @@ err_reg_dflt: __addrconf_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(dflt); + net->ipv6.devconf_dflt = NULL; #endif err_alloc_dflt: kfree(all); + net->ipv6.devconf_all = NULL; err_alloc_all: kfree(net->ipv6.inet6_addr_lst); err_alloc_addr: -- cgit From 141b3523e9be6f15577acf4bbc3bc1f82d81d6d1 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Tue, 18 Oct 2022 10:06:45 -0400 Subject: dm bufio: use the acquire memory barrier when testing for B_READING The function test_bit doesn't provide any memory barrier. It may be possible that the read requests that follow test_bit(B_READING, &b->state) are reordered before the test, reading invalid data that existed before B_READING was cleared. Fix this bug by changing test_bit to test_bit_acquire. This is particularly important on arches with weak(er) memory ordering (e.g. arm64). Depends-On: 8238b4579866 ("wait_on_bit: add an acquire memory barrier") Depends-On: d6ffe6067a54 ("provide arch_test_bit_acquire for architectures that define test_bit") Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-bufio.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 09c7ed2650ca..9c5ef818ca36 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -795,7 +795,8 @@ static void __make_buffer_clean(struct dm_buffer *b) { BUG_ON(b->hold_count); - if (!b->state) /* fast case */ + /* smp_load_acquire() pairs with read_endio()'s smp_mb__before_atomic() */ + if (!smp_load_acquire(&b->state)) /* fast case */ return; wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); @@ -816,7 +817,7 @@ static struct dm_buffer *__get_unclaimed_buffer(struct dm_bufio_client *c) BUG_ON(test_bit(B_DIRTY, &b->state)); if (static_branch_unlikely(&no_sleep_enabled) && c->no_sleep && - unlikely(test_bit(B_READING, &b->state))) + unlikely(test_bit_acquire(B_READING, &b->state))) continue; if (!b->hold_count) { @@ -1058,7 +1059,7 @@ found_buffer: * If the user called both dm_bufio_prefetch and dm_bufio_get on * the same buffer, it would deadlock if we waited. */ - if (nf == NF_GET && unlikely(test_bit(B_READING, &b->state))) + if (nf == NF_GET && unlikely(test_bit_acquire(B_READING, &b->state))) return NULL; b->hold_count++; @@ -1218,7 +1219,7 @@ void dm_bufio_release(struct dm_buffer *b) * invalid buffer. */ if ((b->read_error || b->write_error) && - !test_bit(B_READING, &b->state) && + !test_bit_acquire(B_READING, &b->state) && !test_bit(B_WRITING, &b->state) && !test_bit(B_DIRTY, &b->state)) { __unlink_buffer(b); @@ -1479,7 +1480,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_release_move); static void forget_buffer_locked(struct dm_buffer *b) { - if (likely(!b->hold_count) && likely(!b->state)) { + if (likely(!b->hold_count) && likely(!smp_load_acquire(&b->state))) { __unlink_buffer(b); __free_buffer_wake(b); } @@ -1639,7 +1640,7 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp) { if (!(gfp & __GFP_FS) || (static_branch_unlikely(&no_sleep_enabled) && b->c->no_sleep)) { - if (test_bit(B_READING, &b->state) || + if (test_bit_acquire(B_READING, &b->state) || test_bit(B_WRITING, &b->state) || test_bit(B_DIRTY, &b->state)) return false; -- cgit From 43e6c111824c75940a586cd7d3fe6a5ff1d5104f Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 24 Aug 2022 07:25:57 -0400 Subject: dm: change from DMWARN to DMERR or DMCRIT for fatal errors Change DMWARN to DMERR in cases when there is an unrecoverable error. Change DMWARN to DMCRIT when handling of a case is unimplemented. Signed-off-by: Mikulas Patocka Signed-off-by: Mike Snitzer --- drivers/md/dm-ioctl.c | 78 +++++++++++++++++++++++++-------------------------- drivers/md/dm-rq.c | 4 +-- drivers/md/dm-stats.c | 2 +- drivers/md/dm-table.c | 78 +++++++++++++++++++++++++-------------------------- drivers/md/dm.c | 8 +++--- 5 files changed, 85 insertions(+), 85 deletions(-) diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 98976aaa9db9..6b3f867d0b70 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -434,10 +434,10 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, hc = __get_name_cell(new); if (hc) { - DMWARN("Unable to change %s on mapped device %s to one that " - "already exists: %s", - change_uuid ? "uuid" : "name", - param->name, new); + DMERR("Unable to change %s on mapped device %s to one that " + "already exists: %s", + change_uuid ? "uuid" : "name", + param->name, new); dm_put(hc->md); up_write(&_hash_lock); kfree(new_data); @@ -449,8 +449,8 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, */ hc = __get_name_cell(param->name); if (!hc) { - DMWARN("Unable to rename non-existent device, %s to %s%s", - param->name, change_uuid ? "uuid " : "", new); + DMERR("Unable to rename non-existent device, %s to %s%s", + param->name, change_uuid ? "uuid " : "", new); up_write(&_hash_lock); kfree(new_data); return ERR_PTR(-ENXIO); @@ -460,9 +460,9 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, * Does this device already have a uuid? */ if (change_uuid && hc->uuid) { - DMWARN("Unable to change uuid of mapped device %s to %s " - "because uuid is already set to %s", - param->name, new, hc->uuid); + DMERR("Unable to change uuid of mapped device %s to %s " + "because uuid is already set to %s", + param->name, new, hc->uuid); dm_put(hc->md); up_write(&_hash_lock); kfree(new_data); @@ -750,7 +750,7 @@ static int get_target_version(struct file *filp, struct dm_ioctl *param, size_t static int check_name(const char *name) { if (strchr(name, '/')) { - DMWARN("invalid device name"); + DMERR("invalid device name"); return -EINVAL; } @@ -773,7 +773,7 @@ static struct dm_table *dm_get_inactive_table(struct mapped_device *md, int *src down_read(&_hash_lock); hc = dm_get_mdptr(md); if (!hc || hc->md != md) { - DMWARN("device has been removed from the dev hash table."); + DMERR("device has been removed from the dev hash table."); goto out; } @@ -1026,7 +1026,7 @@ static int dev_rename(struct file *filp, struct dm_ioctl *param, size_t param_si if (new_data < param->data || invalid_str(new_data, (void *) param + param_size) || !*new_data || strlen(new_data) > (change_uuid ? DM_UUID_LEN - 1 : DM_NAME_LEN - 1)) { - DMWARN("Invalid new mapped device name or uuid string supplied."); + DMERR("Invalid new mapped device name or uuid string supplied."); return -EINVAL; } @@ -1061,7 +1061,7 @@ static int dev_set_geometry(struct file *filp, struct dm_ioctl *param, size_t pa if (geostr < param->data || invalid_str(geostr, (void *) param + param_size)) { - DMWARN("Invalid geometry supplied."); + DMERR("Invalid geometry supplied."); goto out; } @@ -1069,13 +1069,13 @@ static int dev_set_geometry(struct file *filp, struct dm_ioctl *param, size_t pa indata + 1, indata + 2, indata + 3, &dummy); if (x != 4) { - DMWARN("Unable to interpret geometry settings."); + DMERR("Unable to interpret geometry settings."); goto out; } if (indata[0] > 65535 || indata[1] > 255 || indata[2] > 255 || indata[3] > ULONG_MAX) { - DMWARN("Geometry exceeds range limits."); + DMERR("Geometry exceeds range limits."); goto out; } @@ -1387,7 +1387,7 @@ static int populate_table(struct dm_table *table, char *target_params; if (!param->target_count) { - DMWARN("populate_table: no targets specified"); + DMERR("populate_table: no targets specified"); return -EINVAL; } @@ -1395,7 +1395,7 @@ static int populate_table(struct dm_table *table, r = next_target(spec, next, end, &spec, &target_params); if (r) { - DMWARN("unable to find target"); + DMERR("unable to find target"); return r; } @@ -1404,7 +1404,7 @@ static int populate_table(struct dm_table *table, (sector_t) spec->length, target_params); if (r) { - DMWARN("error adding target to table"); + DMERR("error adding target to table"); return r; } @@ -1451,8 +1451,8 @@ static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_si if (immutable_target_type && (immutable_target_type != dm_table_get_immutable_target_type(t)) && !dm_table_get_wildcard_target(t)) { - DMWARN("can't replace immutable target type %s", - immutable_target_type->name); + DMERR("can't replace immutable target type %s", + immutable_target_type->name); r = -EINVAL; goto err_unlock_md_type; } @@ -1461,12 +1461,12 @@ static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_si /* setup md->queue to reflect md's type (may block) */ r = dm_setup_md_queue(md, t); if (r) { - DMWARN("unable to set up device queue for new table."); + DMERR("unable to set up device queue for new table."); goto err_unlock_md_type; } } else if (!is_valid_type(dm_get_md_type(md), dm_table_get_type(t))) { - DMWARN("can't change device type (old=%u vs new=%u) after initial table load.", - dm_get_md_type(md), dm_table_get_type(t)); + DMERR("can't