From dee37e90b41f7b41a63b894ded5b3840a9dddbd7 Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:14 +0200 Subject: [PATCH 01/13] PCI: Add and use devres helper for bit masks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current devres implementation uses manual shift operations to check whether a bit in a mask is set. The code can be made more readable by writing a small helper function for that. Implement mask_contains_bar() and use it where applicable. Link: https://lore.kernel.org/r/20240613115032.29098-2-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index 2c562b9eaf80..f13edd4a3873 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -161,6 +161,10 @@ int pcim_set_mwi(struct pci_dev *dev) } EXPORT_SYMBOL(pcim_set_mwi); +static inline bool mask_contains_bar(int mask, int bar) +{ + return mask & BIT(bar); +} static void pcim_release(struct device *gendev, void *res) { @@ -169,7 +173,7 @@ static void pcim_release(struct device *gendev, void *res) int i; for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) - if (this->region_mask & (1 << i)) + if (mask_contains_bar(this->region_mask, i)) pci_release_region(dev, i); if (this->mwi) @@ -363,7 +367,7 @@ int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name) for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { unsigned long len; - if (!(mask & (1 << i))) + if (!mask_contains_bar(mask, i)) continue; rc = -EINVAL; @@ -386,7 +390,7 @@ int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name) pci_release_region(pdev, i); err_inval: while (--i >= 0) { - if (!(mask & (1 << i))) + if (!mask_contains_bar(mask, i)) continue; pcim_iounmap(pdev, iomap[i]); pci_release_region(pdev, i); @@ -438,7 +442,7 @@ void pcim_iounmap_regions(struct pci_dev *pdev, int mask) return; for (i = 0; i < PCIM_IOMAP_MAX; i++) { - if (!(mask & (1 << i))) + if (!mask_contains_bar(mask, i)) continue; pcim_iounmap(pdev, iomap[i]); From d5fe8207d8786142061fb18c8fb671b34649f114 Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:15 +0200 Subject: [PATCH 02/13] PCI: Add devres helpers for iomap table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The pcim_iomap_devres.table administrated by pcim_iomap_table() has its entries set and unset at several places throughout devres.c using manual iterations which are effectively code duplications. Add pcim_add_mapping_to_legacy_table() and pcim_remove_mapping_from_legacy_table() helper functions and use them where possible. Link: https://lore.kernel.org/r/20240613115032.29098-3-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 77 +++++++++++++++++++++++++++++++++----------- 1 file changed, 58 insertions(+), 19 deletions(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index f13edd4a3873..845d6fab0ce7 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -297,6 +297,52 @@ void __iomem * const *pcim_iomap_table(struct pci_dev *pdev) } EXPORT_SYMBOL(pcim_iomap_table); +/* + * Fill the legacy mapping-table, so that drivers using the old API can + * still get a BAR's mapping address through pcim_iomap_table(). + */ +static int pcim_add_mapping_to_legacy_table(struct pci_dev *pdev, + void __iomem *mapping, int bar) +{ + void __iomem **legacy_iomap_table; + + if (bar >= PCI_STD_NUM_BARS) + return -EINVAL; + + legacy_iomap_table = (void __iomem **)pcim_iomap_table(pdev); + if (!legacy_iomap_table) + return -ENOMEM; + + /* The legacy mechanism doesn't allow for duplicate mappings. */ + WARN_ON(legacy_iomap_table[bar]); + + legacy_iomap_table[bar] = mapping; + + return 0; +} + +/* + * Remove a mapping. The table only contains whole-BAR mappings, so this will + * never interfere with ranged mappings. + */ +static void pcim_remove_mapping_from_legacy_table(struct pci_dev *pdev, + void __iomem *addr) +{ + int bar; + void __iomem **legacy_iomap_table; + + legacy_iomap_table = (void __iomem **)pcim_iomap_table(pdev); + if (!legacy_iomap_table) + return; + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { + if (legacy_iomap_table[bar] == addr) { + legacy_iomap_table[bar] = NULL; + return; + } + } +} + /** * pcim_iomap - Managed pcim_iomap() * @pdev: PCI device to iomap for @@ -308,16 +354,20 @@ EXPORT_SYMBOL(pcim_iomap_table); */ void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen) { - void __iomem **tbl; + void __iomem *mapping; - BUG_ON(bar >= PCIM_IOMAP_MAX); - - tbl = (void __iomem **)pcim_iomap_table(pdev); - if (!tbl || tbl[bar]) /* duplicate mappings not allowed */ + mapping = pci_iomap(pdev, bar, maxlen); + if (!mapping) return NULL; - tbl[bar] = pci_iomap(pdev, bar, maxlen); - return tbl[bar]; + if (pcim_add_mapping_to_legacy_table(pdev, mapping, bar) != 0) + goto err_table; + + return mapping; + +err_table: + pci_iounmap(pdev, mapping); + return NULL; } EXPORT_SYMBOL(pcim_iomap); @@ -330,20 +380,9 @@ EXPORT_SYMBOL(pcim_iomap); */ void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr) { - void __iomem **tbl; - int i; - pci_iounmap(pdev, addr); - tbl = (void __iomem **)pcim_iomap_table(pdev); - BUG_ON(!tbl); - - for (i = 0; i < PCIM_IOMAP_MAX; i++) - if (tbl[i] == addr) { - tbl[i] = NULL; - return; - } - WARN_ON(1); + pcim_remove_mapping_from_legacy_table(pdev, addr); } EXPORT_SYMBOL(pcim_iounmap); From bbaff68bf4a404bee5f5e20e7b1e30301b26304a Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:16 +0200 Subject: [PATCH 03/13] PCI: Add managed partial-BAR request and map infrastructure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The pcim_iomap_devres table tracks entire-BAR mappings, so we can't use it to build a managed version of pci_iomap_range(), which maps partial BARs. Add struct pcim_addr_devres, which can track request and mapping of both entire BARs and partial BARs. Add the following internal devres functions based on struct pcim_addr_devres: pcim_iomap_region() # request & map entire BAR pcim_iounmap_region() # unmap & release entire BAR pcim_request_region() # request entire BAR pcim_release_region() # release entire BAR pcim_request_all_regions() # request all entire BARs pcim_release_all_regions() # release all entire BARs Rework the following public interfaces using the new infrastructure listed above: pcim_iomap() # map partial BAR pcim_iounmap() # unmap partial BAR pcim_iomap_regions() # request & map specified BARs pcim_iomap_regions_request_all() # request all BARs, map specified BARs pcim_iounmap_regions() # unmap & release specified BARs Link: https://lore.kernel.org/r/20240613115032.29098-4-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 611 ++++++++++++++++++++++++++++++++++++++----- drivers/pci/pci.c | 22 ++ drivers/pci/pci.h | 5 + 3 files changed, 571 insertions(+), 67 deletions(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index 845d6fab0ce7..8388ca463a7a 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -4,14 +4,246 @@ #include "pci.h" /* - * PCI iomap devres + * On the state of PCI's devres implementation: + * + * The older devres API for PCI has two significant problems: + * + * 1. It is very strongly tied to the statically allocated mapping table in + * struct pcim_iomap_devres below. This is mostly solved in the sense of the + * pcim_ functions in this file providing things like ranged mapping by + * bypassing this table, whereas the functions that were present in the old + * API still enter the mapping addresses into the table for users of the old + * API. + * + * 2. The region-request-functions in pci.c do become managed IF the device has + * been enabled with pcim_enable_device() instead of pci_enable_device(). + * This resulted in the API becoming inconsistent: Some functions have an + * obviously managed counter-part (e.g., pci_iomap() <-> pcim_iomap()), + * whereas some don't and are never managed, while others don't and are + * _sometimes_ managed (e.g. pci_request_region()). + * + * Consequently, in the new API, region requests performed by the pcim_ + * functions are automatically cleaned up through the devres callback + * pcim_addr_resource_release(), while requests performed by + * pcim_enable_device() + pci_*region*() are automatically cleaned up + * through the for-loop in pcim_release(). + * + * TODO 1: + * Remove the legacy table entirely once all calls to pcim_iomap_table() in + * the kernel have been removed. + * + * TODO 2: + * Port everyone calling pcim_enable_device() + pci_*region*() to using the + * pcim_ functions. Then, remove all devres functionality from pci_*region*() + * functions and remove the associated cleanups described above in point #2. */ -#define PCIM_IOMAP_MAX