From dc72c32e1fd872a9a4fdfe645283c9dcd68e556d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 22 Mar 2013 15:04:39 -0700 Subject: printk: Provide a wake_up_klogd() off-case wake_up_klogd() is useless when CONFIG_PRINTK=n because neither printk() nor printk_sched() are in use and there are actually no waiter on log_wait waitqueue. It should be a stub in this case for users like bust_spinlocks(). Otherwise this results in this warning when CONFIG_PRINTK=n and CONFIG_IRQ_WORK=n: kernel/built-in.o In function `wake_up_klogd': (.text.wake_up_klogd+0xb4): undefined reference to `irq_work_queue' To fix this, provide an off-case for wake_up_klogd() when CONFIG_PRINTK=n. There is much more from console_unlock() and other console related code in printk.c that should be moved under CONFIG_PRINTK. But for now, focus on a minimal fix as we passed the merged window already. [akpm@linux-foundation.org: include printk.h in bust_spinlocks.c] Signed-off-by: Frederic Weisbecker Reported-by: James Hogan Cc: James Hogan Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/bust_spinlocks.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/bust_spinlocks.c b/lib/bust_spinlocks.c index 9681d54b95d..f8e0e536739 100644 --- a/lib/bust_spinlocks.c +++ b/lib/bust_spinlocks.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -28,5 +29,3 @@ void __attribute__((weak)) bust_spinlocks(int yes) wake_up_klogd(); } } - - -- cgit v1.2.3-70-g09d2 From 8d640a51ec9e9cdefa680b67ad55f933eefc5923 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 22 Mar 2013 15:04:48 -0700 Subject: dma-debug: fix locking bug in check_unmap() In check_unmap() it is possible to get into a dead-locked state if dma_mapping_error is called. The problem is that the bucket is locked in check_unmap, and locked again by debug_dma_mapping_error which is called by dma_mapping_error. To resolve that we must release the lock on the bucket before making the call to dma_mapping_error. [akpm@linux-foundation.org: restore 80-col trickery to be consistent with the rest of the file] Signed-off-by: Alexander Duyck Cc: Joerg Roedel Reviewed-by: Shuah Khan Tested-by: Shuah Khan Cc: Jakub Kicinski Cc: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/dma-debug.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 5e396accd3d..d3e06a5e981 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -862,17 +862,21 @@ static void check_unmap(struct dma_debug_entry *ref) entry = bucket_find_exact(bucket, ref); if (!entry) { + /* must drop lock before calling dma_mapping_error */ + put_hash_bucket(bucket, &flags); + if (dma_mapping_error(ref->dev, ref->dev_addr)) { err_printk(ref->dev, NULL, - "DMA-API: device driver tries " - "to free an invalid DMA memory address\n"); - return; + "DMA-API: device driver tries to free an " + "invalid DMA memory address\n"); + } else { + err_printk(ref->dev, NULL, + "DMA-API: device driver tries to free DMA " + "memory it has not allocated [device " + "address=0x%016llx] [size=%llu bytes]\n", + ref->dev_addr, ref->size); } - err_printk(ref->dev, NULL, "DMA-API: device driver tries " - "to free DMA memory it has not allocated " - "[device address=0x%016llx] [size=%llu bytes]\n", - ref->dev_addr, ref->size); - goto out; + return; } if (ref->size != entry->size) { @@ -936,7 +940,6 @@ static void check_unmap(struct dma_debug_entry *ref) hash_bucket_del(entry); dma_entry_free(entry); -out: put_hash_bucket(bucket, &flags); } -- cgit v1.2.3-70-g09d2 From 96e7d7a1e0fc7780b4c1981c787e42473aa91a95 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 22 Mar 2013 15:04:49 -0700 Subject: dma-debug: update DMA debug API to better handle multiple mappings of a buffer There were reports of the igb driver unmapping buffers without calling dma_mapping_error. On closer inspection issues were found in the DMA debug API and how it handled multiple mappings of the same buffer. The issue I found is the fact that the debug_dma_mapping_error would only set the map_err_type to MAP_ERR_CHECKED in the case that the was only one match for device and device