Re: [PATCH 3/3] x86/mm: disable ioremap free page handling on x86-PAE

On Mon, 2018-04-30 at 11:59 -0600, Toshi Kani wrote: > ioremap() supports pmd mappings on x86-PAE. However, kernel's pmd > tables are not shared among processes on x86-PAE. Therefore, any > update to sync'd pmd entries need re-syncing. Freeing a pte page > also leads to a vmalloc fault and hits

Re: [PATCH] Revert "x86/mm: implement free pmd/pte page interfaces"

On Fri, 2018-04-27 at 08:28 +0200, Ingo Molnar wrote: > * Kani, Toshi <toshi.k...@hpe.com> wrote: > > > On Thu, 2018-04-26 at 17:14 +0200, Joerg Roedel wrote: > > > From: Joerg Roedel <jroe...@suse.de> > > > > > > This reve

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Fri, 2018-04-27 at 09:37 +0200, j...@8bytes.org wrote: > On Thu, Apr 26, 2018 at 10:30:14PM +0000, Kani, Toshi wrote: > > Thanks for the clarification. After reading through SDM one more time, I > > agree that we need a TLB purge here. Here is my current understanding. >

Re: [PATCH v3 2/3] ioremap: Update pgtable free interfaces with addr

On Thu, 2018-05-17 at 08:47 +0200, Michal Hocko wrote: > On Wed 16-05-18 17:32:06, Kani Toshimitsu wrote: > > From: Chintan Pandya > > > > This patch ("mm/vmalloc: Add interfaces to free unmapped > > page table") adds following 2 interfaces to free the page > > table in

Re: [PATCH v2 1/3] x86/mm: disable ioremap free page handling on x86-PAE

On Wed, 2018-05-16 at 19:00 +0800, kbuild test robot wrote: > Hi Toshi, > > Thank you for the patch! Yet something to improve: > > [auto build test ERROR on arm64/for-next/core] > [also build test ERROR on v4.17-rc5 next-20180515] > [cannot apply to tip/x86/core] > [if your patch is applied to

Re: [PATCH 2/3] x86/mm: add TLB purge to free pmd/pte page interfaces

On Tue, 2018-05-15 at 16:05 +0200, Joerg Roedel wrote: > On Mon, Apr 30, 2018 at 11:59:24AM -0600, Toshi Kani wrote: > > int pud_free_pmd_page(pud_t *pud, unsigned long addr) > > { > > - pmd_t *pmd; > > + pmd_t *pmd, *pmd_sv; > > + pte_t *pte; > > int i; > > > > if

Re: [PATCH v9 3/4] arm64: Implement page table free interfaces

On Wed, 2018-05-23 at 15:01 +0100, Will Deacon wrote: > Hi Chintan, > > [as a side note: I'm confused on the status of this patch series, as part > of it was reposted separately by Toshi. Please can you work together?] I do not know the status of my patch series, either... That being said, I

Re: [PATCH v3 3/3] x86/mm: add TLB purge to free pmd/pte page interfaces

On Wed, 2018-05-30 at 06:59 +0200, j...@8bytes.org wrote: > On Tue, May 29, 2018 at 04:10:24PM +0000, Kani, Toshi wrote: > > Can you explain why you think allocating a page here is a major problem? > > Because a larger allocation is more likely to fail. And if you fail the > al

Re: [PATCH v3 3/3] x86/mm: add TLB purge to free pmd/pte page interfaces

On Tue, 2018-05-29 at 16:44 +0200, Joerg Roedel wrote: > On Wed, May 16, 2018 at 05:32:07PM -0600, Toshi Kani wrote: > > pmd = (pmd_t *)pud_page_vaddr(*pud); > > + pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL); > > + if (!pmd_sv) > > + return 0; > > So your code still needs to

Re: [PATCH v3 0/3] fix free pmd/pte page handlings on x86

this patch breaks the current ioremap() callers using 2MB mappings by failing pmd_free_pte_page(). 2. Add a special page list, instead of memory alloc, in patch 3/3 Quoting his concerns about the memory allocation: === On Tue, May 29, 2018 at 04:10:24PM +, Kani, Toshi wrote: > Can you expl

Re: [PATCH v4 2/3] ioremap: Update pgtable free interfaces with addr

On Wed, 2018-06-27 at 16:56 +0100, Will Deacon wrote: > Hi Toshi, > > On Wed, Jun 27, 2018 at 08:13:47AM -0600, Toshi Kani wrote: > > From: Chintan Pandya > > > > The following kernel panic was observed on ARM64 platform due to a stale > > TLB entry. > > > > 1. ioremap with 4K size, a valid