PCI_STD_NUM_BARS +/* + * Legacy struct storing addresses to whole mapped BARs. + */ struct pcim_iomap_devres { - void __iomem *table[PCIM_IOMAP_MAX]; + void __iomem *table[PCI_STD_NUM_BARS]; }; +enum pcim_addr_devres_type { + /* Default initializer. */ + PCIM_ADDR_DEVRES_TYPE_INVALID, + + /* A requested region spanning an entire BAR. */ + PCIM_ADDR_DEVRES_TYPE_REGION, + + /* + * A requested region spanning an entire BAR, and a mapping for + * the entire BAR. + */ + PCIM_ADDR_DEVRES_TYPE_REGION_MAPPING, + + /* + * A mapping within a BAR, either spanning the whole BAR or just a + * range. Without a requested region. + */ + PCIM_ADDR_DEVRES_TYPE_MAPPING, +}; + +/* + * This struct envelops IO or MEM addresses, i.e., mappings and region + * requests, because those are very frequently requested and released + * together. + */ +struct pcim_addr_devres { + enum pcim_addr_devres_type type; + void __iomem *baseaddr; + unsigned long offset; + unsigned long len; + int bar; +}; + +static inline void pcim_addr_devres_clear(struct pcim_addr_devres *res) +{ + memset(res, 0, sizeof(*res)); + res->bar = -1; +} + +/* + * The following functions, __pcim_*_region*, exist as counterparts to the + * versions from pci.c - which, unfortunately, can be in "hybrid mode", i.e., + * sometimes managed, sometimes not. + * + * To separate the APIs cleanly, we define our own, simplified versions here. + */ + +/** + * __pcim_request_region_range - Request a ranged region + * @pdev: PCI device the region belongs to + * @bar: BAR the range is within + * @offset: offset from the BAR's start address + * @maxlen: length in bytes, beginning at @offset + * @name: name associated with the request + * @req_flags: flags for the request, e.g., for kernel-exclusive requests + * + * Returns: 0 on success, a negative error code on failure. + * + * Request a range within a device's PCI BAR. Sanity check the input. + */ +static int __pcim_request_region_range(struct pci_dev *pdev, int bar, + unsigned long offset, + unsigned long maxlen, + const char *name, int req_flags) +{ + resource_size_t start = pci_resource_start(pdev, bar); + resource_size_t len = pci_resource_len(pdev, bar); + unsigned long dev_flags = pci_resource_flags(pdev, bar); + + if (start == 0 || len == 0) /* Unused BAR. */ + return 0; + if (len <= offset) + return -EINVAL; + + start += offset; + len -= offset; + + if (len > maxlen && maxlen != 0) + len = maxlen; + + if (dev_flags & IORESOURCE_IO) { + if (!request_region(start, len, name)) + return -EBUSY; + } else if (dev_flags & IORESOURCE_MEM) { + if (!__request_mem_region(start, len, name, req_flags)) + return -EBUSY; + } else { + /* That's not a device we can request anything on. */ + return -ENODEV; + } + + return 0; +} + +static void __pcim_release_region_range(struct pci_dev *pdev, int bar, + unsigned long offset, + unsigned long maxlen) +{ + resource_size_t start = pci_resource_start(pdev, bar); + resource_size_t len = pci_resource_len(pdev, bar); + unsigned long flags = pci_resource_flags(pdev, bar); + + if (len <= offset || start == 0) + return; + + if (len == 0 || maxlen == 0) /* This an unused BAR. Do nothing. */ + return; + + start += offset; + len -= offset; + + if (len > maxlen) + len = maxlen; + + if (flags & IORESOURCE_IO) + release_region(start, len); + else if (flags & IORESOURCE_MEM) + release_mem_region(start, len); +} + +static int __pcim_request_region(struct pci_dev *pdev, int bar, + const char *name, int flags) +{ + unsigned long offset = 0; + unsigned long len = pci_resource_len(pdev, bar); + + return __pcim_request_region_range(pdev, bar, offset, len, name, flags); +} + +static void __pcim_release_region(struct pci_dev *pdev, int bar) +{ + unsigned long offset = 0; + unsigned long len = pci_resource_len(pdev, bar); + + __pcim_release_region_range(pdev, bar, offset, len); +} + +static void pcim_addr_resource_release(struct device *dev, void *resource_raw) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct pcim_addr_devres *res = resource_raw; + + switch (res->type) { + case PCIM_ADDR_DEVRES_TYPE_REGION: + __pcim_release_region(pdev, res->bar); + break; + case PCIM_ADDR_DEVRES_TYPE_REGION_MAPPING: + pci_iounmap(pdev, res->baseaddr); + __pcim_release_region(pdev, res->bar); + break; + case PCIM_ADDR_DEVRES_TYPE_MAPPING: + pci_iounmap(pdev, res->baseaddr); + break; + default: + break; + } +} + +static struct pcim_addr_devres *pcim_addr_devres_alloc(struct pci_dev *pdev) +{ + struct pcim_addr_devres *res; + + res = devres_alloc_node(pcim_addr_resource_release, sizeof(*res), + GFP_KERNEL, dev_to_node(&pdev->dev)); + if (res) + pcim_addr_devres_clear(res); + return res; +} + +/* Just for consistency and readability. */ +static inline void pcim_addr_devres_free(struct pcim_addr_devres *res) +{ + devres_free(res); +} + +/* + * Used by devres to identify a pcim_addr_devres. + */ +static int pcim_addr_resources_match(struct device *dev, + void *a_raw, void *b_raw) +{ + struct pcim_addr_devres *a, *b; + + a = a_raw; + b = b_raw; + + if (a->type != b->type) + return 0; + + switch (a->type) { + case PCIM_ADDR_DEVRES_TYPE_REGION: + case PCIM_ADDR_DEVRES_TYPE_REGION_MAPPING: + return a->bar == b->bar; + case PCIM_ADDR_DEVRES_TYPE_MAPPING: + return a->baseaddr == b->baseaddr; + default: + return 0; + } +} static void devm_pci_unmap_iospace(struct device *dev, void *ptr) { @@ -92,8 +324,8 @@ EXPORT_SYMBOL(devm_pci_remap_cfgspace); * * All operations are managed and will be undone on driver detach. * - * Returns a pointer to the remapped memory or an ERR_PTR() encoded error code - * on failure. Usage example:: + * Returns a pointer to the remapped memory or an IOMEM_ERR_PTR() encoded error + * code on failure. Usage example:: * * res = platform_get_resource(pdev, IORESOURCE_MEM, 0); * base = devm_pci_remap_cfg_resource(&pdev->dev, res); @@ -172,6 +404,17 @@ static void pcim_release(struct device *gendev, void *res) struct pci_devres *this = res; int i; + /* + * This is legacy code. + * + * All regions requested by a pcim_ function do get released through + * pcim_addr_resource_release(). Thanks to the hybrid nature of the pci_ + * region-request functions, this for-loop has to release the regions + * if they have been requested by such a function. + * + * TODO: Remove this once all users of pcim_enable_device() PLUS + * pci-region-request-functions have been ported to pcim_ functions. + */ for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) if (mask_contains_bar(this->region_mask, i)) pci_release_region(dev, i); @@ -258,19 +501,21 @@ EXPORT_SYMBOL(pcim_pin_device); static void pcim_iomap_release(struct device *gendev, void *res) { - struct pci_dev *dev = to_pci_dev(gendev); - struct pcim_iomap_devres *this = res; - int i; - - for (i = 0; i < PCIM_IOMAP_MAX; i++) - if (this->table[i]) - pci_iounmap(dev, this->table[i]); + /* + * Do nothing. This is legacy code. + * + * Cleanup of the mappings is now done directly through the callbacks + * registered when creating them. + */ } /** * pcim_iomap_table - access iomap allocation table * @pdev: PCI device to access iomap table for * + * Returns: + * Const pointer to array of __iomem pointers on success, NULL on failure. + * * Access iomap allocation table for @dev. If iomap table doesn't * exist and @pdev is managed, it will be allocated. All iomaps * recorded in the iomap table are automatically unmapped on driver @@ -343,30 +588,67 @@ static void pcim_remove_mapping_from_legacy_table(struct pci_dev *pdev, } } +/* + * The same as pcim_remove_mapping_from_legacy_table(), but identifies the + * mapping by its BAR index. + */ +static void pcim_remove_bar_from_legacy_table(struct pci_dev *pdev, int bar) +{ + void __iomem **legacy_iomap_table; + + if (bar >= PCI_STD_NUM_BARS) + return; + + legacy_iomap_table = (void __iomem **)pcim_iomap_table(pdev); + if (!legacy_iomap_table) + return; + + legacy_iomap_table[bar] = NULL; +} + /** * pcim_iomap - Managed pcim_iomap() * @pdev: PCI device to iomap for * @bar: BAR to iomap * @maxlen: Maximum length of iomap * - * Managed pci_iomap(). Map is automatically unmapped on driver - * detach. + * Returns: __iomem pointer on success, NULL on failure. + * + * Managed pci_iomap(). Map is automatically unmapped on driver detach. If + * desired, unmap manually only with pcim_iounmap(). + * + * This SHOULD only be used once per BAR. + * + * NOTE: + * Contrary to the other pcim_* functions, this function does not return an + * IOMEM_ERR_PTR() on failure, but a simple NULL. This is done for backwards + * compatibility. */ void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen) { void __iomem *mapping; + struct pcim_addr_devres *res; + + res = pcim_addr_devres_alloc(pdev); + if (!res) + return NULL; + res->type = PCIM_ADDR_DEVRES_TYPE_MAPPING; mapping = pci_iomap(pdev, bar, maxlen); if (!mapping) - return NULL; + goto err_iomap; + res->baseaddr = mapping; if (pcim_add_mapping_to_legacy_table(pdev, mapping, bar) != 0) goto err_table; + devres_add(&pdev->dev, res); return mapping; err_table: pci_iounmap(pdev, mapping); +err_iomap: + pcim_addr_devres_free(res); return NULL; } EXPORT_SYMBOL(pcim_iomap); @@ -376,91 +658,291 @@ EXPORT_SYMBOL(pcim_iomap); * @pdev: PCI device to iounmap for * @addr: Address to unmap * - * Managed pci_iounmap(). @addr must have been mapped using pcim_iomap(). + * Managed pci_iounmap(). @addr must have been mapped using a pcim_* mapping + * function. */ void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr) { - pci_iounmap(pdev, addr); + struct pcim_addr_devres res_searched; + + pcim_addr_devres_clear(&res_searched); + res_searched.type = PCIM_ADDR_DEVRES_TYPE_MAPPING; + res_searched.baseaddr = addr; + + if (devres_release(&pdev->dev, pcim_addr_resource_release, + pcim_addr_resources_match, &res_searched) != 0) { + /* Doesn't exist. User passed nonsense. */ + return; + } pcim_remove_mapping_from_legacy_table(pdev, addr); } EXPORT_SYMBOL(pcim_iounmap); +/** + * pcim_iomap_region - Request and iomap a PCI BAR + * @pdev: PCI device to map IO resources for + * @bar: Index of a BAR to map + * @name: Name associated with the request + * + * Returns: __iomem pointer on success, an IOMEM_ERR_PTR on failure. + * + * Mapping and region will get automatically released on driver detach. If + * desired, release manually only with pcim_iounmap_region(). + */ +static void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar, + const char *name) +{ + int ret; + struct pcim_addr_devres *res; + + res = pcim_addr_devres_alloc(pdev); + if (!res) + return IOMEM_ERR_PTR(-ENOMEM); + + res->type = PCIM_ADDR_DEVRES_TYPE_REGION_MAPPING; + res->bar = bar; + + ret = __pcim_request_region(pdev, bar, name, 0); + if (ret != 0) + goto err_region; + + res->baseaddr = pci_iomap(pdev, bar, 0); + if (!res->baseaddr) { + ret = -EINVAL; + goto err_iomap; + } + + devres_add(&pdev->dev, res); + return res->baseaddr; + +err_iomap: + __pcim_release_region(pdev, bar); +err_region: + pcim_addr_devres_free(res); + + return IOMEM_ERR_PTR(ret); +} + +/** + * pcim_iounmap_region - Unmap and release a PCI BAR + * @pdev: PCI device to operate on + * @bar: Index of BAR to unmap and release + * + * Unmap a BAR and release its region manually. Only pass BARs that were + * previously mapped by pcim_iomap_region(). + */ +static void pcim_iounmap_region(struct pci_dev *pdev, int bar) +{ + struct pcim_addr_devres res_searched; + + pcim_addr_devres_clear(&res_searched); + res_searched.type = PCIM_ADDR_DEVRES_TYPE_REGION_MAPPING; + res_searched.bar = bar; + + devres_release(&pdev->dev, pcim_addr_resource_release, + pcim_addr_resources_match, &res_searched); +} + /** * pcim_iomap_regions - Request and iomap PCI BARs * @pdev: PCI device to map IO resources for * @mask: Mask of BARs to request and iomap - * @name: Name used when requesting regions + * @name: Name associated with the requests + * + * Returns: 0 on success, negative error code on failure. * * Request and iomap regions specified by @mask. */ int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name) { - void __iomem * const *iomap; - int i, rc; + int ret; + int bar; + void __iomem *mapping; - iomap = pcim_iomap_table(pdev); - if (!iomap) - return -ENOMEM; - - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { - unsigned long len; - - if (!mask_contains_bar(mask, i)) + for (bar = 0; bar < DEVICE_COUNT_RESOURCE; bar++) { + if (!mask_contains_bar(mask, bar)) continue; - rc = -EINVAL; - len = pci_resource_len(pdev, i); - if (!len) - goto err_inval; - - rc = pci_request_region(pdev, i, name); - if (rc) - goto err_inval; - - rc = -ENOMEM; - if (!pcim_iomap(pdev, i, 0)) - goto err_region; + mapping = pcim_iomap_region(pdev, bar, name); + if (IS_ERR(mapping)) { + ret = PTR_ERR(mapping); + goto err; + } + ret = pcim_add_mapping_to_legacy_table(pdev, mapping, bar); + if (ret != 0) + goto err; } return 0; - err_region: - pci_release_region(pdev, i); - err_inval: - while (--i >= 0) { - if (!mask_contains_bar(mask, i)) - continue; - pcim_iounmap(pdev, iomap[i]); - pci_release_region(pdev, i); +err: + while (--bar >= 0) { + pcim_iounmap_region(pdev, bar); + pcim_remove_bar_from_legacy_table(pdev, bar); } - return rc; + return ret; } EXPORT_SYMBOL(pcim_iomap_regions); +static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name, + int request_flags) +{ + int ret; + struct pcim_addr_devres *res; + + res = pcim_addr_devres_alloc(pdev); + if (!res) + return -ENOMEM; + res->type = PCIM_ADDR_DEVRES_TYPE_REGION; + res->bar = bar; + + ret = __pcim_request_region(pdev, bar, name, request_flags); + if (ret != 0) { + pcim_addr_devres_free(res); + return ret; + } + + devres_add(&pdev->dev, res); + return 0; +} + +/** + * pcim_request_region - Request a PCI BAR + * @pdev: PCI device to requestion region for + * @bar: Index of BAR to request + * @name: Name associated with the request + * + * Returns: 0 on success, a negative error code on failure. + * + * Request region specified by @bar. + * + * The region will automatically be released on driver detach. If desired, + * release manually only with pcim_release_region(). + */ +static int pcim_request_region(struct pci_dev *pdev, int bar, const char *name) +{ + return _pcim_request_region(pdev, bar, name, 0); +} + +/** + * pcim_release_region - Release a PCI BAR + * @pdev: PCI device to operate on + * @bar: Index of BAR to release + * + * Release a region manually that was previously requested by + * pcim_request_region(). + */ +static void pcim_release_region(struct pci_dev *pdev, int bar) +{ + struct pcim_addr_devres res_searched; + + pcim_addr_devres_clear(&res_searched); + res_searched.type = PCIM_ADDR_DEVRES_TYPE_REGION; + res_searched.bar = bar; + + devres_release(&pdev->dev, pcim_addr_resource_release, + pcim_addr_resources_match, &res_searched); +} + + +/** + * pcim_release_all_regions - Release all regions of a PCI-device + * @pdev: the PCI device + * + * Release all regions previously requested through pcim_request_region() + * or pcim_request_all_regions(). + * + * Can be called from any context, i.e., not necessarily as a counterpart to + * pcim_request_all_regions(). + */ +static void pcim_release_all_regions(struct pci_dev *pdev) +{ + int bar; + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) + pcim_release_region(pdev, bar); +} + +/** + * pcim_request_all_regions - Request all regions + * @pdev: PCI device to map IO resources for + * @name: name associated with the request + * + * Returns: 0 on success, negative error code on failure. + * + * Requested regions will automatically be released at driver detach. If + * desired, release individual regions with pcim_release_region() or all of + * them at once with pcim_release_all_regions(). + */ +static int pcim_request_all_regions(struct pci_dev *pdev, const char *name) +{ + int ret; + int bar; + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { + ret = pcim_request_region(pdev, bar, name); + if (ret != 0) + goto err; + } + + return 0; + +err: + pcim_release_all_regions(pdev); + + return ret; +} + /** * pcim_iomap_regions_request_all - Request all BARs and iomap specified ones * @pdev: PCI device to map IO resources for * @mask: Mask of BARs to iomap - * @name: Name used when requesting regions + * @name: Name associated with the requests + * + * Returns: 0 on success, negative error code on failure. * * Request all PCI BARs and iomap regions specified by @mask. + * + * To release these resources manually, call pcim_release_region() for the + * regions and pcim_iounmap() for the mappings. */ int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask, const char *name) { - int request_mask = ((1 << 6) - 1) & ~mask; - int rc; + int bar; + int ret; + void __iomem **legacy_iomap_table; - rc = pci_request_selected_regions(pdev, request_mask, name); - if (rc) - return rc; + ret = pcim_request_all_regions(pdev, name); + if (ret != 0) + return ret; - rc = pcim_iomap_regions(pdev, mask, name); - if (rc) - pci_release_selected_regions(pdev, request_mask); - return rc; + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) { + if (!mask_contains_bar(mask, bar)) + continue; + if (!pcim_iomap(pdev, bar, 0)) + goto err; + } + + return 0; + +err: + /* + * If bar is larger than 0, then pcim_iomap() above has most likely + * failed because of -EINVAL. If it is equal 0, most likely the table + * couldn't be created, indicating -ENOMEM. + */ + ret = bar > 0 ? -EINVAL : -ENOMEM; + legacy_iomap_table = (void __iomem **)pcim_iomap_table(pdev); + + while (--bar >= 0) + pcim_iounmap(pdev, legacy_iomap_table[bar]); + + pcim_release_all_regions(pdev); + + return ret; } EXPORT_SYMBOL(pcim_iomap_regions_request_all); @@ -473,19 +955,14 @@ EXPORT_SYMBOL(pcim_iomap_regions_request_all); */ void pcim_iounmap_regions(struct pci_dev *pdev, int mask) { - void __iomem * const *iomap; int i; - iomap = pcim_iomap_table(pdev); - if (!iomap) - return; - - for (i = 0; i < PCIM_IOMAP_MAX; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (!mask_contains_bar(mask, i)) continue; - pcim_iounmap(pdev, iomap[i]); - pci_release_region(pdev, i); + pcim_iounmap_region(pdev, i); + pcim_remove_bar_from_legacy_table(pdev, i); } } EXPORT_SYMBOL(pcim_iounmap_regions); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 59e0949fb079..d94445f5f882 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3883,6 +3883,17 @@ void pci_release_region(struct pci_dev *pdev, int bar) release_mem_region(pci_resource_start(pdev, bar), pci_resource_len(pdev, bar)); + /* + * This devres utility makes this function sometimes managed + * (when pcim_enable_device() has been called before). + * + * This is bad because it conflicts with the pcim_ functions being + * exclusively responsible for managed PCI. Its "sometimes yes, + * sometimes no" nature can cause bugs. + * + * TODO: Remove this once all users that use pcim_enable_device() PLUS + * a region request function have been ported to using pcim_ functions. + */ dr = find_pci_dr(pdev); if (dr) dr->region_mask &= ~(1 << bar); @@ -3927,6 +3938,17 @@ static int __pci_request_region(struct pci_dev *pdev, int bar, goto err_out; } + /* + * This devres utility makes this function sometimes managed + * (when pcim_enable_device() has been called before). + * + * This is bad because it conflicts with the pcim_ functions being + * exclusively responsible for managed pci. Its "sometimes yes, + * sometimes no" nature can cause bugs. + * + * TODO: Remove this once all users that use pcim_enable_device() PLUS + * a region request function have been ported to using pcim_ functions. + */ dr = find_pci_dr(pdev); if (dr) dr->region_mask |= 1 << bar; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index fd44565c4756..c09487f5550c 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -826,6 +826,11 @@ struct pci_devres { unsigned int orig_intx:1; unsigned int restore_intx:1; unsigned int mwi:1; + + /* + * TODO: remove the region_mask once everyone calling + * pcim_enable_device() + pci_*region*() is ported to pcim_ functions. + */ u32 region_mask; }; From e354bb84a4c1cbb928e052260cc5ce12ec6722ff Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:17 +0200 Subject: [PATCH 04/13] PCI: Deprecate pcim_iomap_table(), pcim_iomap_regions_request_all() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Deprecate pcim_iomap_table(). It returns a pointer to a table of ioremapped BARs, or NULL if it fails. This makes uses like this: addr = pcim_iomap_table(pdev)[0]; problematic because it causes a NULL pointer dereference on failure. Callers should use pcim_iomap() instead. Deprecate pcim_iomap_regions_request_all() because it is built on __pci_request_region() and is managed if pcim_enable_device() has been called, but unmanaged otherwise, which is prone to errors. Callers should either use pcim_iomap_regions() to request and map BARs, or use pcim_request_region() followed by pcim_iomap(). Link: https://lore.kernel.org/r/20240613115032.29098-5-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński [bhelgaas: commit log, sphinx markup] Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index 8388ca463a7a..a5957b4cbc0e 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -510,7 +510,7 @@ static void pcim_iomap_release(struct device *gendev, void *res) } /** - * pcim_iomap_table - access iomap allocation table + * pcim_iomap_table - access iomap allocation table (DEPRECATED) * @pdev: PCI device to access iomap table for * * Returns: @@ -524,6 +524,11 @@ static void pcim_iomap_release(struct device *gendev, void *res) * This function might sleep when the table is first allocated but can * be safely called without context and guaranteed to succeed once * allocated. + * + * This function is DEPRECATED. Do not use it in new code. Instead, obtain a + * mapping's address directly from one of the pcim_* mapping functions. For + * example: + * void __iomem \*mappy = pcim_iomap(pdev, bar, length); */ void __iomem * const *pcim_iomap_table(struct pci_dev *pdev) { @@ -897,6 +902,7 @@ static int pcim_request_all_regions(struct pci_dev *pdev, const char *name) /** * pcim_iomap_regions_request_all - Request all BARs and iomap specified ones + * (DEPRECATED) * @pdev: PCI device to map IO resources for * @mask: Mask of BARs to iomap * @name: Name associated with the requests @@ -907,6 +913,10 @@ static int pcim_request_all_regions(struct pci_dev *pdev, const char *name) * * To release these resources manually, call pcim_release_region() for the * regions and pcim_iounmap() for the mappings. + * + * This function is DEPRECATED. Don't use it in new code. Instead, use one + * of the pcim_* region request functions in combination with a pcim_* + * mapping function. */ int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask, const char *name) From d47bde708086c77b1ceeb7643e600089f63dd03b Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:18 +0200 Subject: [PATCH 05/13] PCI: Add managed pcim_request_region() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These existing functions: pci_request_region() pci_request_selected_regions() pci_request_selected_regions_exclusive() are "hybrid" functions built on __pci_request_region() and are managed if pcim_enable_device() has been called, but unmanaged otherwise. Add these new functions: pcim_request_region() pcim_request_region_exclusive() These are *always* managed and use the new pcim_addr_devres tracking infrastructure instead of find_pci_dr() and struct pci_devres.region_mask. Implement the hybrid functions using the new "pure" functions and remove struct pci_devres.region_mask, which is no longer needed. Link: https://lore.kernel.org/r/20240613115032.29098-6-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 54 ++++++++++++++++++++++---------------------- drivers/pci/pci.c | 47 ++++++++++++-------------------------- drivers/pci/pci.h | 11 ++++----- 3 files changed, 47 insertions(+), 65 deletions(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index a5957b4cbc0e..e4c37fcb12df 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -24,18 +24,16 @@ * * Consequently, in the new API, region requests performed by the pcim_ * functions are automatically cleaned up through the devres callback - * pcim_addr_resource_release(), while requests performed by - * pcim_enable_device() + pci_*region*() are automatically cleaned up - * through the for-loop in pcim_release(). + * pcim_addr_resource_release(). * - * TODO 1: + * Users of pcim_enable_device() + pci_*region*() are redirected in + * pci.c to the managed functions here in this file. This isn't exactly + * perfect, but the only alternative way would be to port ALL drivers + * using said combination to pcim_ functions. + * + * TODO: * Remove the legacy table entirely once all calls to pcim_iomap_table() in * the kernel have been removed. - * - * TODO 2: - * Port everyone calling pcim_enable_device() + pci_*region*() to using the - * pcim_ functions. Then, remove all devres functionality from pci_*region*() - * functions and remove the associated cleanups described above in point #2. */ /* @@ -402,22 +400,6 @@ static void pcim_release(struct device *gendev, void *res) { struct pci_dev *dev = to_pci_dev(gendev); struct pci_devres *this = res; - int i; - - /* - * This is legacy code. - * - * All regions requested by a pcim_ function do get released through - * pcim_addr_resource_release(). Thanks to the hybrid nature of the pci_ - * region-request functions, this for-loop has to release the regions - * if they have been requested by such a function. - * - * TODO: Remove this once all users of pcim_enable_device() PLUS - * pci-region-request-functions