address. However in the case of non-IOMMU, multiple addresses existed and as a result it was not setting this field once a second mapping was instantiated. I have resolved this by changing the search so that it instead will now set MAP_ERR_CHECKED on the first buffer that matches the device and DMA address that is currently in the state MAP_ERR_NOT_CHECKED. A secondary side effect of this patch is that in the case of multiple buffers using the same address only the last mapping will have a valid map_err_type. The previous mappings will all end up with map_err_type set to MAP_ERR_CHECKED because of the dma_mapping_error call in debug_dma_map_page. However this behavior may be preferable as it means you will likely only see one real error per multi-mapped buffer, versus the current behavior of multiple false errors mer multi-mapped buffer. Signed-off-by: Alexander Duyck Cc: Joerg Roedel Reviewed-by: Shuah Khan Tested-by: Shuah Khan Cc: Jakub Kicinski Cc: Konrad Rzeszutek Wilk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/dma-debug.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/dma-debug.c b/lib/dma-debug.c index d3e06a5e981..d87a17a819d 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -1085,13 +1085,27 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) ref.dev = dev; ref.dev_addr = dma_addr; bucket = get_hash_bucket(&ref, &flags); - entry = bucket_find_exact(bucket, &ref); - if (!entry) - goto out; + list_for_each_entry(entry, &bucket->list, list) { + if (!exact_match(&ref, entry)) + continue; + + /* + * The same physical address can be mapped multiple + * times. Without a hardware IOMMU this results in the + * same device addresses being put into the dma-debug + * hash multiple times too. This can result in false + * positives being reported. Therefore we implement a + * best-fit algorithm here which updates the first entry + * from the hash which fits the reference value and is + * not currently listed as being checked. + */ + if (entry->map_err_type == MAP_ERR_NOT_CHECKED) { + entry->map_err_type = MAP_ERR_CHECKED; + break; + } + } - entry->map_err_type = MAP_ERR_CHECKED; -out: put_hash_bucket(bucket, &flags); } EXPORT_SYMBOL(debug_dma_mapping_error); -- cgit v1.2.3-70-g09d2 From a49b7e82cab0f9b41f483359be83f44fbb6b4979 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 13 Apr 2013 15:15:30 -0700 Subject: kobject: fix kset_find_obj() race with concurrent last kobject_put() Anatol Pomozov identified a race condition that hits module unloading and re-loading. To quote Anatol: "This is a race codition that exists between kset_find_obj() and kobject_put(). kset_find_obj() might return kobject that has refcount equal to 0 if this kobject is freeing by kobject_put() in other thread. Here is timeline for the crash in case if kset_find_obj() searches for an object tht nobody holds and other thread is doing kobject_put() on the same kobject: THREAD A (calls kset_find_obj()) THREAD B (calls kobject_put()) splin_lock() atomic_dec_return(kobj->kref), counter gets zero here ... starts kobject cleanup .... spin_lock() // WAIT thread A in kobj_kset_leave() iterate over kset->list atomic_inc(kobj->kref) (counter becomes 1) spin_unlock() spin_lock() // taken // it does not know that thread A increased counter so it remove obj from list spin_unlock() vfree(module) // frees module object with containing kobj // kobj points to freed memory area!! kobject_put(kobj) // OOPS!!!! The race above happens because module.c tries to use kset_find_obj() when somebody unloads module. The module.c code was introduced in commit 6494a93d55fa" Anatol supplied a patch specific for module.c that worked around the problem by simply not using kset_find_obj() at all, but rather than make a local band-aid, this just fixes kset_find_obj() to be thread-safe using the proper model of refusing the get a new reference if the refcount has already dropped to zero. See examples of this proper refcount handling not only in the kref documentation, but in various other equivalent uses of this pattern by grepping for atomic_inc_not_zero(). [ Side note: the module race does indicate that module loading and unloading is not properly serialized wrt sysfs information using the module mutex. That may require further thought, but this is the correct fix at the kobject layer regardless. ] Reported-analyzed-and-tested-by: Anatol Pomozov Cc: Greg Kroah-Hartman Cc: Al Viro Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- lib/kobject.