Re: [PATCH v3 0/3] fix free pmd/pte page handlings on x86

On Sun, 2018-06-24 at 15:19 +0200, Thomas Gleixner wrote: > On Wed, 16 May 2018, Toshi Kani wrote: > > > This series fixes two issues in the x86 ioremap free page handlings > > for pud/pmd mappings. > > > > Patch 01 fixes BUG_ON on x86-PAE reported by Joerg. It disables > > the free page

Re: [PATCH v3 0/3] fix free pmd/pte page handlings on x86

On Mon, 2018-06-25 at 19:53 +0200, Michal Hocko wrote: > On Mon 25-06-18 14:56:26, Kani Toshimitsu wrote: > > On Sun, 2018-06-24 at 15:19 +0200, Thomas Gleixner wrote: > > > On Wed, 16 May 2018, Toshi Kani wrote: > > > > > > > This series fixes two issues in the x86 ioremap free page handlings >

Re: [PATCH v3 1/3] pmem: only set QUEUE_FLAG_DAX for fsdax mode

On Tue, 2018-06-26 at 15:13 -0400, Mike Snitzer wrote: > On Tue, Jun 26 2018 at 3:07pm -0400, > Dan Williams wrote: > > > On Tue, Jun 26, 2018 at 11:58 AM, Mike Snitzer wrote: > > > On Tue, Jun 26 2018 at 2:52pm -0400, > > > Dan Williams wrote: > > > > > > > On Tue, Jun 26, 2018 at 10:59

Re: [PATCH] Revert "x86/mm: implement free pmd/pte page interfaces"

On Thu, 2018-04-26 at 17:14 +0200, Joerg Roedel wrote: > From: Joerg Roedel > > This reverts commit 28ee90fe6048fa7b7ceaeb8831c0e4e454a4cf89. > > This commit is broken for x86, as it unmaps the PTE and PMD > pages and immediatly frees them without doing a TLB flush. > >

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Thu, 2018-04-26 at 19:23 +0200, j...@8bytes.org wrote: > On Thu, Apr 26, 2018 at 04:21:19PM +0000, Kani, Toshi wrote: > > All pages under the pmd had been unmapped and then lazy TLB purged with > > INVLPG before coming to this code path. Speculation is not allowed to > >

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Thu, 2018-04-26 at 16:19 +0200, Joerg Roedel wrote: > Hi Toshi, Andrew, > > this patch(-set) is broken in several ways, please see below. > > On Wed, Mar 14, 2018 at 12:01:55PM -0600, Toshi Kani wrote: > > Implement pud_free_pmd_page() and pmd_free_pte_page() on x86, which > > clear a given

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Thu, 2018-04-26 at 22:07 +0200, j...@8bytes.org wrote: > On Thu, Apr 26, 2018 at 05:49:58PM +0000, Kani, Toshi wrote: > > On Thu, 2018-04-26 at 19:23 +0200, j...@8bytes.org wrote: > > > So the PMD entry you clear can still be in a page-walk cache and this > > > nee

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Mon, 2018-04-30 at 13:00 +0530, Chintan Pandya wrote: > > On 4/29/2018 2:24 AM, Kani, Toshi wrote: > > On Sat, 2018-04-28 at 11:02 +0200, j...@8bytes.org wrote: > > > On Fri, Apr 27, 2018 at 02:31:51PM +, Kani, Toshi wrote: > > > > So, we can ad

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Sat, 2018-04-28 at 11:02 +0200, j...@8bytes.org wrote: > On Fri, Apr 27, 2018 at 02:31:51PM +0000, Kani, Toshi wrote: > > So, we can add the step 2 on top of this patch. > > 1. Clear pud/pmd entry. > > 2. System wide TLB flush <-- TO BE ADDED BY NEW PATCH > > 3

Re: [RFC patch] ioremap: don't set up huge I/O mappings when p4d/pud/pmd is zero

On Thu, 2017-12-28 at 19:24 +0800, Hanjun Guo wrote: > From: Hanjun Guo > > When we using iounmap() to free the 4K mapping, it just clear the PTEs > but leave P4D/PUD/PMD unchanged, also will not free the memory of page > tables. > > This will cause issues on ARM64