change device type (old=%u vs new=%u) after initial table load.", + dm_get_md_type(md), dm_table_get_type(t)); r = -EINVAL; goto err_unlock_md_type; } @@ -1477,7 +1477,7 @@ static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_si down_write(&_hash_lock); hc = dm_get_mdptr(md); if (!hc || hc->md != md) { - DMWARN("device has been removed from the dev hash table."); + DMERR("device has been removed from the dev hash table."); up_write(&_hash_lock); r = -ENXIO; goto err_destroy_table; @@ -1686,19 +1686,19 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para if (tmsg < (struct dm_target_msg *) param->data || invalid_str(tmsg->message, (void *) param + param_size)) { - DMWARN("Invalid target message parameters."); + DMERR("Invalid target message parameters."); r = -EINVAL; goto out; } r = dm_split_args(&argc, &argv, tmsg->message); if (r) { - DMWARN("Failed to split target message parameters"); + DMERR("Failed to split target message parameters"); goto out; } if (!argc) { - DMWARN("Empty message received."); + DMERR("Empty message received."); r = -EINVAL; goto out_argv; } @@ -1718,12 +1718,12 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para ti = dm_table_find_target(table, tmsg->sector); if (!ti) { - DMWARN("Target message sector outside device."); + DMERR("Target message sector outside device."); r = -EINVAL; } else if (ti->type->message) r = ti->type->message(ti, argc, argv, result, maxlen); else { - DMWARN("Target type does not support messages"); + DMERR("Target type does not support messages"); r = -EINVAL; } @@ -1814,11 +1814,11 @@ static int check_version(unsigned int cmd, struct dm_ioctl __user *user) if ((DM_VERSION_MAJOR != version[0]) || (DM_VERSION_MINOR < version[1])) { - DMWARN("ioctl interface mismatch: " - "kernel(%u.%u.%u), user(%u.%u.%u), cmd(%d)", - DM_VERSION_MAJOR, DM_VERSION_MINOR, - DM_VERSION_PATCHLEVEL, - version[0], version[1], version[2], cmd); + DMERR("ioctl interface mismatch: " + "kernel(%u.%u.%u), user(%u.%u.%u), cmd(%d)", + DM_VERSION_MAJOR, DM_VERSION_MINOR, + DM_VERSION_PATCHLEVEL, + version[0], version[1], version[2], cmd); r = -EINVAL; } @@ -1927,11 +1927,11 @@ static int validate_params(uint cmd, struct dm_ioctl *param) if (cmd == DM_DEV_CREATE_CMD) { if (!*param->name) { - DMWARN("name not supplied when creating device"); + DMERR("name not supplied when creating device"); return -EINVAL; } } else if (*param->uuid && *param->name) { - DMWARN("only supply one of name or uuid, cmd(%u)", cmd); + DMERR("only supply one of name or uuid, cmd(%u)", cmd); return -EINVAL; } @@ -1978,7 +1978,7 @@ static int ctl_ioctl(struct file *file, uint command, struct dm_ioctl __user *us fn = lookup_ioctl(cmd, &ioctl_flags); if (!fn) { - DMWARN("dm_ctl_ioctl: unknown command 0x%x", command); + DMERR("dm_ctl_ioctl: unknown command 0x%x", command); return -ENOTTY; } @@ -2203,7 +2203,7 @@ int __init dm_early_create(struct dm_ioctl *dmi, (sector_t) spec_array[i]->length, target_params_array[i]); if (r) { - DMWARN("error adding target to table"); + DMERR("error adding target to table"); goto err_destroy_table; } } @@ -2216,7 +2216,7 @@ int __init dm_early_create(struct dm_ioctl *dmi, /* setup md->queue to reflect md's type (may block) */ r = dm_setup_md_queue(md, t); if (r) { - DMWARN("unable to set up device queue for new table."); + DMERR("unable to set up device queue for new table."); goto err_destroy_table; } diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 3001b10a3fbf..a41209a43506 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -238,7 +238,7 @@ static void dm_done(struct request *clone, blk_status_t error, bool mapped) dm_requeue_original_request(tio, true); break; default: - DMWARN("unimplemented target endio return value: %d", r); + DMCRIT("unimplemented target endio return value: %d", r); BUG(); } } @@ -409,7 +409,7 @@ static int map_request(struct dm_rq_target_io *tio) dm_kill_unmapped_request(rq, BLK_STS_IOERR); break; default: - DMWARN("unimplemented target map return value: %d", r); + DMCRIT("unimplemented target map return value: %d", r); BUG(); } diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 8326f9fe0e91..f105a71915ab 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -1220,7 +1220,7 @@ int dm_stats_message(struct mapped_device *md, unsigned argc, char **argv, return 2; /* this wasn't a stats message */ if (r == -EINVAL) - DMWARN("Invalid parameters for message %s", argv[0]); + DMCRIT("Invalid parameters for message %s", argv[0]); return r; } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index d8034ff0cb24..078da18bb86d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -234,12 +234,12 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, return 0; if ((start >= dev_size) || (start + len > dev_size)) { - DMWARN("%s: %pg too small for target: " - "start=%llu, len=%llu, dev_size=%llu", - dm_device_name(ti->table->md), bdev, - (unsigned long long)start, - (unsigned long long)len, - (unsigned long long)dev_size); + DMERR("%s: %pg too small for target: " + "start=%llu, len=%llu, dev_size=%llu", + dm_device_name(ti->table->md), bdev, + (unsigned long long)start, + (unsigned long long)len, + (unsigned long long)dev_size); return 1; } @@ -251,10 +251,10 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, unsigned int zone_sectors = bdev_zone_sectors(bdev); if (start & (zone_sectors - 1)) { - DMWARN("%s: start=%llu not aligned to h/w zone size %u of %pg", - dm_device_name(ti->table->md), - (unsigned long long)start, - zone_sectors, bdev); + DMERR("%s: start=%llu not aligned to h/w zone size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)start, + zone_sectors, bdev); return 1; } @@ -268,10 +268,10 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * the sector range. */ if (len & (zone_sectors - 1)) { - DMWARN("%s: len=%llu not aligned to h/w zone size %u of %pg", - dm_device_name(ti->table->md), - (unsigned long long)len, - zone_sectors, bdev); + DMERR("%s: len=%llu not aligned to h/w zone size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)len, + zone_sectors, bdev); return 1; } } @@ -280,20 +280,20 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, return 0; if (start & (logical_block_size_sectors - 1)) { - DMWARN("%s: start=%llu not aligned to h/w " - "logical block size %u of %pg", - dm_device_name(ti->table->md), - (unsigned long long)start, - limits->logical_block_size, bdev); + DMERR("%s: start=%llu not aligned to h/w " + "logical block size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)start, + limits->logical_block_size, bdev); return 1; } if (len & (logical_block_size_sectors - 1)) { - DMWARN("%s: len=%llu not aligned to h/w " - "logical block size %u of %pg", - dm_device_name(ti->table->md), - (unsigned long long)len, - limits->logical_block_size, bdev); + DMERR("%s: len=%llu not aligned to h/w " + "logical block size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)len, + limits->logical_block_size, bdev); return 1; } @@ -434,8 +434,8 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d) } } if (!found) { - DMWARN("%s: device %s not in table devices list", - dm_device_name(ti->table->md), d->name); + DMERR("%s: device %s not in table devices list", + dm_device_name(ti->table->md), d->name); return; } if (refcount_dec_and_test(&dd->count)) { @@ -618,12 +618,12 @@ static int validate_hardware_logical_block_alignment(struct dm_table *t, } if (remaining) { - DMWARN("%s: table line %u (start sect %llu len %llu) " - "not aligned to h/w logical block size %u", - dm_device_name(t->md), i, - (unsigned long long) ti->begin, - (unsigned long long) ti->len, - limits->logical_block_size); + DMERR("%s: table line %u (start sect %llu len %llu) " + "not aligned to h/w logical block size %u", + dm_device_name(t->md), i, + (unsigned long long) ti->begin, + (unsigned long long) ti->len, + limits->logical_block_size); return -EINVAL; } @@ -1008,7 +1008,7 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device * struct dm_md_mempools *pools; if (unlikely(type == DM_TYPE_NONE)) { - DMWARN("no table type is set, can't allocate mempools"); + DMERR("no table type is set, can't allocate mempools"); return -EINVAL; } @@ -1112,7 +1112,7 @@ static bool integrity_profile_exists(struct gendisk *disk) * Get a disk whose integrity profile reflects the table's profile. * Returns NULL if integrity support was inconsistent or unavailable. */ -static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t) +static struct gendisk *dm_table_get_integrity_disk(struct dm_table *t) { struct list_head *devices = dm_table_get_devices(t); struct dm_dev_internal *dd = NULL; @@ -1185,10 +1185,10 @@ static int dm_table_register_integrity(struct dm_table *t) * profile the new profile should not conflict. */ if (blk_integrity_compare(dm_disk(md), template_disk) < 0) { - DMWARN("%s: conflict with existing integrity profile: " - "%s profile mismatch", - dm_device_name(t->md), - template_disk->disk_name); + DMERR("%s: conflict with existing integrity profile: " + "%s profile mismatch", + dm_device_name(t->md), + template_disk->disk_name); return 1; } @@ -1327,7 +1327,7 @@ static int dm_table_construct_crypto_profile(struct dm_table *t) if (t->md->queue && !blk_crypto_has_capabilities(profile, t->md->queue->crypto_profile)) { - DMWARN("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!"); + DMERR("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!"); dm_destroy_crypto_profile(profile); return -EINVAL; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 60549b65c799..7c35dea88ed1 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -864,7 +864,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo) sector_t sz = (sector_t)geo->cylinders * geo->heads * geo->sectors; if (geo->start > sz) { - DMWARN("Start sector is beyond the geometry limits."); + DMERR("Start sector is beyond the geometry limits."); return -EINVAL; } @@ -1149,7 +1149,7 @@ static void clone_endio(struct bio *bio) /* The target will handle the io */ return; default: - DMWARN("unimplemented target endio return value: %d", r); + DMCRIT("unimplemented target endio return value: %d", r); BUG(); } } @@ -1455,7 +1455,7 @@ static void __map_bio(struct bio *clone) dm_io_dec_pending(io, BLK_STS_DM_REQUEUE); break; default: - DMWARN("unimplemented target map return value: %d", r); + DMCRIT("unimplemented target map return value: %d", r); BUG(); } } @@ -2005,7 +2005,7 @@ static struct mapped_device *alloc_dev(int minor) md = kvzalloc_node(sizeof(*md), GFP_KERNEL, numa_node_id); if (!md) { - DMWARN("unable to allocate device, out of memory."); + DMERR("unable to allocate device, out of memory."); return NULL; } -- cgit From cea446630feab57f49d47abccf206e9725019cce Mon Sep 17 00:00:00 2001 From: Jilin Yuan Date: Tue, 30 Aug 2022 23:33:45 +0800 Subject: dm raid: delete the redundant word 'that' in comment Signed-off-by: Jilin Yuan Signed-off-by: Mike Snitzer --- drivers/md/dm-raid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index c640be453313..e448fd45a914 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2529,7 +2529,7 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) * of the "sync" directive. * * With reshaping capability added, we must ensure that - * that the "sync" directive is disallowed during the reshape. + * the "sync" directive is disallowed during the reshape. */ if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags)) continue; -- cgit From afd41fff9c73ccc3757e94ad727d2a9ac4d7f6cb Mon Sep 17 00:00:00 2001 From: Nathan Huckleberry Date: Tue, 30 Aug 2022 18:44:44 +0000 Subject: dm verity: enable WQ_HIGHPRI on verify_wq WQ_HIGHPRI increases throughput and decreases disk latency when using dm-verity. This is important in Android for camera startup speed. The following tests were run by doing 60 seconds of random reads using a dm-verity device backed by two ramdisks. Without WQ_HIGHPRI lat (usec): min=13, max=3947, avg=69.53, stdev=50.55 READ: bw=51.1MiB/s (53.6MB/s), 51.1MiB/s-51.1MiB/s (53.6MB/s-53.6MB/s) With WQ_HIGHPRI: lat (usec): min=13, max=7854, avg=31.15, stdev=30.42 READ: bw=116MiB/s (121MB/s), 116MiB/s-116MiB/s (121MB/s-121MB/s) Further testing was done by measuring how long it takes to open a camera on an Android device. Without WQ_HIGHPRI Total verity work queue wait times (ms): 880.960, 789.517, 898.852 With WQ_HIGHPRI: Total verity work queue wait times (ms): 528.824, 439.191, 433.300 The average time to open the camera is reduced by 350ms (or 40-50%). Signed-off-by: Nathan Huckleberry Signed-off-by: Mike Snitzer --- drivers/md/dm-verity-target.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 8a00cc42e498..ccf5b852fbf7 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1401,14 +1401,16 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) /* WQ_UNBOUND greatly improves performance when running on ramdisk */ wq_flags = WQ_MEM_RECLAIM | WQ_UNBOUND; - if (v->use_tasklet) { - /* - * Allow verify_wq to preempt softirq since verification in - * tasklet will fall-back to using it for error handling - * (or if the bufio cache doesn't have required hashes). - */ - wq_flags |= WQ_HIGHPRI; - } + /* + * Using WQ_HIGHPRI improves throughput and completion latency by + * reducing wait times when reading from a dm-verity device. + * + * Also as required for the "try_verify_in_tasklet" feature: WQ_HIGHPRI + * allows verify_wq to preempt softirq since verification in tasklet + * will fall-back to using it for error handling (or if the bufio cache + * doesn't have required hashes). + */ + wq_flags |= WQ_HIGHPRI; v->verify_wq = alloc_workqueue("kverityd", wq_flags, num_online_cpus()); if (!v->verify_wq) { ti->error = "Cannot allocate workqueue"; -- cgit From 96fccdce97ce647d5c7bf1db0d3159cc90774054 Mon Sep 17 00:00:00 2001 From: Jiangshan Yi Date: Mon, 5 Sep 2022 10:45:52 +0800 Subject: dm raid: fix typo in analyse_superblocks code comment Reported-by: k2ci Signed-off-by: Jiangshan Yi Signed-off-by: Mike Snitzer --- drivers/md/dm-raid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index e448fd45a914..54263679a7b1 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2590,7 +2590,7 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) /* * Adjust data_offset and new_data_offset on all disk members of @rs - * for out of place reshaping if requested by contructor + * for out of place reshaping if requested by constructor * * We need free space at the beginning of each raid disk for forward * and at the end for backward reshapes which userspace has to provide -- cgit From 48d1a964dca532698bc67ac71c04df7908815de1 Mon Sep 17 00:00:00 2001 From: Shaomin Deng Date: Sun, 4 Sep 2022 12:04:27 -0400 Subject: dm cache: delete the redundant word 'each' in comment Signed-off-by: Shaomin Deng Signed-off-by: Mike Snitzer --- drivers/md/dm-cache-policy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h index c05fc3436cef..06eb31af626f 100644 --- a/drivers/md/dm-cache-policy.h +++ b/drivers/md/dm-cache-policy.h @@ -166,7 +166,7 @@ struct dm_cache_policy_type { struct dm_cache_policy_type *real; /* - * Policies may store a hint for each each cache block. + * Policies may store a hint for each cache block. * Currently the size of this hint must be 0 or 4 bytes but we * expect to relax this in future. */ -- cgit From dc3efedf9f7b802d0817183020ed01cb0c120fe8 Mon Sep 17 00:00:00 2001 From: Milan Broz Date: Tue, 27 Sep 2022 20:42:26 +0200 Subject: dm verity: Add documentation for try_verify_in_tasklet option Add documentation that was missing from commit 5721d4e5a9cd ("dm verity: Add optional "try_verify_in_tasklet" feature"). Signed-off-by: Milan Broz Signed-off-by: Mike Snitzer --- Documentation/admin-guide/device-mapper/verity.rst | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/admin-guide/device-mapper/verity.rst b/Documentation/admin-guide/device-mapper/verity.rst index 1a6b91368e59..a65c1602cb23 100644 --- a/Documentation/admin-guide/device-mapper/verity.rst +++ b/Documentation/admin-guide/device-mapper/verity.rst @@ -141,6 +141,10 @@ root_hash_sig_key_desc also gain new certificates at run time if they are signed by a certificate already in the secondary trusted keyring. +try_verify_in_tasklet + If verity hashes are in cache, verify data blocks in kernel tasklet instead + of workqueue. This option can reduce IO latency. + Theory of operation =================== -- cgit From 99f4f5bcb975527508eb7a5e3e34bdb91d576746 Mon Sep 17 00:00:00 2001 From: Genjian Zhang Date: Thu, 29 Sep 2022 16:20:36 +0800 Subject: dm: remove unnecessary assignment statement in alloc_dev() Fixes: 74fe6ba923949 ("dm: convert to blk_alloc_disk/blk_cleanup_disk") Signed-off-by: Genjian Zhang Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7c35dea88ed1..95a1ee3d314e 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2065,7 +2065,6 @@ static struct mapped_device *alloc_dev(int minor) md->disk->minors = 1; md->disk->flags |= GENHD_FL_NO_PART; md->disk->fops = &dm_blk_dops; - md->disk->queue = md->queue; md->disk->private_data = md; sprintf(md->disk->disk_name, "dm-%d", minor); -- cgit From 5434ee8d28575b2e784bd5b4dbfc912e5da90759 Mon Sep 17 00:00:00 2001 From: Nikos Tsironis Date: Thu, 29 Sep 2022 17:11:48 +0300 Subject: dm clone: Fix typo in block_device format specifier Use %pg for printing the block device name, instead of %pd. Fixes: 385411ffba0c ("dm: stop using bdevname") Cc: stable@vger.kernel.org # v5.18+ Signed-off-by: Nikos Tsironis Signed-off-by: Mike Snitzer --- drivers/md/dm-clone-target.