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/kobject.c b/lib/kobject.c index e07ee1fcd6f..a65486613d7 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -529,6 +529,13 @@ struct kobject *kobject_get(struct kobject *kobj) return kobj; } +static struct kobject *kobject_get_unless_zero(struct kobject *kobj) +{ + if (!kref_get_unless_zero(&kobj->kref)) + kobj = NULL; + return kobj; +} + /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup @@ -751,7 +758,7 @@ struct kobject *kset_find_obj(struct kset *kset, const char *name) list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { - ret = kobject_get(k); + ret = kobject_get_unless_zero(k); break; } } -- cgit v1.2.3-70-g09d2 From 0635eb8a54cf0fea64b174bb68bc36b9c3d622db Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 15 Apr 2013 13:09:45 -0700 Subject: Move utf16 functions to kernel core and rename We want to be able to use the utf16 functions that are currently present in the EFI variables code in platform-specific code as well. Move them to the kernel core, and in the process rename them to accurately describe what they do - they don't handle UTF16, only UCS2. Signed-off-by: Matthew Garrett Signed-off-by: Matt Fleming --- drivers/firmware/Kconfig | 1 + drivers/firmware/efivars.c | 80 ++++++++++----------------------------------- include/linux/ucs2_string.h | 14 ++++++++ lib/Kconfig | 3 ++ lib/Makefile | 2 ++ lib/ucs2_string.c | 51 +++++++++++++++++++++++++++++ 6 files changed, 89 insertions(+), 62 deletions(-) create mode 100644 include/linux/ucs2_string.h create mode 100644 lib/ucs2_string.c (limited to 'lib') diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 42c759a4d04..3e532002e4d 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -39,6 +39,7 @@ config FIRMWARE_MEMMAP config EFI_VARS tristate "EFI Variable Support via sysfs" depends on EFI + select UCS2_STRING default n help If you say Y here, you are able to get EFI (Extensible Firmware diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index bf15d81d74e..182ce947117 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -80,6 +80,7 @@ #include #include #include +#include #include #include @@ -172,51 +173,6 @@ static void efivar_update_sysfs_entries(struct work_struct *); static DECLARE_WORK(efivar_work, efivar_update_sysfs_entries); static bool efivar_wq_enabled = true; -/* Return the number of unicode characters in data */ -static unsigned long -utf16_strnlen(efi_char16_t *s, size_t maxlength) -{ - unsigned long length = 0; - - while (*s++ != 0 && length < maxlength) - length++; - return length; -} - -static inline unsigned long -utf16_strlen(efi_char16_t *s) -{ - return utf16_strnlen(s, ~0UL); -} - -/* - * Return the number of bytes is the length of this string - * Note: this is NOT the same as the number of unicode characters - */ -static inline unsigned long -utf16_strsize(efi_char16_t *data, unsigned long maxlength) -{ - return utf16_strnlen(data, maxlength/sizeof(efi_char16_t)) * sizeof(efi_char16_t); -} - -static inline int -utf16_strncmp(const efi_char16_t *a, const efi_char16_t *b, size_t len) -{ - while (1) { - if (len == 0) - return 0; - if (*a < *b) - return -1; - if (*a > *b) - return 1; - if (*a == 0) /* implies *b == 0 */ - return 0; - a++; - b++; - len--; - } -} - static bool validate_device_path(struct efi_variable *var, int match, u8 *buffer, unsigned long len) @@ -268,7 +224,7 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer, u16 filepathlength; int i, desclength = 0, namelen; - namelen = utf16_strnlen(var->VariableName, sizeof(var->VariableName)); + namelen = ucs2_strnlen(var->VariableName, sizeof(var->VariableName)); /* Either "Boot" or "Driver" followed by four digits of hex */ for (i = match; i < match+4; i++) { @@ -291,7 +247,7 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer, * There's no stored length for the description, so it has to be * found by hand */ - desclength = utf16_strsize((efi_char16_t *)(buffer + 6), len - 6) + 2; + desclength = ucs2_strsize((efi_char16_t *)(buffer + 6), len - 6) + 2; /* Each boot entry must have a descriptor */ if (!desclength) @@ -581,7 +537,7 @@ efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count) spin_lock_irq(&efivars->lock); status = check_var_size_locked(efivars, new_var->Attributes, - new_var->DataSize + utf16_strsize(new_var->VariableName, 1024)); + new_var->DataSize + ucs2_strsize(new_var->VariableName, 1024)); if (status == EFI_SUCCESS || status == EFI_UNSUPPORTED) status = efivars->ops->set_variable(new_var->VariableName, @@ -759,7 +715,7 @@ static ssize_t efivarfs_file_write(struct file *file, * QueryVariableInfo() isn't supported by the firmware. */ - varsize = datasize + utf16_strsize(var->var.VariableName, 1024); + varsize = datasize + ucs2_strsize(var->var.VariableName, 1024); status = check_var_size(efivars, attributes, varsize); if (status != EFI_SUCCESS) { @@ -1211,7 +1167,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) inode = NULL; - len = utf16_strlen(entry->var.VariableName); + len = ucs2_strlen(entry->var.VariableName); /* name, plus '-', plus GUID, plus NUL*/ name = kmalloc(len + 1 + GUID_LEN + 1, GFP_ATOMIC); @@ -1469,8 +1425,8 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count, if (efi_guidcmp(entry->var.VendorGuid, vendor)) continue; - if (utf16_strncmp(entry->var.VariableName, efi_name, - utf16_strlen(efi_name))) { + if (ucs2_strncmp(entry->var.VariableName, efi_name, + ucs2_strlen(efi_name))) { /* * Check if an old format, * which doesn't support holding @@ -1482,8 +1438,8 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count, for (i = 0; i < DUMP_NAME_LEN; i++) efi_name_old[i] = name_old[i]; - if (utf16_strncmp(entry->var.VariableName, efi_name_old, - utf16_strlen(efi_name_old))) + if (ucs2_strncmp(entry->var.VariableName, efi_name_old, + ucs2_strlen(efi_name_old))) continue; } @@ -1561,8 +1517,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, * Does this variable already exist? */ list_for_each_entry_safe(search_efivar, n, &efivars->list, list) { - strsize1 = utf16_strsize(search_efivar->var.VariableName, 1024); - strsize2 = utf16_strsize(new_var->VariableName, 1024); + strsize1 = ucs2_strsize(search_efivar->var.VariableName, 1024); + strsize2 = ucs2_strsize(new_var->VariableName, 1024); if (strsize1 == strsize2 && !memcmp(&(search_efivar->var.VariableName), new_var->VariableName, strsize1) && @@ -1578,7 +1534,7 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, } status = check_var_size_locked(efivars, new_var->Attributes, - new_var->DataSize + utf16_strsize(new_var->VariableName, 1024)); + new_var->DataSize + ucs2_strsize(new_var->VariableName, 1024)); if (status && status != EFI_UNSUPPORTED) { spin_unlock_irq(&efivars->lock); @@ -1602,7 +1558,7 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, /* Create the entry in sysfs. Locking is not required here */ status = efivar_create_sysfs_entry(efivars, - utf16_strsize(new_var->VariableName, + ucs2_strsize(new_var->VariableName, 1024), new_var->VariableName, &new_var->VendorGuid); @@ -1632,8 +1588,8 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, * Does this variable already exist? */ list_for_each_entry_safe(search_efivar, n, &efivars->list, list) { - strsize1 = utf16_strsize(search_efivar->var.VariableName, 1024); - strsize2 = utf16_strsize(del_var->VariableName, 1024); + strsize1 = ucs2_strsize(search_efivar->var.VariableName, 1024); + strsize2 = ucs2_strsize(del_var->VariableName, 1024); if (strsize1 == strsize2 && !memcmp(&(search_efivar->var.VariableName), del_var->VariableName, strsize1) && @@ -1679,9 +1635,9 @@ static bool variable_is_present(efi_char16_t *variable_name, efi_guid_t *vendor) unsigned long strsize1, strsize2; bool found = false; - strsize1 = utf16_strsize(variable_name, 1024); + strsize1 = ucs2_strsize(variable_name, 1024); list_for_each_entry_safe(entry, n, &efivars->list, list) { - strsize2 = utf16_strsize(entry->var.VariableName, 1024); + strsize2 = ucs2_strsize(entry->var.VariableName, 1024); if (strsize1 == strsize2 && !memcmp(variable_name, &(entry->var.VariableName), strsize2) && diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h new file mode 100644 index 00000000000..cbb20afdbc0 --- /dev/null +++ b/include/linux/ucs2_string.h @@ -0,0 +1,14 @@ +#ifndef _LINUX_UCS2_STRING_H_ +#define _LINUX_UCS2_STRING_H_ + +#include /* for size_t */ +#include /* for NULL */ + +typedef u16 ucs2_char_t; + +unsigned long ucs2_strnlen(const ucs2_char_t *s, size_t maxlength); +unsigned long ucs2_strlen(const ucs2_char_t *s); +unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength); +int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len); + +#endif /* _LINUX_UCS2_STRING_H_ */ diff --git a/lib/Kconfig b/lib/Kconfig index 3958dc4389f..fe01d418b09 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -404,4 +404,7 @@ config OID_REGISTRY help Enable fast lookup object identifier registry. +config UCS2_STRING + tristate + endmenu diff --git a/lib/Makefile b/lib/Makefile index d7946ff75b2..6e2cc561f76 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -174,3 +174,5 @@ quiet_cmd_build_OID_registry = GEN $@ cmd_build_OID_registry = perl $(srctree)/$(src)/build_OID_registry $< $@ clean-files += oid_registry_data.c + +obj-$(CONFIG_UCS2_STRING) += ucs2_string.o diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c new file mode 100644 index 00000000000..6f500ef2301 --- /dev/null +++ b/lib/ucs2_string.c @@ -0,0 +1,51 @@ +#include +#include + +/* Return the number of unicode characters in data */ +unsigned long +ucs2_strnlen(const ucs2_char_t *s, size_t maxlength) +{ + unsigned long length = 0; + + while (*s++ != 0 && length < maxlength) + length++; + return length; +} +EXPORT_SYMBOL(ucs2_strnlen); + +unsigned long +ucs2_strlen(const ucs2_char_t *s) +{ + return ucs2_strnlen(s, ~0UL); +} +EXPORT_SYMBOL(ucs2_strlen); + +/* + * Return the number of bytes is the length of this string + * Note: this is NOT the same as the number of unicode characters + */ +unsigned long +ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength) +{ + return ucs2_strnlen(data, maxlength/sizeof(ucs2_char_t)) * sizeof(ucs2_char_t); +} +EXPORT_SYMBOL(ucs2_strsize); + +int +ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len) +{ + while (1) { + if (len == 0) + return 0; + if (*a < *b) + return -1; + if (*a > *b) + return 1; + if (*a == 0) /* implies *b == 0 */ + return 0; + a++; + b++; + len--; + } +} +EXPORT_SYMBOL(ucs2_strncmp); -- cgit v1.2.3-70-g09d2 From c729de8fcea37a1c444e81857eace12494c804a9 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 15 Apr 2013 22:23:45 -0700 Subject: x86, kdump: Set crashkernel_low automatically Chao said that kdump does does work well on his system on 3.8 without extra parameter, even iommu does not work with kdump. And now have to append crashkernel_low=Y in first kernel to make kdump work. We have now modified crashkernel=X to allocate memory beyong 4G (if available) and do not allocate low range for crashkernel if the user does not specify that with crashkernel_low=Y. This causes regression if iommu is not enabled. Without iommu, swiotlb needs to be setup in first 4G and there is no low memory available to second kernel. Set crashkernel_low automatically if the user does not specify that. For system that does support IOMMU with kdump properly, user could specify crashkernel_low=0 to save that 72M low ram. -v3: add swiotlb_size() according to Konrad. -v4: add comments what 8M is for according to hpa. also update more crashkernel_low= in kernel-parameters.txt -v5: update changelog according to Vivek. -v6: Change description about swiotlb referring according to HATAYAMA. Reported-by: WANG Chao Tested-by: WANG Chao Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1366089828-19692-2-git-send-email-yinghai@kernel.org