Re: [RFC patch] ioremap: don't set up huge I/O mappings when p4d/pud/pmd is zero

On Sat, 2018-01-06 at 17:46 +0800, Hanjun Guo wrote: > On 2018/1/6 6:15, Kani, Toshi wrote: > > On Thu, 2017-12-28 at 19:24 +0800, Hanjun Guo wrote: > > > From: Hanjun Guo <hanjun@linaro.org> > > > > > > When we using iounmap() to free the 4K mappi

Re: [PATCH] acpi, nfit: fix register dimm error handling

On Fri, 2018-02-02 at 12:31 -0800, Dan Williams wrote: > On Fri, Feb 2, 2018 at 1:00 PM, Toshi Kani wrote: > > A NULL pointer reference kernel bug was observed when > > acpi_nfit_add_dimm() called in acpi_nfit_register_dimms() > > failed. This error path does not set

Re: [RFC patch] ioremap: don't set up huge I/O mappings when p4d/pud/pmd is zero

On Tue, 2018-02-20 at 14:54 +0530, Chintan Pandya wrote: > > On 12/28/2017 4:54 PM, Hanjun Guo wrote: > > From: Hanjun Guo > > > > When we using iounmap() to free the 4K mapping, it just clear the PTEs > > but leave P4D/PUD/PMD unchanged, also will not free the memory of

Re: [PATCH v2] EDAC, ghes: use CPER module handles to locate DIMMs

On Thu, 2018-08-30 at 18:37 +, Fan Wu wrote: > For platforms whose firmwares provide valid module handles > (SMBIOS type 17) in error records, this patch uses the module > handles to locate corresponding DIMMs and enables per-DIMM > error counter update. > > Signed-off-by: Fan Wu Tested on

Re: [PATCH 1/2] mm/vmalloc: Add interfaces to free unused page table

On Wed, 2018-03-07 at 14:54 -0800, Andrew Morton wrote: > On Wed, 7 Mar 2018 11:32:26 -0700 Toshi Kani wrote: > > > On architectures with CONFIG_HAVE_ARCH_HUGE_VMAP set, ioremap() > > may create pud/pmd mappings. Kernel panic was observed on arm64 > > systems with

Re: [PATCH 2/2] x86/mm: implement free pmd/pte page interfaces

On Wed, 2018-03-07 at 15:01 -0800, Andrew Morton wrote: > On Wed, 7 Mar 2018 11:32:27 -0700 Toshi Kani wrote: > > > Implement pud_free_pmd_page() and pmd_free_pte_page() on x86, which > > clear a given pud/pmd entry and free up lower level page table(s). > > Address range

Re: 答复: [RFC patch] ioremap: don't set up huge I/O mappings when p4d/pud/pmd is zero

On Mon, 2018-02-26 at 20:53 +0800, Hanjun Guo wrote: > On 2018/2/26 19:04, Will Deacon wrote: > > On Mon, Feb 26, 2018 at 06:57:20PM +0800, Hanjun Guo wrote: > > > On 2018/2/21 19:57, Will Deacon wrote: > > > > [sorry, trying to deal with top-posting here] > > > > > > > > On Wed, Feb 21, 2018 at

Re: 答复: [RFC patch] ioremap: don't set up huge I/O mappings when p4d/pud/pmd is zero

On Tue, 2018-02-27 at 19:59 +, Will Deacon wrote: > On Tue, Feb 27, 2018 at 07:49:42PM +0000, Kani, Toshi wrote: > > On Mon, 2018-02-26 at 20:53 +0800, Hanjun Guo wrote: > > > On 2018/2/26 19:04, Will Deacon wrote: > > > > On Mon, Feb 26, 2018 at 06:5

Re: [PATCH v2 2/4] ioremap: Implement TLB_INV before huge mapping

On Thu, 2018-03-15 at 18:15 +0530, Chintan Pandya wrote: > Huge mapping changes PMD/PUD which could have > valid previous entries. This requires proper > TLB maintanance on some architectures, like > ARM64. > > Implent BBM (break-before-make) safe TLB > invalidation. > > Here, I've used

Re: Kernel page fault in vmalloc_fault() after a preempted ioremap

On Thu, 2018-03-08 at 22:38 +, Andy Lutomirski wrote: > On Thu, Mar 8, 2018 at 9:43 PM, Kani, Toshi <toshi.k...@hpe.com> wrote: > > On Thu, 2018-03-08 at 14:34 -0600, Gratian Crisan wrote: : > > > > Thanks for the report and analysis! I believe pud_large() and