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 811b0a5379d0..2f1cc66d2641 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -2035,7 +2035,7 @@ static void disable_passdown_if_not_supported(struct clone *clone) reason = "max discard sectors smaller than a region"; if (reason) { - DMWARN("Destination device (%pd) %s: Disabling discard passdown.", + DMWARN("Destination device (%pg) %s: Disabling discard passdown.", dest_dev, reason); clear_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags); } -- cgit From ba077d683d45190afc993c1ce45bcdbfda741a40 Mon Sep 17 00:00:00 2001 From: Vikas Gupta Date: Mon, 17 Oct 2022 11:32:22 -0400 Subject: bnxt_en: fix memory leak in bnxt_nvm_test() Free the kzalloc'ed buffer before returning in the success path. Fixes: 5b6ff128fdf6 ("bnxt_en: implement callbacks for devlink selftests") Signed-off-by: Vikas Gupta Signed-off-by: Michael Chan Link: https://lore.kernel.org/r/1666020742-25834-1-git-send-email-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index a36803e79e92..8a6f788f6294 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -613,6 +613,7 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti static bool bnxt_nvm_test(struct bnxt *bp, struct netlink_ext_ack *extack) { + bool rc = false; u32 datalen; u16 index; u8 *buf; @@ -632,20 +633,20 @@ static bool bnxt_nvm_test(struct bnxt *bp, struct netlink_ext_ack *extack) if (bnxt_get_nvram_item(bp->dev, index, 0, datalen, buf)) { NL_SET_ERR_MSG_MOD(extack, "nvm test vpd read error"); - goto err; + goto done; } if (bnxt_flash_nvram(bp->dev, BNX_DIR_TYPE_VPD, BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE, 0, 0, buf, datalen)) { NL_SET_ERR_MSG_MOD(extack, "nvm test vpd write error"); - goto err; + goto done; } - return true; + rc = true; -err: +done: kfree(buf); - return false; + return rc; } static bool bnxt_dl_selftest_check(struct devlink *dl, unsigned int id, -- cgit From d8b57135fd9ffe9a5b445350a686442a531c5339 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 Oct 2022 16:59:28 +0000 Subject: net: hsr: avoid possible NULL deref in skb_clone() syzbot got a crash [1] in skb_clone(), caused by a bug in hsr_get_untagged_frame(). When/if create_stripped_skb_hsr() returns NULL, we must not attempt to call skb_clone(). While we are at it, replace a WARN_ONCE() by netdev_warn_once(). [1] general protection fault, probably for non-canonical address 0xdffffc000000000f: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000078-0x000000000000007f] CPU: 1 PID: 754 Comm: syz-executor.0 Not tainted 6.0.0-syzkaller-02734-g0326074ff465 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/22/2022 RIP: 0010:skb_clone+0x108/0x3c0 net/core/skbuff.c:1641 Code: 93 02 00 00 49 83 7c 24 28 00 0f 85 e9 00 00 00 e8 5d 4a 29 fa 4c 8d 75 7e 48 b8 00 00 00 00 00 fc ff df 4c 89 f2 48 c1 ea 03 <0f> b6 04 02 4c 89 f2 83 e2 07 38 d0 7f 08 84 c0 0f 85 9e 01 00 00 RSP: 0018:ffffc90003ccf4e0 EFLAGS: 00010207 RAX: dffffc0000000000 RBX: ffffc90003ccf5f8 RCX: ffffc9000c24b000 RDX: 000000000000000f RSI: ffffffff8751cb13 RDI: 0000000000000000 RBP: 0000000000000000 R08: 00000000000000f0 R09: 0000000000000140 R10: fffffbfff181d972 R11: 0000000000000000 R12: ffff888161fc3640 R13: 0000000000000a20 R14: 000000000000007e R15: ffffffff8dc5f620 FS: 00007feb621e4700(0000) GS:ffff8880b9b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007feb621e3ff8 CR3: 00000001643a9000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: hsr_get_untagged_frame+0x4e/0x610 net/hsr/hsr_forward.c:164 hsr_forward_do net/hsr/hsr_forward.c:461 [inline] hsr_forward_skb+0xcca/0x1d50 net/hsr/hsr_forward.c:623 hsr_handle_frame+0x588/0x7c0 net/hsr/hsr_slave.c:69 __netif_receive_skb_core+0x9fe/0x38f0 net/core/dev.c:5379 __netif_receive_skb_one_core+0xae/0x180 net/core/dev.c:5483 __netif_receive_skb+0x1f/0x1c0 net/core/dev.c:5599 netif_receive_skb_internal net/core/dev.c:5685 [inline] netif_receive_skb+0x12f/0x8d0 net/core/dev.c:5744 tun_rx_batched+0x4ab/0x7a0 drivers/net/tun.c:1544 tun_get_user+0x2686/0x3a00 drivers/net/tun.c:1995 tun_chr_write_iter+0xdb/0x200 drivers/net/tun.c:2025 call_write_iter include/linux/fs.h:2187 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x9e9/0xdd0 fs/read_write.c:584 ksys_write+0x127/0x250 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: f266a683a480 ("net/hsr: Better frame dispatch") Reported-by: syzbot Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20221017165928.2150130-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/hsr/hsr_forward.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 5bf357734b11..a50429a62f74 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -150,15 +150,15 @@ struct sk_buff *hsr_get_untagged_frame(struct hsr_frame_info *frame, struct hsr_port *port) { if (!frame->skb_std) { - if (frame->skb_hsr) { + if (frame->skb_hsr) frame->skb_std = create_stripped_skb_hsr(frame->skb_hsr, frame); - } else { - /* Unexpected */ - WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n", - __FILE__, __LINE__, port->dev->name); + else + netdev_warn_once(port->dev, + "Unexpected frame received in hsr_get_untagged_frame()\n"); + + if (!frame->skb_std) return NULL; - } } return skb_clone(frame->skb_std, GFP_ATOMIC); -- cgit From aa1d7e1267c12e07d979aa34c613716a89029db2 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Mon, 17 Oct 2022 16:31:23 -0700 Subject: ionic: catch NULL pointer issue on reconfig It's possible that the driver will dereference a qcq that doesn't exist when calling ionic_reconfigure_queues(), which causes a page fault BUG. If a reduction in the number of queues is followed by a different reconfig such as changing the ring size, the driver can hit a NULL pointer when trying to clean up non-existent queues. Fix this by checking to make sure both the qcqs array and qcq entry exists bofore trying to use and free the entry. Fixes: 101b40a0171f ("ionic: change queue count with no reset") Signed-off-by: Brett Creeley Signed-off-by: Shannon Nelson Link: https://lore.kernel.org/r/20221017233123.15869-1-snelson@pensando.io Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/pensando/ionic/ionic_lif.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 5d58fd99be3c..19d4848df17d 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2817,11 +2817,15 @@ err_out: * than the full array, but leave the qcq shells in place */ for (i = lif->nxqs; i < lif->ionic->ntxqs_per_lif; i++) { - lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; - ionic_qcq_free(lif, lif->txqcqs[i]); + if (lif->txqcqs && lif->txqcqs[i]) { + lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->txqcqs[i]); + } - lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; - ionic_qcq_free(lif, lif->rxqcqs[i]); + if (lif->rxqcqs && lif->rxqcqs[i]) { + lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->rxqcqs[i]); + } } if (err) -- cgit From 1fcc064b305a1aadeff0d4bff961094d27660acd Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Thu, 13 Oct 2022 16:37:47 +0200 Subject: netfilter: rpfilter/fib: Set ->flowic_uid correctly for user namespaces. Currently netfilter's rpfilter and fib modules implicitely initialise ->flowic_uid with 0. This is normally the root UID. However, this isn't the case in user namespaces, where user ID 0 is mapped to a different kernel UID. By initialising ->flowic_uid with sock_net_uid(), we get the root UID of the user namespace, thus keeping the same behaviour whether or not we're running in a user namepspace. Note, this is similar to commit 8bcfd0925ef1 ("ipv4: add missing initialization for flowi4_uid"), which fixed the rp_filter sysctl. Fixes: 622ec2c9d524 ("net: core: add UID to flows, rules, and routes") Signed-off-by: Guillaume Nault Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/ipt_rpfilter.c | 1 + net/ipv4/netfilter/nft_fib_ipv4.c | 1 + net/ipv6/netfilter/ip6t_rpfilter.c | 1 + net/ipv6/netfilter/nft_fib_ipv6.c | 2 ++ 4 files changed, 5 insertions(+) diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index ff85db52b2e5..ded5bef02f77 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.flowi4_tos = iph->tos & IPTOS_RT_MASK; flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); + flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert; } diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index e886147eed11..fc65d69f23e1 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -65,6 +65,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, struct flowi4 fl4 = { .