have been ported to pcim_ functions. - */ - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) - if (mask_contains_bar(this->region_mask, i)) - pci_release_region(dev, i); if (this->mwi) pci_clear_mwi(dev); @@ -826,11 +808,29 @@ static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name, * The region will automatically be released on driver detach. If desired, * release manually only with pcim_release_region(). */ -static int pcim_request_region(struct pci_dev *pdev, int bar, const char *name) +int pcim_request_region(struct pci_dev *pdev, int bar, const char *name) { return _pcim_request_region(pdev, bar, name, 0); } +/** + * pcim_request_region_exclusive - Request a PCI BAR exclusively + * @pdev: PCI device to requestion region for + * @bar: Index of BAR to request + * @name: Name associated with the request + * + * Returns: 0 on success, a negative error code on failure. + * + * Request region specified by @bar exclusively. + * + * The region will automatically be released on driver detach. If desired, + * release manually only with pcim_release_region(). + */ +int pcim_request_region_exclusive(struct pci_dev *pdev, int bar, const char *name) +{ + return _pcim_request_region(pdev, bar, name, IORESOURCE_EXCLUSIVE); +} + /** * pcim_release_region - Release a PCI BAR * @pdev: PCI device to operate on @@ -839,7 +839,7 @@ static int pcim_request_region(struct pci_dev *pdev, int bar, const char *name) * Release a region manually that was previously requested by * pcim_request_region(). */ -static void pcim_release_region(struct pci_dev *pdev, int bar) +void pcim_release_region(struct pci_dev *pdev, int bar) { struct pcim_addr_devres res_searched; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d94445f5f882..7013699db242 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3872,7 +3872,15 @@ EXPORT_SYMBOL(pci_enable_atomic_ops_to_root); */ void pci_release_region(struct pci_dev *pdev, int bar) { - struct pci_devres *dr; + /* + * This is done for backwards compatibility, because the old PCI devres + * API had a mode in which the function became managed if it had been + * enabled with pcim_enable_device() instead of pci_enable_device(). + */ + if (pci_is_managed(pdev)) { + pcim_release_region(pdev, bar); + return; + } if (pci_resource_len(pdev, bar) == 0) return; @@ -3882,21 +3890,6 @@ void pci_release_region(struct pci_dev *pdev, int bar) else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) release_mem_region(pci_resource_start(pdev, bar), pci_resource_len(pdev, bar)); - - /* - * This devres utility makes this function sometimes managed - * (when pcim_enable_device() has been called before). - * - * This is bad because it conflicts with the pcim_ functions being - * exclusively responsible for managed PCI. Its "sometimes yes, - * sometimes no" nature can cause bugs. - * - * TODO: Remove this once all users that use pcim_enable_device() PLUS - * a region request function have been ported to using pcim_ functions. - */ - dr = find_pci_dr(pdev); - if (dr) - dr->region_mask &= ~(1 << bar); } EXPORT_SYMBOL(pci_release_region); @@ -3922,7 +3915,12 @@ EXPORT_SYMBOL(pci_release_region); static int __pci_request_region(struct pci_dev *pdev, int bar, const char *res_name, int exclusive) { - struct pci_devres *dr; + if (pci_is_managed(pdev)) { + if (exclusive == IORESOURCE_EXCLUSIVE) + return pcim_request_region_exclusive(pdev, bar, res_name); + + return pcim_request_region(pdev, bar, res_name); + } if (pci_resource_len(pdev, bar) == 0) return 0; @@ -3938,21 +3936,6 @@ static int __pci_request_region(struct pci_dev *pdev, int bar, goto err_out; } - /* - * This devres utility makes this function sometimes managed - * (when pcim_enable_device() has been called before). - * - * This is bad because it conflicts with the pcim_ functions being - * exclusively responsible for managed pci. Its "sometimes yes, - * sometimes no" nature can cause bugs. - * - * TODO: Remove this once all users that use pcim_enable_device() PLUS - * a region request function have been ported to using pcim_ functions. - */ - dr = find_pci_dr(pdev); - if (dr) - dr->region_mask |= 1 << bar; - return 0; err_out: diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index c09487f5550c..37894852c2a0 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -826,16 +826,15 @@ struct pci_devres { unsigned int orig_intx:1; unsigned int restore_intx:1; unsigned int mwi:1; - - /* - * TODO: remove the region_mask once everyone calling - * pcim_enable_device() + pci_*region*() is ported to pcim_ functions. - */ - u32 region_mask; }; struct pci_devres *find_pci_dr(struct pci_dev *pdev); +int pcim_request_region(struct pci_dev *pdev, int bar, const char *name); +int pcim_request_region_exclusive(struct pci_dev *pdev, int bar, + const char *name); +void pcim_release_region(struct pci_dev *pdev, int bar); + /* * Config Address for PCI Configuration Mechanism #1 * From 81fcf28e74a3ffda67a6896cd38843d80bc9ec68 Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:19 +0200 Subject: [PATCH 06/13] PCI: Document hybrid devres hazards MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These functions: pci_request_region() pci_request_regions() pci_request_regions_exclusive() pci_request_selected_regions() pci_request_selected_regions_exclusive() pci_intx() are "hybrid" functions that are managed if pcim_enable_device() has been called, but unmanaged otherwise. This is confusing and has already caused a bug (in 8558de401b5f ("drm/vboxvideo: use managed pci functions")) because users believe all PCI functions, such as pci_iomap_range(), can become managed that way, which is not the case. Add comments to the relevant functions' docstrings that warn users about this behavior. Link: https://lore.kernel.org/r/20240613115032.29098-7-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas --- drivers/pci/iomap.c | 16 +++++++++++++++ drivers/pci/pci.c | 47 ++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 62 insertions(+), 1 deletion(-) diff --git a/drivers/pci/iomap.c b/drivers/pci/iomap.c index c9725428e387..a715a4803c95 100644 --- a/drivers/pci/iomap.c +++ b/drivers/pci/iomap.c @@ -23,6 +23,10 @@ * * @maxlen specifies the maximum length to map. If you want to get access to * the complete BAR from offset to the end, pass %0 here. + * + * NOTE: + * This function is never managed, even if you initialized with + * pcim_enable_device(). * */ void __iomem *pci_iomap_range(struct pci_dev *dev, int bar, @@ -63,6 +67,10 @@ EXPORT_SYMBOL(pci_iomap_range); * * @maxlen specifies the maximum length to map. If you want to get access to * the complete BAR from offset to the end, pass %0 here. + * + * NOTE: + * This function is never managed, even if you initialized with + * pcim_enable_device(). * */ void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, @@ -106,6 +114,10 @@ EXPORT_SYMBOL_GPL(pci_iomap_wc_range); * * @maxlen specifies the maximum length to map. If you want to get access to * the complete BAR without checking for its length first, pass %0 here. + * + * NOTE: + * This function is never managed, even if you initialized with + * pcim_enable_device(). If you need automatic cleanup, use pcim_iomap(). * */ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen) { @@ -127,6 +139,10 @@ EXPORT_SYMBOL(pci_iomap); * * @maxlen specifies the maximum length to map. If you want to get access to * the complete BAR without checking for its length first, pass %0 here. + * + * NOTE: + * This function is never managed, even if you initialized with + * pcim_enable_device(). * */ void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen) { diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 7013699db242..1e258c98df1a 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3900,6 +3900,8 @@ EXPORT_SYMBOL(pci_release_region); * @res_name: Name to be associated with resource. * @exclusive: whether the region access is exclusive or not * + * Returns: 0 on success, negative error code on failure. + * * Mark the PCI region associated with PCI device @pdev BAR @bar as * being reserved by owner @res_name. Do not access any * address inside the PCI regions unless this call returns @@ -3950,6 +3952,8 @@ static int __pci_request_region(struct pci_dev *pdev, int bar, * @bar: BAR to be reserved * @res_name: Name to be associated with resource * + * Returns: 0 on success, negative error code on failure. + * * Mark the PCI region associated with PCI device @pdev BAR @bar as * being reserved by owner @res_name. Do not access any * address inside the PCI regions unless this call returns @@ -3957,6 +3961,11 @@ static int __pci_request_region(struct pci_dev *pdev, int bar, * * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name) { @@ -4007,6 +4016,13 @@ static int __pci_request_selected_regions(struct pci_dev *pdev, int bars, * @pdev: PCI device whose resources are to be reserved * @bars: Bitmask of BARs to be requested * @res_name: Name to be associated with resource + * + * Returns: 0 on success, negative error code on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_selected_regions(struct pci_dev *pdev, int bars, const char *res_name) @@ -4015,6 +4031,19 @@ int pci_request_selected_regions(struct pci_dev *pdev, int bars, } EXPORT_SYMBOL(pci_request_selected_regions); +/** + * pci_request_selected_regions_exclusive - Request regions exclusively + * @pdev: PCI device to request regions from + * @bars: bit mask of BARs to request + * @res_name: name to be associated with the requests + * + * Returns: 0 on success, negative error code on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. + */ int pci_request_selected_regions_exclusive(struct pci_dev *pdev, int bars, const char *res_name) { @@ -4032,7 +4061,6 @@ EXPORT_SYMBOL(pci_request_selected_regions_exclusive); * successful call to pci_request_regions(). Call this function only * after all use of the PCI regions has ceased. */ - void pci_release_regions(struct pci_dev *pdev) { pci_release_selected_regions(pdev, (1 << PCI_STD_NUM_BARS) - 1); @@ -4051,6 +4079,11 @@ EXPORT_SYMBOL(pci_release_regions); * * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_regions(struct pci_dev *pdev, const char *res_name) { @@ -4064,6 +4097,8 @@ EXPORT_SYMBOL(pci_request_regions); * @pdev: PCI device whose resources are to be reserved * @res_name: Name to be associated with resource. * + * Returns: 0 on success, negative error code on failure. + * * Mark all PCI regions associated with PCI device @pdev as being reserved * by owner @res_name. Do not access any address inside the PCI regions * unless this call returns successfully. @@ -4073,6 +4108,11 @@ EXPORT_SYMBOL(pci_request_regions); * * Returns 0 on success, or %EBUSY on error. A warning message is also * printed on failure. + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) { @@ -4404,6 +4444,11 @@ void pci_disable_parity(struct pci_dev *dev) * @enable: boolean: whether to enable or disable PCI INTx * * Enables/disables PCI INTx for device @pdev + * + * NOTE: + * This is a "hybrid" function: It's normally unmanaged, but becomes managed + * when pcim_enable_device() has been called in advance. This hybrid feature is + * DEPRECATED! */ void pci_intx(struct pci_dev *pdev, int enable) { From 77f79ac8de0f490fca4f0a5f2e1e38eeee191f05 Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:20 +0200 Subject: [PATCH 07/13] PCI: Remove struct pci_devres.enabled status bit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The struct pci_devres has a separate boolean to track whether a device is enabled. That, however, can easily be tracked in an agnostic manner through the function pci_is_enabled(). Using it allows for simplifying the PCI devres implementation. Replace the separate 'enabled' status bit from struct pci_devres with calls to pci_is_enabled() at the appropriate places. Link: https://lore.kernel.org/r/20240613115032.29098-8-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 11 ++++------- drivers/pci/pci.c | 6 ------ drivers/pci/pci.h | 1 - 3 files changed, 4 insertions(+), 14 deletions(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index e4c37fcb12df..4ac662efc6ac 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -407,7 +407,7 @@ static void pcim_release(struct device *gendev, void *res) if (this->restore_intx) pci_intx(dev, this->orig_intx); - if (this->enabled && !this->pinned) + if (pci_is_enabled(dev) && !this->pinned) pci_disable_device(dev); } @@ -450,14 +450,11 @@ int pcim_enable_device(struct pci_dev *pdev) dr = get_pci_dr(pdev); if (unlikely(!dr)) return -ENOMEM; - if (dr->enabled) - return 0; rc = pci_enable_device(pdev); - if (!rc) { + if (!rc) pdev->is_managed = 1; - dr->enabled = 1; - } + return rc; } EXPORT_SYMBOL(pcim_enable_device); @@ -475,7 +472,7 @@ void pcim_pin_device(struct pci_dev *pdev) struct pci_devres *dr; dr = find_pci_dr(pdev); - WARN_ON(!dr || !dr->enabled); + WARN_ON(!dr || !pci_is_enabled(pdev)); if (dr) dr->pinned = 1; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 1e258c98df1a..a0fad5990f03 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2218,12 +2218,6 @@ void pci_disable_enabled_device(struct pci_dev *dev) */ void pci_disable_device(struct pci_dev *dev) { - struct pci_devres *dr; - - dr = find_pci_dr(dev); - if (dr) - dr->enabled = 0; - dev_WARN_ONCE(&dev->dev, atomic_read(&dev->enable_cnt) <= 0, "disabling already-disabled device"); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 37894852c2a0..4f220bbbd4ae 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -821,7 +821,6 @@ static inline pci_power_t mid_pci_get_power_state(struct pci_dev *pdev) * then remove them from here. */ struct pci_devres { - unsigned int enabled:1; unsigned int pinned:1; unsigned int orig_intx:1; unsigned int restore_intx:1; From 1b9469cf15976a7cb7378caaa8a1772e7901514d Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:21 +0200 Subject: [PATCH 08/13] PCI: Move struct pci_devres.pinned bit to struct pci_dev MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bit describing whether the PCI device is currently pinned is stored in struct pci_devres. To clean up and simplify the PCI devres API, it's better if this information is stored in struct pci_dev. This will later permit simplifying pcim_enable_device(). Move the 'pinned' boolean bit to struct pci_dev. Restructure bits in struct pci_dev so the pm / pme fields are next to each other. Link: https://lore.kernel.org/r/20240613115032.29098-9-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 14 ++++---------- drivers/pci/pci.h | 1 - include/linux/pci.h | 3 ++- 3 files changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index 4ac662efc6ac..31ebda1db1b0 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -407,7 +407,7 @@ static void pcim_release(struct device *gendev, void *res) if (this->restore_intx) pci_intx(dev, this->orig_intx); - if (pci_is_enabled(dev) && !this->pinned) + if (pci_is_enabled(dev) && !dev->pinned) pci_disable_device(dev); } @@ -463,18 +463,12 @@ EXPORT_SYMBOL(pcim_enable_device); * pcim_pin_device - Pin managed PCI device * @pdev: PCI device to pin * - * Pin managed PCI device @pdev. Pinned device won't be disabled on - * driver detach. @pdev must have been enabled with - * pcim_enable_device(). + * Pin managed PCI device @pdev. Pinned device won't be disabled on driver + * detach. @pdev must have been enabled with pcim_enable_device(). */ void pcim_pin_device(struct pci_dev *pdev) { - struct pci_devres *dr; - - dr = find_pci_dr(pdev); - WARN_ON(!dr || !pci_is_enabled(pdev)); - if (dr) - dr->pinned = 1; + pdev->pinned = true; } EXPORT_SYMBOL(pcim_pin_device); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 4f220bbbd4ae..eb1eb4c7c34a 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -821,7 +821,6 @@ static inline pci_power_t mid_pci_get_power_state(struct pci_dev *pdev) * then remove them from here. */ struct pci_devres { - unsigned int pinned:1; unsigned int orig_intx:1; unsigned int restore_intx:1; unsigned int mwi:1; diff --git a/include/linux/pci.h b/include/linux/pci.h index fb004fd4e889..0c19f0717899 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -367,10 +367,11 @@ struct pci_dev { this is D0-D3, D0 being fully functional, and D3 being off. */ u8 pm_cap; /* PM capability offset */ - unsigned int imm_ready:1; /* Supports Immediate Readiness */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ unsigned int pme_poll:1; /* Poll device's PME status bit */ + unsigned int pinned:1; /* Whether this dev is pinned */ + unsigned int imm_ready:1; /* Supports Immediate Readiness */ unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ unsigned int no_d1d2:1; /* D1 and D2 are forbidden */ From 2c3e842f125fc1c57cd2824840d04e401c0542c2 Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:22 +0200 Subject: [PATCH 09/13] PCI: Give pcim_set_mwi() its own devres cleanup callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Managing pci_set_mwi() with devres can easily be done with its own callback, without the necessity to store any state about it in