Re: [PATCH 1/2] mm/vmalloc: Add interfaces to free unused page table

On Thu, 2018-03-08 at 18:04 +, Will Deacon wrote: : > > diff --git a/lib/ioremap.c b/lib/ioremap.c > > index b808a390e4c3..54e5bbaa3200 100644 > > --- a/lib/ioremap.c > > +++ b/lib/ioremap.c > > @@ -91,7 +91,8 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned > > long addr, > > >

Re: Kernel page fault in vmalloc_fault() after a preempted ioremap

On Thu, 2018-03-08 at 14:34 -0600, Gratian Crisan wrote: > Hi all, > > We are seeing kernel page faults happening on module loads with certain > drivers like the i915 video driver[1]. This was initially discovered on > a 4.9 PREEMPT_RT kernel. It takes 5 days on average to reproduce using a >

Re: [PATCH v2 1/2] mm/vmalloc: Add interfaces to free unmapped page table

On Wed, 2018-03-14 at 15:38 -0700, Andrew Morton wrote: > On Wed, 14 Mar 2018 12:01:54 -0600 Toshi Kani wrote: : > > whoops. > > --- > a/include/asm-generic/pgtable.h~mm-vmalloc-add-interfaces-to-free-unmapped-page-table-fix > +++ a/include/asm-generic/pgtable.h > @@

Re: [PATCH v1 0/4] Fix issues with huge mapping in ioremap

On Thu, 2018-03-15 at 12:47 +0530, Chintan Pandya wrote: > > On 3/14/2018 8:08 PM, Kani, Toshi wrote: > > On Wed, 2018-03-14 at 14:18 +0530, Chintan Pandya wrote: > > > Note: I was working on these patches for quite sometime > > > and realized that Tosh

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Thu, 2018-03-15 at 13:09 +0530, Chintan Pandya wrote: > > On 3/14/2018 11:31 PM, Toshi Kani wrote: > > Implement pud_free_pmd_page() and pmd_free_pte_page() on x86, which > > clear a given pud/pmd entry and free up lower level page table(s). > > Address range associated with the pud/pmd entry

Re: [PATCH 1/2] mm/vmalloc: Add interfaces to free unused page table

On Thu, 2018-03-08 at 14:07 -0800, Matthew Wilcox wrote: > On Thu, Mar 08, 2018 at 03:56:30PM +0000, Kani, Toshi wrote: > > On Wed, 2018-03-07 at 20:00 -0800, Matthew Wilcox wrote: > > > On Wed, Mar 07, 2018 at 11:32:26AM -0700, Toshi Kani wrote: > > > > +/** > &g

Re: [PATCH 1/2] mm/vmalloc: Add interfaces to free unused page table

On Wed, 2018-03-07 at 20:00 -0800, Matthew Wilcox wrote: > On Wed, Mar 07, 2018 at 11:32:26AM -0700, Toshi Kani wrote: > > +/** > > + * pud_free_pmd_page - clear pud entry and free pmd page > > + * > > + * Returns 1 on success and 0 on failure (pud not cleared). > > + */ > > +int

Re: [PATCH v1 0/4] Fix issues with huge mapping in ioremap

On Wed, 2018-03-14 at 14:18 +0530, Chintan Pandya wrote: > Note: I was working on these patches for quite sometime > and realized that Toshi Kani has shared some patches > addressing the same isssue with subject > "[PATCH 0/2] fix memory leak / panic in ioremap huge pages". > I've taken slightly

Re: [PATCH 2/2] x86/mm: remove pointless checks in vmalloc_fault

On Wed, 2018-03-14 at 20:27 +0100, Thomas Gleixner wrote: > On Tue, 13 Mar 2018, Toshi Kani wrote: > > > vmalloc_fault() sets user's pgd or p4d from the kernel page table. > > Once it's set, all tables underneath are identical. There is no point > > of following the same page table with two

Re: [PATCH 2/2] x86/mm: remove pointless checks in vmalloc_fault

On Wed, 2018-03-14 at 20:56 +0100, Thomas Gleixner wrote: > On Wed, 14 Mar 2018, Kani, Toshi wrote: > > On Wed, 2018-03-14 at 20:27 +0100, Thomas Gleixner wrote: > > > On Tue, 13 Mar 2018, Toshi Kani wrote: > > > > > > > vmalloc_fault() sets user'