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_iif = LOOPBACK_IFINDEX, + .flowi4_uid = sock_net_uid(nft_net(pkt), NULL), }; const struct net_device *oif; const struct net_device *found; diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 69d86b040a6a..a01d9b842bd0 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -40,6 +40,7 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, .flowi6_l3mdev = l3mdev_master_ifindex_rcu(dev), .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, .flowi6_proto = iph->nexthdr, + .flowi6_uid = sock_net_uid(net, NULL), .daddr = iph->saddr, }; int lookup_flags; diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 91faac610e03..36dc14b34388 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -66,6 +66,7 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv, struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_proto = pkt->tprot, + .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), }; u32 ret = 0; @@ -163,6 +164,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_proto = pkt->tprot, + .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), }; struct rt6_info *rt; int lookup_flags; -- cgit From 96df8360dbb435cc69f7c3c8db44bf8b1c24cd7b Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 17 Oct 2022 14:12:58 +0200 Subject: netfilter: nf_tables: relax NFTA_SET_ELEM_KEY_END set flags requirements Otherwise EINVAL is bogusly reported to userspace when deleting a set element. NFTA_SET_ELEM_KEY_END does not need to be set in case of: - insertion: if not present, start key is used as end key. - deletion: only start key needs to be specified, end key is ignored. Hence, relax the sanity check. Fixes: 88cccd908d51 ("netfilter: nf_tables: NFTA_SET_ELEM_KEY_END requires concat and interval flags") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a0653a8dfa82..58d9cbc9ccdc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5865,8 +5865,9 @@ static bool nft_setelem_valid_key_end(const struct nft_set *set, (NFT_SET_CONCAT | NFT_SET_INTERVAL)) { if (flags & NFT_SET_ELEM_INTERVAL_END) return false; - if (!nla[NFTA_SET_ELEM_KEY_END] && - !(flags & NFT_SET_ELEM_CATCHALL)) + + if (nla[NFTA_SET_ELEM_KEY_END] && + flags & NFT_SET_ELEM_CATCHALL) return false; } else { if (nla[NFTA_SET_ELEM_KEY_END]) -- cgit From 7b55c2ed2ba061b65fc51d7a18d37e017085997f Mon Sep 17 00:00:00 2001 From: Manank Patel Date: Tue, 18 Oct 2022 11:03:18 +0530 Subject: ethernet: marvell: octeontx2 Fix resource not freed after malloc fix rxsc and txsc not getting freed before going out of scope Fixes: c54ffc73601c ("octeontx2-pf: mcs: Introduce MACSEC hardware offloading") Signed-off-by: Manank Patel Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 9809f551fc2e..9ec5f38d38a8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -815,6 +815,7 @@ free_flowid: cn10k_mcs_free_rsrc(pfvf, MCS_TX, MCS_RSRC_TYPE_FLOWID, txsc->hw_flow_id, false); fail: + kfree(txsc); return ERR_PTR(ret); } @@ -870,6 +871,7 @@ free_flowid: cn10k_mcs_free_rsrc(pfvf, MCS_RX, MCS_RSRC_TYPE_FLOWID, rxsc->hw_flow_id, false); fail: + kfree(rxsc); return ERR_PTR(ret); } -- cgit From 51f9a8921ceacd7bf0d3f47fa867a64988ba1dcb Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Tue, 18 Oct 2022 14:31:59 +0800 Subject: net: sched: cake: fix null pointer access issue when cake_init() fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the default qdisc is cake, if the qdisc of dev_queue fails to be inited during mqprio_init(), cake_reset() is invoked to clear resources. In this case, the tins is NULL, and it will cause gpf issue. The process is as follows: qdisc_create_dflt() cake_init() q->tins = kvcalloc(...) --->failed, q->tins is NULL ... qdisc_put() ... cake_reset() ... cake_dequeue_one() b = &q->tins[...] --->q->tins is NULL The following is the Call Trace information: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] RIP: 0010:cake_dequeue_one+0xc9/0x3c0 Call Trace: cake_reset+0xb1/0x140 qdisc_reset+0xed/0x6f0 qdisc_destroy+0x82/0x4c0 qdisc_put+0x9e/0xb0 qdisc_create_dflt+0x2c3/0x4a0 mqprio_init+0xa71/0x1760 qdisc_create+0x3eb/0x1000 tc_modify_qdisc+0x408/0x1720 rtnetlink_rcv_msg+0x38e/0xac0 netlink_rcv_skb+0x12d/0x3a0 netlink_unicast+0x4a2/0x740 netlink_sendmsg+0x826/0xcc0 sock_sendmsg+0xc5/0x100 ____sys_sendmsg+0x583/0x690 ___sys_sendmsg+0xe8/0x160 __sys_sendmsg+0xbf/0x160 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f89e5122d04 Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc") Signed-off-by: Zhengchao Shao Acked-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- net/sched/sch_cake.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 55c6879d2c7e..87f8ce2c65ee 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2224,8 +2224,12 @@ retry: static void cake_reset(struct Qdisc *sch) { + struct cake_sched_data *q = qdisc_priv(sch); u32 c; + if (!q->tins) + return; + for (c = 0; c < CAKE_MAX_TINS; c++) cake_clear_tin(sch, c); } -- cgit From f5ffa3b1197395501b72c10b35518bf58ef24475 Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Tue, 18 Oct 2022 14:32:00 +0800 Subject: Revert "net: sched: fq_codel: remove redundant resource cleanup in fq_codel_init()" This reverts commit 494f5063b86cd6e972cb41a27e083c9a3664319d. When the default qdisc is fq_codel, if the qdisc of dev_queue fails to be inited during mqprio_init(), fq_codel_reset() is invoked to clear resources. In this case, the flow is NULL, and it will cause gpf issue. The process is as follows: qdisc_create_dflt() fq_codel_init() ... q->flows_cnt = 1024; ... q->flows = kvcalloc(...) --->failed, q->flows is NULL ... qdisc_put() ... fq_codel_reset() ... flow = q->flows + i --->q->flows is NULL The following is the Call Trace information: general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] RIP: 0010:fq_codel_reset+0x14d/0x350 Call Trace: qdisc_reset+0xed/0x6f0 qdisc_destroy+0x82/0x4c0 qdisc_put+0x9e/0xb0 qdisc_create_dflt+0x2c3/0x4a0 mqprio_init+0xa71/0x1760 qdisc_create+0x3eb/0x1000 tc_modify_qdisc+0x408/0x1720 rtnetlink_rcv_msg+0x38e/0xac0 netlink_rcv_skb+0x12d/0x3a0 netlink_unicast+0x4a2/0x740 netlink_sendmsg+0x826/0xcc0 sock_sendmsg+0xc5/0x100 ____sys_sendmsg+0x583/0x690 ___sys_sendmsg+0xe8/0x160 __sys_sendmsg+0xbf/0x160 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fd272b22d04 Signed-off-by: Zhengchao Shao Signed-off-by: David S. Miller --- net/sched/sch_fq_codel.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 99d318b60568..8c4fee063436 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -478,24 +478,26 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, if (opt) { err = fq_codel_change(sch, opt, extack); if (err) - return err; + goto init_failure; } err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) - return err; + goto init_failure; if (!q->flows) { q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_codel_flow), GFP_KERNEL); - if (!q->flows) - return -ENOMEM; - + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL); - if (!q->backlogs) - return -ENOMEM; - + if (!q->backlogs) { + err = -ENOMEM; + goto alloc_failure; + } for (i = 0; i < q->flows_cnt; i++) { struct fq_codel_flow *flow = q->flows + i; @@ -508,6 +510,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; + +alloc_failure: + kvfree(q->flows); + q->flows = NULL; +init_failure: + q->flows_cnt = 0; + return err; } static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) -- cgit From 2a3fc78210b9f0e85372a2435368962009f480fc Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Tue, 18 Oct 2022 14:32:01 +0800 Subject: net: sched: sfb: fix null pointer access issue when sfb_init() fails When the default qdisc is sfb, if the qdisc of dev_queue fails to be inited during mqprio_init(), sfb_reset() is invoked to clear resources. In this case, the q->qdisc is NULL, and it will cause gpf issue. The process is as follows: qdisc_create_dflt() sfb_init() tcf_block_get() --->failed, q->qdisc is NULL ... qdisc_put() ... sfb_reset() qdisc_reset(q->qdisc) --->q->qdisc is NULL ops = qdisc->ops The following is the Call Trace information: general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] RIP: 0010:qdisc_reset+0x2b/0x6f0 Call Trace: sfb_reset+0x37/0xd0 qdisc_reset+0xed/0x6f0 qdisc_destroy+0x82/0x4c0 qdisc_put+0x9e/0xb0 qdisc_create_dflt+0x2c3/0x4a0 mqprio_init+0xa71/0x1760 qdisc_create+0x3eb/0x1000 tc_modify_qdisc+0x408/0x1720 rtnetlink_rcv_msg+0x38e/0xac0 netlink_rcv_skb+0x12d/0x3a0 netlink_unicast+0x4a2/0x740 netlink_sendmsg+0x826/0xcc0 sock_sendmsg+0xc5/0x100 ____sys_sendmsg+0x583/0x690 ___sys_sendmsg+0xe8/0x160 __sys_sendmsg+0xbf/0x160 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f2164122d04 Fixes: e13e02a3c68d ("net_sched: SFB flow scheduler") Signed-off-by: Zhengchao Shao Signed-off-by: David S. Miller --- net/sched/sch_sfb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index e2389fa3cff8..73ae2e726512 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -455,7 +455,8 @@ static void sfb_reset(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); - qdisc_reset(q->qdisc); + if (likely(q->qdisc)) + qdisc_reset(q->qdisc); q->slot = 0; q->double_buffering = false; sfb_zero_all_buckets(q); -- cgit From 672e97ef689a38cb20c2cc6a1814298fea34461e Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 18 Oct 2022 10:34:38 +0300 Subject: net: Fix return value of qdisc ingress handling on success Currently qdisc ingress handling (sch_handle_ingress()) doesn't set a return value and it is left to the old return value of the caller (__netif_receive_skb_core()) which is RX drop, so if the packet is consumed, caller will stop and return this value as if the packet was dropped. This causes a problem in the kernel tcp stack when having a egress tc rule forwarding to a ingress tc rule. The tcp stack sending packets on the device having the egress rule will see the packets as not successfully transmitted (although they actually were), will not advance it's internal state of sent data, and packets returning on such tcp stream will be dropped by the tcp stack with reason ack-of-unsent-data. See reproduction in [0] below. Fix that by setting the return value to RX success if the packet was handled successfully. [0] Reproduction steps: $ ip link add veth1 type veth peer name peer1 $ ip link add veth2 type veth peer name peer2 $ ifconfig peer1 5.5.5.6/24 up $ ip netns add ns0 $ ip link set dev peer2 netns ns0 $ ip netns exec ns0 ifconfig peer2 5.5.5.5/24 up $ ifconfig veth2 0 up $ ifconfig veth1 0 up #ingress forwarding veth1 <-> veth2 $ tc qdisc add dev veth2 ingress $ tc qdisc add dev veth1 ingress $ tc filter add dev veth2 ingress prio 1 proto all flower \ action mirred egress redirect dev veth1 $ tc filter add dev veth1 ingress prio 1 proto all flower \ action mirred egress redirect dev veth2 #steal packet from peer1 egress to veth2 ingress, bypassing the veth pipe $ tc qdisc add dev peer1 clsact $ tc filter add dev peer1 egress prio 20 proto ip flower \ action mirred ingress redirect dev veth1 #run iperf and see connection not running $ iperf3 -s& $ ip netns exec ns0 iperf3 -c 5.5.5.6 -i 1 #delete egress rule, and run again, now should work $ tc filter del dev peer1 egress $ ip netns exec ns0 iperf3 -c 5.5.5.6 -i 1 Fixes: f697c3e8b35c ("[NET]: Avoid unnecessary cloning for ingress filtering") Signed-off-by: Paul Blakey Signed-off-by: David S. Miller --- net/core/dev.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/core/dev.c b/net/core/dev.c index fa53830d0683..3be256051e99 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5136,11 +5136,13 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS); + *ret = NET_RX_DROP; return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_REDIRECT: /* skb_mac_header check was done by cls/act_bpf, so @@ -5153,8 +5155,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, *another = true; break; } + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_CONSUMED: + *ret = NET_RX_SUCCESS; return NULL; default: break; -- cgit From fd602f5cb52e336d8c06f8da2d80c76ce2905030 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 18 Oct 2022 10:34:39 +0300 Subject: selftests: add selftest for chaining of tc ingress handling to egress This test runs a simple ingress tc setup between two veth pairs, then adds a egress->ingress rule to test the chaining of tc ingress pipeline to tc egress piepline. Signed-off-by: Paul Blakey Signed-off-by: David S. Miller --- tools/testing/selftests/net/Makefile | 1 + .../selftests/net/test_ingress_egress_chaining.sh | 79 ++++++++++++++++++++++ 2 files changed, 80 insertions(+) create mode 100644 tools/testing/selftests/net/test_ingress_egress_chaining.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 2a6b0bc648c4..69c58362c0ed 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -70,6 +70,7 @@ TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr +TEST_PROGS += test_ingress_egress_chaining.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/test_ingress_egress_chaining.sh b/tools/testing/selftests/net/test_ingress_egress_chaining.sh new file mode 100644 index 000000000000..08adff6bb3b6 --- /dev/null +++ b/tools/testing/selftests/net/test_ingress_egress_chaining.sh @@ -0,0 +1,79 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test runs a simple ingress tc setup between two veth pairs, +# and chains a single egress rule to test ingress chaining to egress. +# +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip +fi + +needed_mods="act_mirred cls_flower sch_ingress" +for mod in $needed_mods; do + modinfo $mod &>/dev/null || { echo "SKIP: Need act_mirred module"; exit $ksft_skip; } +done + +ns="ns$((RANDOM%899+100))" +veth1="veth1$((RANDOM%899+100))" +veth2="veth2$((RANDOM%899+100))" +peer1="peer1$((RANDOM%899+100))" +peer2="peer2$((RANDOM%899+100))" +ip_peer1=198.51.100.5 +ip_peer2=198.51.100.6 + +function fail() { + echo "FAIL: $@" >> /dev/stderr + exit 1 +} + +function cleanup() { + killall -q -9 udpgso_bench_rx + ip link del $veth1 &> /dev/null + ip link del $veth2 &> /dev/null + ip netns del $ns &> /dev/null +} +trap cleanup EXIT + +function config() { + echo "Setup veth pairs [$veth1, $peer1], and veth pair [$veth2, $peer2]" + ip link add $veth1 type veth peer name $peer1 + ip link add $veth2 type veth peer name $peer2 + ip addr add $ip_peer1/24 dev $peer1 + ip link set $peer1 up + ip netns add $ns + ip link set dev $peer2 netns $ns + ip netns exec $ns ip addr add $ip_peer2/24 dev $peer2 + ip netns exec $ns ip link set $peer2 up + ip link set $veth1 up + ip link set $veth2 up + + echo "Add tc filter ingress->egress forwarding $veth1 <-> $veth2" + tc qdisc add dev $veth2 ingress + tc qdisc add dev $veth1 ingress + tc filter add dev $veth2 ingress prio 1 proto all flower \ + action mirred egress redirect dev $veth1 + tc filter add dev $veth1 ingress prio 1 proto all flower \ + action mirred egress redirect dev $veth2 + + echo "Add tc filter egress->ingress forwarding $peer1 -> $veth1, bypassing the veth pipe" + tc qdisc add dev $peer1 clsact + tc filter add dev $peer1 egress prio 20 proto ip flower \ + action mirred ingress redirect dev $veth1 +} + +function test_run() { + echo "Run tcp traffic" + ./udpgso_bench_rx -t & + sleep 1 + ip netns exec $ns timeout -k 2 10 ./udpgso_bench_tx -t -l 2 -4 -D $ip_peer1 || fail "traffic failed" + echo "Test passed" +} + +config +test_run +trap - EXIT +cleanup -- cgit From a1a824f448ba96c610b85288d844adc9f781828e Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 18 Oct 2022 16:13:10 -0700 Subject: genetlink: fix kdoc warnings Address a bunch of kdoc warnings: include/net/genetlink.h:81: warning: Function parameter or member 'module' not described in 'genl_family' include/net/genetlink.h:243: warning: expecting prototype for struct genl_info. Prototype was for struct genl_dumpit_info instead include/net/genetlink.h:419: warning: Function parameter or member 'net' not described in 'genlmsg_unicast' include/net/genetlink.h:438: warning: expecting prototype for gennlmsg_data(). Prototype was for genlmsg_data() instead include/net/genetlink.h:244: warning: Function parameter or member 'op' not described in 'genl_dumpit_info' Link: https://lore.kernel.org/r/20221018231310.1040482-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/net/genetlink.