a device-related struct. Remove the MWI state from struct pci_devres. Give pcim_set_mwi() a separate devres cleanup callback. Link: https://lore.kernel.org/r/20240613115032.29098-10-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 29 ++++++++++++++++++----------- drivers/pci/pci.h | 1 - 2 files changed, 18 insertions(+), 12 deletions(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index 31ebda1db1b0..d3c29ec30ad7 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -370,24 +370,34 @@ void __iomem *devm_pci_remap_cfg_resource(struct device *dev, } EXPORT_SYMBOL(devm_pci_remap_cfg_resource); +static void __pcim_clear_mwi(void *pdev_raw) +{ + struct pci_dev *pdev = pdev_raw; + + pci_clear_mwi(pdev); +} + /** * pcim_set_mwi - a device-managed pci_set_mwi() - * @dev: the PCI device for which MWI is enabled + * @pdev: the PCI device for which MWI is enabled * * Managed pci_set_mwi(). * * RETURNS: An appropriate -ERRNO error value on error, or zero for success. */ -int pcim_set_mwi(struct pci_dev *dev) +int pcim_set_mwi(struct pci_dev *pdev) { - struct pci_devres *dr; + int ret; - dr = find_pci_dr(dev); - if (!dr) - return -ENOMEM; + ret = devm_add_action(&pdev->dev, __pcim_clear_mwi, pdev); + if (ret != 0) + return ret; - dr->mwi = 1; - return pci_set_mwi(dev); + ret = pci_set_mwi(pdev); + if (ret != 0) + devm_remove_action(&pdev->dev, __pcim_clear_mwi, pdev); + + return ret; } EXPORT_SYMBOL(pcim_set_mwi); @@ -401,9 +411,6 @@ static void pcim_release(struct device *gendev, void *res) struct pci_dev *dev = to_pci_dev(gendev); struct pci_devres *this = res; - if (this->mwi) - pci_clear_mwi(dev); - if (this->restore_intx) pci_intx(dev, this->orig_intx); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index eb1eb4c7c34a..9a12f6774431 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -823,7 +823,6 @@ static inline pci_power_t mid_pci_get_power_state(struct pci_dev *pdev) struct pci_devres { unsigned int orig_intx:1; unsigned int restore_intx:1; - unsigned int mwi:1; }; struct pci_devres *find_pci_dr(struct pci_dev *pdev); From 25216afc9db53d85dc648aba8fb7f6d31f2c8731 Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:23 +0200 Subject: [PATCH 10/13] PCI: Add managed pcim_intx() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit pci_intx() is a "hybrid" function, i.e., it is managed if pcim_enable_device() has been called, but unmanaged otherwise. Add pcim_intx(), which is always managed, and implement pci_intx() using it. Remove the now-unused struct pci_devres.orig_intx and .restore_intx and find_pci_dr(). Link: https://lore.kernel.org/r/20240613115032.29098-11-pstanner@redhat.com Signed-off-by: Philipp Stanner [kwilczynski: squashed in https://lore.kernel.org/r/426645d40776198e0fcc942f4a6cac4433c7a9aa.camel@redhat.com to fix problem reported and tested by Ashish Kalra : https://lore.kernel.org/r/20240708214656.4721-1-Ashish.Kalra@amd.com https://lore.kernel.org/r/8c4634e9-4f02-4c54-9c89-d75e2f4bf026@amd.com/] Signed-off-by: Krzysztof Wilczyński [bhelgaas: commit log] Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 86 ++++++++++++++++++++++++++++++++++++-------- drivers/pci/pci.c | 19 +++++----- drivers/pci/pci.h | 13 +++---- 3 files changed, 86 insertions(+), 32 deletions(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index d3c29ec30ad7..f7b718438412 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -43,6 +43,11 @@ struct pcim_iomap_devres { void __iomem *table[PCI_STD_NUM_BARS]; }; +/* Used to restore the old INTx state on driver detach. */ +struct pcim_intx_devres { + int orig_intx; +}; + enum pcim_addr_devres_type { /* Default initializer. */ PCIM_ADDR_DEVRES_TYPE_INVALID, @@ -406,29 +411,80 @@ static inline bool mask_contains_bar(int mask, int bar) return mask & BIT(bar); } +/* + * This is a copy of pci_intx() used to bypass the problem of recursive + * function calls due to the hybrid nature of pci_intx(). + */ +static void __pcim_intx(struct pci_dev *pdev, int enable) +{ + u16 pci_command, new; + + pci_read_config_word(pdev, PCI_COMMAND, &pci_command); + + if (enable) + new = pci_command & ~PCI_COMMAND_INTX_DISABLE; + else + new = pci_command | PCI_COMMAND_INTX_DISABLE; + + if (new != pci_command) + pci_write_config_word(pdev, PCI_COMMAND, new); +} + +static void pcim_intx_restore(struct device *dev, void *data) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct pcim_intx_devres *res = data; + + __pcim_intx(pdev, res->orig_intx); +} + +static struct pcim_intx_devres *get_or_create_intx_devres(struct device *dev) +{ + struct pcim_intx_devres *res; + + res = devres_find(dev, pcim_intx_restore, NULL, NULL); + if (res) + return res; + + res = devres_alloc(pcim_intx_restore, sizeof(*res), GFP_KERNEL); + if (res) + devres_add(dev, res); + + return res; +} + +/** + * pcim_intx - managed pci_intx() + * @pdev: the PCI device to operate on + * @enable: boolean: whether to enable or disable PCI INTx + * + * Returns: 0 on success, -ENOMEM on error. + * + * Enable/disable PCI INTx for device @pdev. + * Restore the original state on driver detach. + */ +int pcim_intx(struct pci_dev *pdev, int enable) +{ + struct pcim_intx_devres *res; + + res = get_or_create_intx_devres(&pdev->dev); + if (!res) + return -ENOMEM; + + res->orig_intx = !enable; + __pcim_intx(pdev, enable); + + return 0; +} + static void pcim_release(struct device *gendev, void *res) { struct pci_dev *dev = to_pci_dev(gendev); - struct pci_devres *this = res; - - if (this->restore_intx) - pci_intx(dev, this->orig_intx); if (pci_is_enabled(dev) && !dev->pinned) pci_disable_device(dev); } -/* - * TODO: After the last four callers in pci.c are ported, find_pci_dr() - * needs to be made static again. - */ -struct pci_devres *find_pci_dr(struct pci_dev *pdev) -{ - if (pci_is_managed(pdev)) - return devres_find(&pdev->dev, pcim_release, NULL, NULL); - return NULL; -} - static struct pci_devres *get_pci_dr(struct pci_dev *pdev) { struct pci_devres *dr, *new_dr; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a0fad5990f03..807f8be043cd 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4442,12 +4442,18 @@ void pci_disable_parity(struct pci_dev *dev) * NOTE: * This is a "hybrid" function: It's normally unmanaged, but becomes managed * when pcim_enable_device() has been called in advance. This hybrid feature is - * DEPRECATED! + * DEPRECATED! If you want managed cleanup, use pcim_intx() instead. */ void pci_intx(struct pci_dev *pdev, int enable) { u16 pci_command, new; + /* Preserve the "hybrid" behavior for backwards compatibility */ + if (pci_is_managed(pdev)) { + WARN_ON_ONCE(pcim_intx(pdev, enable) != 0); + return; + } + pci_read_config_word(pdev, PCI_COMMAND, &pci_command); if (enable) @@ -4455,17 +4461,8 @@ void pci_intx(struct pci_dev *pdev, int enable) else new = pci_command | PCI_COMMAND_INTX_DISABLE; - if (new != pci_command) { - struct pci_devres *dr; - + if (new != pci_command) pci_write_config_word(pdev, PCI_COMMAND, new); - - dr = find_pci_dr(pdev); - if (dr && !dr->restore_intx) { - dr->restore_intx = 1; - dr->orig_intx = !enable; - } - } } EXPORT_SYMBOL_GPL(pci_intx); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 9a12f6774431..21cb44176350 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -816,16 +816,17 @@ static inline pci_power_t mid_pci_get_power_state(struct pci_dev *pdev) * there's no need to track it separately. pci_devres is initialized * when a device is enabled using managed PCI device enable interface. * - * TODO: Struct pci_devres and find_pci_dr() only need to be here because - * they're used in pci.c. Port or move these functions to devres.c and - * then remove them from here. + * TODO: Struct pci_devres only needs to be here because they're used in pci.c. + * Port or move these functions to devres.c and then remove them from here. */ struct pci_devres { - unsigned int orig_intx:1; - unsigned int restore_intx:1; + /* + * TODO: + * This struct is now surplus. Remove it by refactoring pci/devres.c + */ }; -struct pci_devres *find_pci_dr(struct pci_dev *pdev); +int pcim_intx(struct pci_dev *dev, int enable); int pcim_request_region(struct pci_dev *pdev, int bar, const char *name); int pcim_request_region_exclusive(struct pci_dev *pdev, int bar, From f748a07a0b6430b3ed638e5df7ae5007a28eaf11 Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:24 +0200 Subject: [PATCH 11/13] PCI: Remove legacy pcim_release() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Thanks to preceding cleanup steps, pcim_release() is now not needed anymore and can