Re: [RFC PATCH] lib/ioremap: Avoid triggering BUG_ON when end is not PAGE_ALIGN

On Fri, 2018-03-30 at 12:49 +0800, Yisheng Xie wrote: > Zhou reported a bug on Hisilicon arm64 D06 platform with 64KB page size: : > The cause is the size of PCI IO resource is 32KB, which is 4K aligned but > not 64KB aligned, so when do ioremap_pte_range(), its incoming end is not > PAGE_ALIGN

Re: [PATCH 4.4 20/43] mm/vmalloc: add interfaces to free unmapped page table

On Tue, 2018-03-27 at 13:31 -0700, Nathan Chancellor wrote: > On Tue, Mar 27, 2018 at 03:17:00PM -0500, Dan Rue wrote: > > On Tue, Mar 27, 2018 at 06:27:24PM +0200, Greg Kroah-Hartman wrote: > > > 4.4-stable review patch. If anyone has any objections, please let me > > > know. > > > : > > > >

Re: [PATCH 4.4 20/43] mm/vmalloc: add interfaces to free unmapped page table

On Tue, 2018-03-27 at 15:17 -0500, Dan Rue wrote: > On Tue, Mar 27, 2018 at 06:27:24PM +0200, Greg Kroah-Hartman wrote: > > 4.4-stable review patch. If anyone has any objections, please let me know. > > > > -- > > > > From: Toshi Kani > > > > commit

Re: [PATCH 4.4 20/43] mm/vmalloc: add interfaces to free unmapped page table

n Chancellor wrote: > > > > On Tue, Mar 27, 2018 at 08:40:56PM +, Kani, Toshi wrote: > > > > > On Tue, 2018-03-27 at 13:31 -0700, Nathan Chancellor wrote: > > > > > > On Tue, Mar 27, 2018 at 03:17:00PM -0500, Dan Rue wrote: > > > > > > &g

Re: [PATCH v2 2/4] ioremap: Implement TLB_INV before huge mapping

On Fri, 2018-03-16 at 13:10 +0530, Chintan Pandya wrote: > > On 3/15/2018 9:42 PM, Kani, Toshi wrote: > > On Thu, 2018-03-15 at 18:15 +0530, Chintan Pandya wrote: > > > Huge mapping changes PMD/PUD which could have > > > valid previous entries. This requires proper

Re: [PATCH] acpi, numa: fix pxm to online numa node associations

On Thu, 2018-03-15 at 20:08 -0700, Dan Williams wrote: > Commit 99759869faf1 "acpi: Add acpi_map_pxm_to_online_node()" added > support for mapping a given proximity to its nearest, by SLIT distance, > online node. However, it sometimes returns unexpected results due to the > fact that it switches

Re: [PATCH v4 1/3] ioremap: Update pgtable free interfaces with addr

On Tue, 2018-03-20 at 17:15 +0530, Chintan Pandya wrote: > This patch ("mm/vmalloc: Add interfaces to free unmapped > page table") adds following 2 interfaces to free the page > table in case we implement huge mapping. > > pud_free_pmd_page() and pmd_free_pte_page() > > Some architectures (like

Re: [PATCH] nfit: skip region registration for incomplete control regions

On Wed, 2018-03-21 at 21:42 -0700, Dan Williams wrote: > Per the ACPI specification the only functional purpose for a DIMM > Control Region to be mapped into the system physical address space, from > an OSPM perspective, is to support block-apertures. However, there are > some BIOSen that publish

Re: [PATCH v3 2/3] arm64: Implement page table free interfaces

On Mon, 2018-03-19 at 18:10 +0530, Chintan Pandya wrote: > Implement pud_free_pmd_page() and pmd_free_pte_page(). > > Implementation requires, > 1) Freeing of the un-used next level page tables > 2) Clearing off the current pud/pmd entry > 3) Invalidate TLB which could have previously >

Re: [PATCH v3 1/3] ioremap: Update pgtable free interfaces with addr

On Mon, 2018-03-19 at 18:10 +0530, Chintan Pandya wrote: > This patch ("mm/vmalloc: Add interfaces to free unmapped > page table") adds following 2 interfaces to free the page > table in case we implement huge mapping. > > pud_free_pmd_page() and pmd_free_pte_page() > > Some architectures (like