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 8f780170e2f8..3d08e67b3cfc 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -37,6 +37,7 @@ struct genl_info; * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks + * @module: pointer to the owning module (set to THIS_MODULE) * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @resv_start_op: first operation for which reserved fields of the header @@ -173,9 +174,9 @@ struct genl_ops { }; /** - * struct genl_info - info that is available during dumpit op call + * struct genl_dumpit_info - info that is available during dumpit op call * @family: generic netlink family - for internal genl code usage - * @ops: generic netlink ops - for internal genl code usage + * @op: generic netlink ops - for internal genl code usage * @attrs: netlink attributes */ struct genl_dumpit_info { @@ -354,6 +355,7 @@ int genlmsg_multicast_allns(const struct genl_family *family, /** * genlmsg_unicast - unicast a netlink message + * @net: network namespace to look up @portid in * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ @@ -373,7 +375,7 @@ static inline int genlmsg_reply(struct sk_buff *skb, struct genl_info *info) } /** - * gennlmsg_data - head of message payload + * genlmsg_data - head of message payload * @gnlh: genetlink message header */ static inline void *genlmsg_data(const struct genlmsghdr *gnlh) -- cgit From c2bf23e4a5af37a4d77901d9ff14c50a269f143d Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Tue, 18 Oct 2022 10:28:41 +0100 Subject: sfc: include vport_id in filter spec hash and equal() Filters on different vports are qualified by different implicit MACs and/or VLANs, so shouldn't be considered equal even if their other match fields are identical. Fixes: 7c460d9be610 ("sfc: Extend and abstract efx_filter_spec to cover Huntington/EF10") Co-developed-by: Edward Cree Signed-off-by: Edward Cree Signed-off-by: Pieter Jansen van Vuuren Reviewed-by: Martin Habets Link: https://lore.kernel.org/r/20221018092841.32206-1-pieter.jansen-van-vuuren@amd.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/sfc/filter.h | 4 ++-- drivers/net/ethernet/sfc/rx_common.c | 10 +++++----- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h index be72e71da027..5f201a547e5b 100644 --- a/drivers/net/ethernet/sfc/filter.h +++ b/drivers/net/ethernet/sfc/filter.h @@ -162,9 +162,9 @@ struct efx_filter_spec { u32 priority:2; u32 flags:6; u32 dmaq_id:12; - u32 vport_id; u32 rss_context; - __be16 outer_vid __aligned(4); /* allow jhash2() of match values */ + u32 vport_id; + __be16 outer_vid; __be16 inner_vid; u8 loc_mac[ETH_ALEN]; u8 rem_mac[ETH_ALEN]; diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 4826e6a7e4ce..9220afeddee8 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -660,17 +660,17 @@ bool efx_filter_spec_equal(const struct efx_filter_spec *left, (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX))) return false; - return memcmp(&left->outer_vid, &right->outer_vid, + return memcmp(&left->vport_id, &right->vport_id, sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) == 0; + offsetof(struct efx_filter_spec, vport_id)) == 0; } u32 efx_filter_spec_hash(const struct efx_filter_spec *spec) { - BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3); - return jhash2((const u32 *)&spec->outer_vid, + BUILD_BUG_ON(offsetof(struct efx_filter_spec, vport_id) & 3); + return jhash2((const u32 *)&spec->vport_id, (sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) / 4, + offsetof(struct efx_filter_spec, vport_id)) / 4, 0); } -- cgit From 258ad2fe5ede773625adfda88b173f4123e59f45 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 18 Oct 2022 21:16:07 +0800 Subject: wwan_hwsim: fix possible memory leak in wwan_hwsim_dev_new() Inject fault while probing module, if device_register() fails, but the refcount of kobject is not decreased to 0, the name allocated in dev_set_name() is leaked. Fix this by calling put_device(), so that name can be freed in callback function kobject_cleanup(). unreferenced object 0xffff88810152ad20 (size 8): comm "modprobe", pid 252, jiffies 4294849206 (age 22.713s) hex dump (first 8 bytes): 68 77 73 69 6d 30 00 ff hwsim0.. backtrace: [<000000009c3504ed>] __kmalloc_node_track_caller+0x44/0x1b0 [<00000000c0228a5e>] kvasprintf+0xb5/0x140 [<00000000cff8c21f>] kvasprintf_const+0x55/0x180 [<0000000055a1e073>] kobject_set_name_vargs+0x56/0x150 [<000000000a80b139>] dev_set_name+0xab/0xe0 Fixes: f36a111a74e7 ("wwan_hwsim: WWAN device simulator") Signed-off-by: Yang Yingliang Reviewed-by: Loic Poulain Acked-by: Sergey Ryazanov Link: https://lore.kernel.org/r/20221018131607.1901641-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/wwan/wwan_hwsim.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wwan/wwan_hwsim.c b/drivers/net/wwan/wwan_hwsim.c index ff09a8cedf93..2397a903d8f5 100644 --- a/drivers/net/wwan/wwan_hwsim.c +++ b/drivers/net/wwan/wwan_hwsim.c @@ -311,7 +311,7 @@ err_unreg_dev: return ERR_PTR(err); err_free_dev: - kfree(dev); + put_device(&dev->dev); return ERR_PTR(err); } -- cgit From ff2f5ec5d009844ec28f171123f9e58750cef4bf Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Tue, 18 Oct 2022 20:24:51 +0800 Subject: net: hns: fix possible memory leak in hnae_ae_register() Inject fault while probing module, if device_register() fails, but the refcount of kobject is not decreased to 0, the name allocated in dev_set_name() is leaked. Fix this by calling put_device(), so that name can be freed in callback function kobject_cleanup(). unreferenced object 0xffff00c01aba2100 (size 128): comm "systemd-udevd", pid 1259, jiffies 4294903284 (age 294.152s) hex dump (first 32 bytes): 68 6e 61 65 30 00 00 00 18 21 ba 1a c0 00 ff ff hnae0....!...... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000034783f26>] slab_post_alloc_hook+0xa0/0x3e0 [<00000000748188f2>] __kmem_cache_alloc_node+0x164/0x2b0 [<00000000ab0743e8>] __kmalloc_node_track_caller+0x6c/0x390 [<000000006c0ffb13>] kvasprintf+0x8c/0x118 [<00000000fa27bfe1>] kvasprintf_const+0x60/0xc8 [<0000000083e10ed7>] kobject_set_name_vargs+0x3c/0xc0 [<000000000b87affc>] dev_set_name+0x7c/0xa0 [<000000003fd8fe26>] hnae_ae_register+0xcc/0x190 [hnae] [<00000000fe97edc9>] hns_dsaf_ae_init+0x9c/0x108 [hns_dsaf] [<00000000c36ff1eb>] hns_dsaf_probe+0x548/0x748 [hns_dsaf] Fixes: 6fe6611ff275 ("net: add Hisilicon Network Subsystem hnae framework support") Signed-off-by: Yang Yingliang Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/20221018122451.1749171-1-yangyingliang@huawei.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns/hnae.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 00fafc0f8512..430eccea8e5e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -419,8 +419,10 @@ int hnae_ae_register(struct hnae_ae_dev *hdev, struct module *owner) hdev->cls_dev.release = hnae_release; (void)dev_set_name(&hdev->cls_dev, "hnae%d", hdev->id); ret = device_register(&hdev->cls_dev); - if (ret) + if (ret) { + put_device(&hdev->cls_dev); return ret; + } __module_get(THIS_MODULE); -- cgit From ebda44da44f6f309d302522b049f43d6f829f7aa Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 18 Oct 2022 20:32:58 +0000 Subject: net: sched: fix race condition in qdisc_graft() We had one syzbot report [1] in syzbot queue for a while. I was waiting for more occurrences and/or a repro but Dmitry Vyukov spotted the issue right away. qdisc_graft() drops reference to qdisc in notify_and_destroy while it's still assigned to dev->qdisc Indeed, RCU rules are clear when replacing a data structure. The visible pointer (dev->qdisc in this case) must be updated to the new object _before_ RCU grace period is started (qdisc_put(old) in this case). [1] BUG: KASAN: use-after-free in __tcf_qdisc_find.part.0+0xa3a/0xac0 net/sched/cls_api.c:1066 Read of size 4 at addr ffff88802065e038 by task syz-executor.4/21027 CPU: 0 PID: 21027 Comm: syz-executor.4 Not tainted 6.0.0-rc3-syzkaller-00363-g7726d4c3e60b #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:317 [inline] print_report.cold+0x2ba/0x719 mm/kasan/report.c:433 kasan_report+0xb1/0x1e0 mm/kasan/report.c:495 __tcf_qdisc_find.part.0+0xa3a/0xac0 net/sched/cls_api.c:1066 __tcf_qdisc_find net/sched/cls_api.c:1051 [inline] tc_new_tfilter+0x34f/0x2200 net/sched/cls_api.c:2018 rtnetlink_rcv_msg+0x955/0xca0 net/core/rtnetlink.c:6081 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2501 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x917/0xe10 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 ____sys_sendmsg+0x6eb/0x810 net/socket.c:2482 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f5efaa89279 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f5efbc31168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f5efab9bf80 RCX: 00007f5efaa89279 RDX: 0000000000000000 RSI: 0000000020000140 RDI: 0000000000000005 RBP: 00007f5efaae32e9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f5efb0cfb1f R14: 00007f5efbc31300 R15: 0000000000022000 Allocated by task 21027: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track mm/kasan/common.c:45 [inline] set_alloc_info mm/kasan/common.c:437 [inline] ____kasan_kmalloc mm/kasan/common.c:516 [inline] ____kasan_kmalloc mm/kasan/common.c:475 [inline] __kasan_kmalloc+0xa9/0xd0 mm/kasan/common.c:525 kmalloc_node include/linux/slab.h:623 [inline] kzalloc_node include/linux/slab.h:744 [inline] qdisc_alloc+0xb0/0xc50 net/sched/sch_generic.c:938 qdisc_create_dflt+0x71/0x4a0 net/sched/sch_generic.c:997 attach_one_default_qdisc net/sched/sch_generic.c:1152 [inline] netdev_for_each_tx_queue include/linux/netdevice.h:2437 [inline] attach_default_qdiscs net/sched/sch_generic.c:1170 [inline] dev_activate+0x760/0xcd0 net/sched/sch_generic.c:1229 __dev_open+0x393/0x4d0 net/core/dev.c:1441 __dev_change_flags+0x583/0x750 net/core/dev.c:8556 rtnl_configure_link+0xee/0x240 net/core/rtnetlink.c:3189 rtnl_newlink_create net/core/rtnetlink.c:3371 [inline] __rtnl_newlink+0x10b8/0x17e0 net/core/rtnetlink.c:3580 rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3593 rtnetlink_rcv_msg+0x43a/0xca0 net/core/rtnetlink.c:6090 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2501 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x917/0xe10 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 ____sys_sendmsg+0x6eb/0x810 net/socket.c:2482 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Freed by task 21020: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 kasan_set_track+0x21/0x30 mm/kasan/common.c:45 kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 ____kasan_slab_free mm/kasan/common.c:367 [inline] ____kasan_slab_free+0x166/0x1c0 mm/kasan/common.c:329 kasan_slab_free include/linux/kasan.h:200 [inline] slab_free_hook mm/slub.c:1754 [inline] slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1780 slab_free mm/slub.c:3534 [inline] kfree+0xe2/0x580 mm/slub.c:4562 rcu_do_batch kernel/rcu/tree.c:2245 [inline] rcu_core+0x7b5/0x1890 kernel/rcu/tree.c:2505 __do_softirq+0x1d3/0x9c6 kernel/softirq.c:571 Last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 __kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:348 call_rcu+0x99/0x790 kernel/rcu/tree.c:2793 qdisc_put+0xcd/0xe0 net/sched/sch_generic.c:1083 notify_and_destroy net/sched/sch_api.c:1012 [inline] qdisc_graft+0xeb1/0x1270 net/sched/sch_api.c:1084 tc_modify_qdisc+0xbb7/0x1a00 net/sched/sch_api.c:1671 rtnetlink_rcv_msg+0x43a/0xca0 net/core/rtnetlink.c:6090 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2501 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x917/0xe10 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 ____sys_sendmsg+0x6eb/0x810 net/socket.c:2482 ___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 __sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Second to last potentially related work creation: kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 __kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:348 kvfree_call_rcu+0x74/0x940 kernel/rcu/tree.c:3322 neigh_destroy+0x431/0x630 net/core/neighbour.c:912 neigh_release include/net/neighbour.h:454 [inline] neigh_cleanup_and_release+0x1f8/0x330 net/core/neighbour.c:103 neigh_del net/core/neighbour.c:225 [inline] neigh_remove_one+0x37d/0x460 net/core/neighbour.c:246 neigh_forced_gc net/core/neighbour.c:276 [inline] neigh_alloc net/core/neighbour.c:447 [inline] ___neigh_create+0x18b5/0x29a0 net/core/neighbour.c:642 ip6_finish_output2+0xfb8/0x1520 net/ipv6/ip6_output.c:125 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x690/0x1160 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:296 [inline] ip6_output+0x1ed/0x540 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:451 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] mld_sendpack+0xa09/0xe70 net/ipv6/mcast.c:1820 mld_send_cr net/ipv6/mcast.c:2121 [inline] mld_ifc_work+0x71c/0xdc0 net/ipv6/mcast.c:2653 process_one_work+0x991/0x1610 kernel/workqueue.c:2289 worker_thread+0x665/0x1080 kernel/workqueue.c:2436 kthread+0x2e4/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 The buggy address belongs to the object at ffff88802065e000 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 56 bytes inside of 1024-byte region [ffff88802065e000, ffff88802065e400) The buggy address belongs to the physical page: page:ffffea0000819600 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x20658 head:ffffea0000819600 order:3 compound_mapcount:0 compound_pincount:0 flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000010200 0000000000000000 dead000000000001 ffff888011841dc0 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 3523, tgid 3523 (sshd), ts 41495190986, free_ts 41417713212 prep_new_page mm/page_alloc.c:2532 [inline] get_page_from_freelist+0x109b/0x2ce0 mm/page_alloc.c:4283 __alloc_pages+0x1c7/0x510 mm/page_alloc.c:5515 alloc_pages+0x1a6/0x270 mm/mempolicy.c:2270 alloc_slab_page mm/slub.c:1824 [inline] allocate_slab+0x27e/0x3d0 mm/slub.c:1969 new_slab mm/slub.c:2029 [inline] ___slab_alloc+0x7f1/0xe10 mm/slub.c:3031 __slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3118 slab_alloc_node mm/slub.c:3209 [inline] __kmalloc_node_track_caller+0x2f2/0x380 mm/slub.c:4955 kmalloc_reserve net/core/skbuff.c:358 [inline] __alloc_skb+0xd9/0x2f0 net/core/skbuff.c:430 alloc_skb_fclone include/linux/skbuff.h:1307 [inline] tcp_stream_alloc_skb+0x38/0x580 net/ipv4/tcp.c:861 tcp_sendmsg_locked+0xc36/0x2f80 net/ipv4/tcp.c:1325 tcp_sendmsg+0x2b/0x40 net/ipv4/tcp.c:1483 inet_sendmsg+0x99/0xe0 net/ipv4/af_inet.c:819 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:734 sock_write_iter+0x291/0x3d0 net/socket.c:1108 call_write_iter include/linux/fs.h:2187 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x9e9/0xdd0 fs/read_write.c:578 ksys_write+0x1e8/0x250 fs/read_write.c:631 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1449 [inline] free_pcp_prepare+0x5e4/0xd20 mm/page_alloc.c:1499 free_unref_page_prepare mm/page_alloc.c:3380 [inline] free_unref_page+0x19/0x4d0 mm/page_alloc.c:3476 __unfreeze_partials+0x17c/0x1a0 mm/slub.c:2548 qlink_free mm/kasan/quarantine.c:168 [inline] qlist_free_all+0x6a/0x170 mm/kasan/quarantine.c:187 kasan_quarantine_reduce+0x180/0x200 mm/kasan/quarantine.c:294 __kasan_slab_alloc+0xa2/0xc0 mm/kasan/common.c:447 kasan_slab_alloc include/linux/kasan.h:224 [inline] slab_post_alloc_hook mm/slab.h:727 [inline] slab_alloc_node mm/slub.c:3243 [inline] slab_alloc mm/slub.c:3251 [inline] __kmem_cache_alloc_lru mm/slub.c:3258 [inline] kmem_cache_alloc+0x267/0x3b0 mm/slub.c:3268 kmem_cache_zalloc include/linux/slab.h:723 [inline] alloc_buffer_head+0x20/0x140 fs/buffer.c:2974 alloc_page_buffers+0x280/0x790 fs/buffer.c:829 create_empty_buffers+0x2c/0xee0 fs/buffer.c:1558 ext4_block_write_begin+0x1004/0x1530 fs/ext4/inode.c:1074 ext4_da_write_begin+0x422/0xae0 fs/ext4/inode.c:2996 generic_perform_write+0x246/0x560 mm/filemap.c:3738 ext4_buffered_write_iter+0x15b/0x460 fs/ext4/file.c:270 ext4_file_write_iter+0x44a/0x1660 fs/ext4/file.c:679 call_write_iter include/linux/fs.h:2187 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x9e9/0xdd0 fs/read_write.c:578 Fixes: af356afa010f ("net_sched: reintroduce dev->qdisc for use by sch_api") Reported-by: syzbot Diagnosed-by: Dmitry Vyukov Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20221018203258.2793282-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/sched/sch_api.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c98af0ada706..4a27dfb1ba0f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1099,12 +1099,13 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, skip: if (!ingress) { - notify_and_destroy(net, skb, n, classid, - rtnl_dereference(dev->qdisc), new); + old = rtnl_dereference(dev->qdisc); if (new && !new->ops->attach) qdisc_refcount_inc(new); rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); + notify_and_destroy(net, skb, n, classid, old, new); + if (new && new->ops->attach) new->ops->attach(new); } else { -- cgit From 7f378c03aa4952507521174fb0da7b24a9ad0be6 Mon Sep 17 00:00:00 2001 From: Felix Riemann Date: Tue, 18 Oct 2022 12:47:54 +0200 Subject: net: phy: dp83822: disable MDI crossover status change interrupt If the cable is disconnected the PHY seems to toggle between MDI and MDI-X modes. With the MDI crossover status interrupt active this causes roughly 10 interrupts per second. As the crossover status isn't checked by the driver, the interrupt can be disabled to reduce the interrupt load. Fixes: 87461f7a58ab ("net: phy: DP83822 initial driver submission") Signed-off-by: Felix Riemann Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20221018104755.30025-1-svc.sw.rte.linux@sma.de Signed-off-by: Jakub Kicinski --- drivers/net/phy/dp83822.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 8549e0e356c9..b60db8b6f477 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -254,8 +254,7 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_EEE_ERROR_CHANGE_INT_EN); if (!dp83822->fx_enabled) - misr_status |= DP83822_MDI_XOVER_INT_EN | - DP83822_ANEG_ERR_INT_EN | + misr_status |= DP83822_ANEG_ERR_INT_EN | DP83822_WOL_PKT_INT_EN; err = phy_write(phydev, MII_DP83822_MISR2, misr_status); -- cgit