Acked-by: Vivek Goyal Signed-off-by: H. Peter Anvin --- Documentation/kernel-parameters.txt | 14 +++++++++++--- arch/x86/kernel/setup.c | 21 ++++++++++++++++++--- include/linux/swiotlb.h | 1 + lib/swiotlb.c | 19 +++++++++++++++---- 4 files changed, 45 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 4609e81dbc3..cff672da248 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -596,9 +596,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. is selected automatically. Check Documentation/kdump/kdump.txt for further details. - crashkernel_low=size[KMG] - [KNL, x86] parts under 4G. - crashkernel=range1:size1[,range2:size2,...][@offset] [KNL] Same as above, but depends on the memory in the running system. The syntax of range is @@ -606,6 +603,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted. a memory unit (amount[KMG]). See also Documentation/kdump/kdump.txt for an example. + crashkernel_low=size[KMG] + [KNL, x86_64] range under 4G. When crashkernel= is + passed, kernel allocate physical memory region + above 4G, that cause second kernel crash on system + that require some amount of low memory, e.g. swiotlb + requires at least 64M+32K low memory. Kernel would + try to allocate 72M below 4G automatically. + This one let user to specify own low range under 4G + for second kernel instead. + 0: to disable low allocation. + cs89x0_dma= [HW,NET] Format: diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 90d8cc930f5..12349202cae 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -521,19 +521,34 @@ static void __init reserve_crashkernel_low(void) unsigned long long low_base = 0, low_size = 0; unsigned long total_low_mem; unsigned long long base; + bool auto_set = false; int ret; total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); - if (ret != 0 || low_size <= 0) - return; + if (ret != 0) { + /* + * two parts from lib/swiotlb.c: + * swiotlb size: user specified with swiotlb= or default. + * swiotlb overflow buffer: now is hardcoded to 32k. + * We round it to 8M for other buffers that + * may need to stay low too. + */ + low_size = swiotlb_size_or_default() + (8UL<<20); + auto_set = true; + } else { + /* passed with crashkernel_low=0 ? */ + if (!low_size) + return; + } low_base = memblock_find_in_range(low_size, (1ULL<<32), low_size, alignment); if (!low_base) { - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + if (!auto_set) + pr_info("crashkernel low reservation failed - No suitable area found.\n"); return; } diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 2de42f9401d..a5ffd32642f 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -25,6 +25,7 @@ extern int swiotlb_force; extern void swiotlb_init(int verbose); int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern unsigned long swiotlb_nr_tbl(void); +unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); /* diff --git a/lib/swiotlb.c b/lib/swiotlb.c index bfe02b8fc55..d23762e6652 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -105,9 +105,9 @@ setup_io_tlb_npages(char *str) if (!strcmp(str, "force")) swiotlb_force = 1; - return 1; + return 0; } -__setup("swiotlb=", setup_io_tlb_npages); +early_param("swiotlb", setup_io_tlb_npages); /* make io_tlb_overflow tunable too? */ unsigned long swiotlb_nr_tbl(void) @@ -115,6 +115,18 @@ unsigned long swiotlb_nr_tbl(void) return io_tlb_nslabs; } EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); + +/* default to 64MB */ +#define IO_TLB_DEFAULT_SIZE (64UL<<20) +unsigned long swiotlb_size_or_default(void) +{ + unsigned long size; + + size = io_tlb_nslabs << IO_TLB_SHIFT; + + return size ? size : (IO_TLB_DEFAULT_SIZE); +} + /* Note that this doesn't work with highmem page */ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev, volatile void *address) @@ -188,8 +200,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) void __init swiotlb_init(int verbose) { - /* default to 64MB */ - size_t default_size = 64UL<<20; + size_t default_size = IO_TLB_DEFAULT_SIZE; unsigned char *vstart; unsigned long bytes; -- cgit v1.2.3-70-g09d2