Re: [PATCH v2 00/10] Copy Offload in NVMe Fabrics with P2P PCI Memory

On Fri, 2018-03-02 at 09:34 +1100, Benjamin Herrenschmidt wrote: > On Thu, 2018-03-01 at 14:31 -0800, Linus Torvalds wrote: > > On Thu, Mar 1, 2018 at 2:06 PM, Benjamin Herrenschmidt > > wrote: > > > > > > Could be that x86 has the smarts to do the right thing, still trying to

Re: [PATCH v2 00/10] Copy Offload in NVMe Fabrics with P2P PCI Memory

On Fri, 2018-03-02 at 08:57 -0800, Linus Torvalds wrote: > On Fri, Mar 2, 2018 at 8:22 AM, Kani, Toshi <toshi.k...@hpe.com> wrote: > > > > FWIW, this thing is called MTRRs on x86, which are initialized by BIOS. > > No. > > Or rather, that's simply ju

Re: [PATCH v4 2/3] ioremap: Update pgtable free interfaces with addr

On Fri, 2018-06-29 at 13:23 +0100, Will Deacon wrote: > Hi Toshi, Thomas, > > On Wed, Jun 27, 2018 at 04:13:22PM +0000, Kani, Toshi wrote: > > On Wed, 2018-06-27 at 16:56 +0100, Will Deacon wrote: > > > On Wed, Jun 27, 2018 at 08:13:47AM -0600, Toshi Kani wrote: >

Re: [PATCH] libnvdimm: Fix __nd_ioctl() to check error in cmd_rc

On Wed, 2018-11-07 at 11:34 -0800, Dan Williams wrote: > On Wed, Nov 7, 2018 at 10:52 AM Toshi Kani wrote: > > > > ndctl zero-labels completes with a large number of zeroed nmems when > > it fails to do zeroing on a protected NVDIMM. > > > > # ndctl zero-labels nmem1 > > zeroed 65504 nmems

Re: [PATCH 1/5] ioremap: Rework pXd_free_pYd_page() API

On Wed, 2018-09-12 at 11:26 +0100, Will Deacon wrote: > The recently merged API for ensuring break-before-make on page-table > entries when installing huge mappings in the vmalloc/ioremap region is > fairly counter-intuitive, resulting in the arch freeing functions > (e.g. pmd_free_pte_page())

Re: [PATCH 3/5] x86: pgtable: Drop pXd_none() checks from pXd_free_pYd_table()

On Wed, 2018-09-12 at 11:26 +0100, Will Deacon wrote: > Now that the core code checks this for us, we don't need to do it in the > backend. > > Cc: Chintan Pandya > Cc: Toshi Kani > Cc: Thomas Gleixner > Cc: Michal Hocko > Cc: Andrew Morton > Signed-off-by: Will Deacon > --- >

Re: [PATCH 1/5] ioremap: Rework pXd_free_pYd_page() API

On Fri, 2018-09-14 at 14:36 -0600, Toshi Kani wrote: > On Wed, 2018-09-12 at 11:26 +0100, Will Deacon wrote: > > The recently merged API for ensuring break-before-make on page-table > > entries when installing huge mappings in the vmalloc/ioremap region is > > fairly counter-intuitive, resulting

Re: [PATCH 1/5] ioremap: Rework pXd_free_pYd_page() API

On Mon, 2018-09-17 at 12:33 +0100, Will Deacon wrote: > On Fri, Sep 14, 2018 at 09:10:49PM +0000, Kani, Toshi wrote: > > On Fri, 2018-09-14 at 14:36 -0600, Toshi Kani wrote: > > > On Wed, 2018-09-12 at 11:26 +0100, Will Deacon wrote: > > > > The recently merged API

Re: [PATCH 3/5] x86: pgtable: Drop pXd_none() checks from pXd_free_pYd_table()

On Mon, 2018-09-17 at 12:33 +0100, Will Deacon wrote: > On Fri, Sep 14, 2018 at 08:37:48PM +0000, Kani, Toshi wrote: > > On Wed, 2018-09-12 at 11:26 +0100, Will Deacon wrote: > > > Now that the core code checks this for us, we don't need to do it in the > > > backen

Re: [PATCH 5/5] lib/ioremap: Ensure break-before-make is used for huge p4d mappings

: Toshi Kani > Cc: Thomas Gleixner > Cc: Michal Hocko > Cc: Andrew Morton > Signed-off-by: Will Deacon Thanks. This keeps the p4d path consistent. Reviewed-by: Toshi Kani -Toshi