be replaced by pcim_disable_device(), which is the exact counterpart to pcim_enable_device(). This permits removing further parts of the old PCI devres implementation. Replace pcim_release() with pcim_disable_device(). Remove the now unused function get_pci_dr(). Remove the struct pci_devres from pci.h. Link: https://lore.kernel.org/r/20240613115032.29098-12-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 53 +++++++++++++++++++++----------------------- drivers/pci/pci.h | 16 ------------- 2 files changed, 25 insertions(+), 44 deletions(-) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index f7b718438412..f4a0af2c4d79 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -477,48 +477,45 @@ int pcim_intx(struct pci_dev *pdev, int enable) return 0; } -static void pcim_release(struct device *gendev, void *res) +static void pcim_disable_device(void *pdev_raw) { - struct pci_dev *dev = to_pci_dev(gendev); + struct pci_dev *pdev = pdev_raw; - if (pci_is_enabled(dev) && !dev->pinned) - pci_disable_device(dev); -} - -static struct pci_devres *get_pci_dr(struct pci_dev *pdev) -{ - struct pci_devres *dr, *new_dr; - - dr = devres_find(&pdev->dev, pcim_release, NULL, NULL); - if (dr) - return dr; - - new_dr = devres_alloc(pcim_release, sizeof(*new_dr), GFP_KERNEL); - if (!new_dr) - return NULL; - return devres_get(&pdev->dev, new_dr, NULL, NULL); + if (!pdev->pinned) + pci_disable_device(pdev); } /** * pcim_enable_device - Managed pci_enable_device() * @pdev: PCI device to be initialized * - * Managed pci_enable_device(). + * Returns: 0 on success, negative error code on failure. + * + * Managed pci_enable_device(). Device will automatically be disabled on + * driver detach. */ int pcim_enable_device(struct pci_dev *pdev) { - struct pci_devres *dr; - int rc; + int ret; - dr = get_pci_dr(pdev); - if (unlikely(!dr)) - return -ENOMEM; + ret = devm_add_action(&pdev->dev, pcim_disable_device, pdev); + if (ret != 0) + return ret; - rc = pci_enable_device(pdev); - if (!rc) - pdev->is_managed = 1; + /* + * We prefer removing the action in case of an error over + * devm_add_action_or_reset() because the latter could theoretically be + * disturbed by users having pinned the device too soon. + */ + ret = pci_enable_device(pdev); + if (ret != 0) { + devm_remove_action(&pdev->dev, pcim_disable_device, pdev); + return ret; + } - return rc; + pdev->is_managed = true; + + return ret; } EXPORT_SYMBOL(pcim_enable_device); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 21cb44176350..e6d299b93c21 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -810,22 +810,6 @@ static inline pci_power_t mid_pci_get_power_state(struct pci_dev *pdev) } #endif -/* - * Managed PCI resources. This manages device on/off, INTx/MSI/MSI-X - * on/off and BAR regions. pci_dev itself records MSI/MSI-X status, so - * there's no need to track it separately. pci_devres is initialized - * when a device is enabled using managed PCI device enable interface. - * - * TODO: Struct pci_devres only needs to be here because they're used in pci.c. - * Port or move these functions to devres.c and then remove them from here. - */ -struct pci_devres { - /* - * TODO: - * This struct is now surplus. Remove it by refactoring pci/devres.c - */ -}; - int pcim_intx(struct pci_dev *dev, int enable); int pcim_request_region(struct pci_dev *pdev, int bar, const char *name); From ad78e05d654567e0a96f91d5db198469ddc2d4fb Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:25 +0200 Subject: [PATCH 12/13] PCI: Add managed pcim_iomap_range() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The only managed mapping function currently is pcim_iomap() which doesn't allow for mapping an area starting at a certain offset, which many drivers want. Add pcim_iomap_range() as an exported function. Link: https://lore.kernel.org/r/20240613115032.29098-13-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas --- drivers/pci/devres.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 2 ++ 2 files changed, 46 insertions(+) diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index f4a0af2c4d79..3780a9f9ec00 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -1027,3 +1027,47 @@ void pcim_iounmap_regions(struct pci_dev *pdev, int mask) } } EXPORT_SYMBOL(pcim_iounmap_regions); + +/** + * pcim_iomap_range - Create a ranged __iomap mapping within a PCI BAR + * @pdev: PCI device to map IO resources for + * @bar: Index of the BAR + * @offset: Offset from the begin of the BAR + * @len: Length in bytes for the mapping + * + * Returns: __iomem pointer on success, an IOMEM_ERR_PTR on failure. + * + * Creates a new IO-Mapping within the specified @bar, ranging from @offset to + * @offset + @len. + * + * The mapping will automatically get unmapped on driver detach. If desired, + * release manually only with pcim_iounmap(). + */ +void __iomem *pcim_iomap_range(struct pci_dev *pdev, int bar, + unsigned long offset, unsigned long len) +{ + void __iomem *mapping; + struct pcim_addr_devres *res; + + res = pcim_addr_devres_alloc(pdev); + if (!res) + return IOMEM_ERR_PTR(-ENOMEM); + + mapping = pci_iomap_range(pdev, bar, offset, len); + if (!mapping) { + pcim_addr_devres_free(res); + return IOMEM_ERR_PTR(-EINVAL); + } + + res->type = PCIM_ADDR_DEVRES_TYPE_MAPPING; + res->baseaddr = mapping; + + /* + * Ranged mappings don't get added to the legacy-table, since the table + * only ever keeps track of whole BARs. + */ + + devres_add(&pdev->dev, res); + return mapping; +} +EXPORT_SYMBOL(pcim_iomap_range); diff --git a/include/linux/pci.h b/include/linux/pci.h index 0c19f0717899..98893a89bb5b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2303,6 +2303,8 @@ int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name); int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask, const char *name); void pcim_iounmap_regions(struct pci_dev *pdev, int mask); +void __iomem *pcim_iomap_range(struct pci_dev *pdev, int bar, + unsigned long offset, unsigned long len); extern int pci_pci_problems; #define PCIPCI_FAIL 1 /* No PCI PCI DMA */ From f00059b4c1b068df108c70f86749b23f9080d2ba Mon Sep 17 00:00:00 2001 From: Philipp Stanner Date: Thu, 13 Jun 2024 13:50:26 +0200 Subject: [PATCH 13/13] drm/vboxvideo: fix mapping leaks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the PCI devres API was introduced to this driver, it was wrongly assumed that initializing the device with pcim_enable_device() instead of pci_enable_device() will make all PCI functions managed. This is wrong and was caused by the quite confusing PCI devres API in which some, but not all, functions become managed that way. The function pci_iomap_range() is never managed. Replace pci_iomap_range() with the managed function pcim_iomap_range(). Fixes: 8558de401b5f ("drm/vboxvideo: use managed pci functions") Link: https://lore.kernel.org/r/20240613115032.29098-14-pstanner@redhat.com Signed-off-by: Philipp Stanner Signed-off-by: Krzysztof Wilczyński Signed-off-by: Bjorn Helgaas Reviewed-by: Hans de Goede --- drivers/gpu/drm/vboxvideo/vbox_main.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/vboxvideo/vbox_main.c b/drivers/gpu/drm/vboxvideo/vbox_main.c index 42c2d8a99509..d4ade9325401 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_main.c +++ b/drivers/gpu/drm/vboxvideo/vbox_main.c @@ -42,12 +42,11 @@ static int vbox_accel_init(struct vbox_private *vbox) /* Take a command buffer for each screen from the end of usable VRAM. */ vbox->available_vram_size -= vbox->num_crtcs * VBVA_MIN_BUFFER_SIZE; - vbox->vbva_buffers = pci_iomap_range(pdev, 0, - vbox->available_vram_size, - vbox->num_crtcs * - VBVA_MIN_BUFFER_SIZE); - if (!vbox->vbva_buffers) - return -ENOMEM; + vbox->vbva_buffers = pcim_iomap_range( + pdev, 0, vbox->available_vram_size, + vbox->num_crtcs * VBVA_MIN_BUFFER_SIZE); + if (IS_ERR(vbox->vbva_buffers)) + return PTR_ERR(vbox->vbva_buffers); for (i = 0; i < vbox->num_crtcs; ++i) { vbva_setup_buffer_context(&vbox->vbva_info[i], @@ -116,11 +115,10 @@ int vbox_hw_init(struct vbox_private *vbox) DRM_INFO("VRAM %08x\n", vbox->full_vram_size); /* Map guest-heap at end of vram */ - vbox->guest_heap = - pci_iomap_range(pdev, 0, GUEST_HEAP_OFFSET(vbox), - GUEST_HEAP_SIZE); - if (!vbox->guest_heap) - return -ENOMEM; + vbox->guest_heap = pcim_iomap_range(pdev, 0, + GUEST_HEAP_OFFSET(vbox), GUEST_HEAP_SIZE); + if (IS_ERR(vbox->guest_heap)) + return PTR_ERR(vbox->guest_heap); /* Create guest-heap mem-pool use 2^4 = 16 byte chunks */ vbox->guest_pool = devm_gen_pool_create(vbox->ddev.dev, 4, -1,