Re: [PATCH v1 0/4] Fix issues with huge mapping in ioremap

On Wed, 2018-03-14 at 14:18 +0530, Chintan Pandya wrote: > Note: I was working on these patches for quite sometime > and realized that Toshi Kani has shared some patches > addressing the same isssue with subject > "[PATCH 0/2] fix memory leak / panic in ioremap huge pages". > I've taken slightly

Re: [PATCH 2/2] x86/mm: remove pointless checks in vmalloc_fault

On Wed, 2018-03-14 at 20:27 +0100, Thomas Gleixner wrote: > On Tue, 13 Mar 2018, Toshi Kani wrote: > > > vmalloc_fault() sets user's pgd or p4d from the kernel page table. > > Once it's set, all tables underneath are identical. There is no point > > of following the same page table with two

Re: [PATCH 2/2] x86/mm: remove pointless checks in vmalloc_fault

On Wed, 2018-03-14 at 20:56 +0100, Thomas Gleixner wrote: > On Wed, 14 Mar 2018, Kani, Toshi wrote: > > On Wed, 2018-03-14 at 20:27 +0100, Thomas Gleixner wrote: > > > On Tue, 13 Mar 2018, Toshi Kani wrote: > > > > > > > vmalloc_fault() sets user'

Re: [PATCH 4.4 20/43] mm/vmalloc: add interfaces to free unmapped page table

On Tue, 2018-03-27 at 15:17 -0500, Dan Rue wrote: > On Tue, Mar 27, 2018 at 06:27:24PM +0200, Greg Kroah-Hartman wrote: > > 4.4-stable review patch. If anyone has any objections, please let me know. > > > > -- > > > > From: Toshi Kani > > > > commit

Re: [PATCH 4.4 20/43] mm/vmalloc: add interfaces to free unmapped page table

On Tue, 2018-03-27 at 13:31 -0700, Nathan Chancellor wrote: > On Tue, Mar 27, 2018 at 03:17:00PM -0500, Dan Rue wrote: > > On Tue, Mar 27, 2018 at 06:27:24PM +0200, Greg Kroah-Hartman wrote: > > > 4.4-stable review patch. If anyone has any objections, please let me > > > know. > > > : > > > >

Re: [PATCH] nfit: skip region registration for incomplete control regions

On Wed, 2018-03-21 at 21:42 -0700, Dan Williams wrote: > Per the ACPI specification the only functional purpose for a DIMM > Control Region to be mapped into the system physical address space, from > an OSPM perspective, is to support block-apertures. However, there are > some BIOSen that publish

Re: [PATCH 4.4 20/43] mm/vmalloc: add interfaces to free unmapped page table

n Chancellor wrote: > > > > On Tue, Mar 27, 2018 at 08:40:56PM +, Kani, Toshi wrote: > > > > > On Tue, 2018-03-27 at 13:31 -0700, Nathan Chancellor wrote: > > > > > > On Tue, Mar 27, 2018 at 03:17:00PM -0500, Dan Rue wrote: > > > > > > &g

Re: [PATCH v4 1/3] ioremap: Update pgtable free interfaces with addr

; Signed-off-by: Chintan Pandya Thanks for the update. The change looks good. Reviewed-by: Toshi Kani -Toshi

Re: [PATCH 1/2] mm/vmalloc: Add interfaces to free unused page table

On Wed, 2018-03-07 at 20:00 -0800, Matthew Wilcox wrote: > On Wed, Mar 07, 2018 at 11:32:26AM -0700, Toshi Kani wrote: > > +/** > > + * pud_free_pmd_page - clear pud entry and free pmd page > > + * > > + * Returns 1 on success and 0 on failure (pud not cleared). > > + */ > > +int

Re: [PATCH 1/2] mm/vmalloc: Add interfaces to free unused page table

On Thu, 2018-03-08 at 18:04 +, Will Deacon wrote: : > > diff --git a/lib/ioremap.c b/lib/ioremap.c > > index b808a390e4c3..54e5bbaa3200 100644 > > --- a/lib/ioremap.c > > +++ b/lib/ioremap.c > > @@ -91,7 +91,8 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned > > long addr, > > >

Re: Kernel page fault in vmalloc_fault() after a preempted ioremap

On Thu, 2018-03-08 at 14:34 -0600, Gratian Crisan wrote: > Hi all, > > We are seeing kernel page faults happening on module loads with certain > drivers like the i915 video driver[1]. This was initially discovered on > a 4.9 PREEMPT_RT kernel. It takes 5 days on average to reproduce using a >

Re: Kernel page fault in vmalloc_fault() after a preempted ioremap

On Thu, 2018-03-08 at 22:38 +, Andy Lutomirski wrote: > On Thu, Mar 8, 2018 at 9:43 PM, Kani, Toshi wrote: > > On Thu, 2018-03-08 at 14:34 -0600, Gratian Crisan wrote: : > > > > Thanks for the report and analysis! I believe pud_large() and > > pmd_large() sho

Re: [PATCH 1/2] mm/vmalloc: Add interfaces to free unused page table

On Thu, 2018-03-08 at 14:07 -0800, Matthew Wilcox wrote: > On Thu, Mar 08, 2018 at 03:56:30PM +0000, Kani, Toshi wrote: > > On Wed, 2018-03-07 at 20:00 -0800, Matthew Wilcox wrote: > > > On Wed, Mar 07, 2018 at 11:32:26AM -0700, Toshi Kani wrote: > > > > +/** > &g

Re: [PATCH v2 1/2] mm/vmalloc: Add interfaces to free unmapped page table

On Wed, 2018-03-14 at 15:38 -0700, Andrew Morton wrote: > On Wed, 14 Mar 2018 12:01:54 -0600 Toshi Kani wrote: : > > whoops. > > --- > a/include/asm-generic/pgtable.h~mm-vmalloc-add-interfaces-to-free-unmapped-page-table-fix > +++ a/include/asm-generic/pgtable.h > @@ -1014,7 +1014,7 @@ static

Re: [PATCH v1 0/4] Fix issues with huge mapping in ioremap

On Thu, 2018-03-15 at 12:47 +0530, Chintan Pandya wrote: > > On 3/14/2018 8:08 PM, Kani, Toshi wrote: > > On Wed, 2018-03-14 at 14:18 +0530, Chintan Pandya wrote: > > > Note: I was working on these patches for quite sometime > > > and realized that Tosh

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Thu, 2018-03-15 at 13:09 +0530, Chintan Pandya wrote: > > On 3/14/2018 11:31 PM, Toshi Kani wrote: > > Implement pud_free_pmd_page() and pmd_free_pte_page() on x86, which > > clear a given pud/pmd entry and free up lower level page table(s). > > Address range associated with the pud/pmd entry

Re: [PATCH v2 2/4] ioremap: Implement TLB_INV before huge mapping

On Thu, 2018-03-15 at 18:15 +0530, Chintan Pandya wrote: > Huge mapping changes PMD/PUD which could have > valid previous entries. This requires proper > TLB maintanance on some architectures, like > ARM64. > > Implent BBM (break-before-make) safe TLB > invalidation. > > Here, I've used

Re: [PATCH v2 2/4] ioremap: Implement TLB_INV before huge mapping

On Fri, 2018-03-16 at 13:10 +0530, Chintan Pandya wrote: > > On 3/15/2018 9:42 PM, Kani, Toshi wrote: > > On Thu, 2018-03-15 at 18:15 +0530, Chintan Pandya wrote: > > > Huge mapping changes PMD/PUD which could have > > > valid previous entries. This requires proper

Re: [RFC patch] ioremap: don't set up huge I/O mappings when p4d/pud/pmd is zero

On Tue, 2018-02-20 at 14:54 +0530, Chintan Pandya wrote: > > On 12/28/2017 4:54 PM, Hanjun Guo wrote: > > From: Hanjun Guo > > > > When we using iounmap() to free the 4K mapping, it just clear the PTEs > > but leave P4D/PUD/PMD unchanged, also will not free the memory of page > > tables. > > >

Re: [PATCH 2/3] x86/mm: add TLB purge to free pmd/pte page interfaces

On Tue, 2018-05-15 at 16:05 +0200, Joerg Roedel wrote: > On Mon, Apr 30, 2018 at 11:59:24AM -0600, Toshi Kani wrote: > > int pud_free_pmd_page(pud_t *pud, unsigned long addr) > > { > > - pmd_t *pmd; > > + pmd_t *pmd, *pmd_sv; > > + pte_t *pte; > > int i; > > > > if

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Fri, 2018-04-27 at 09:37 +0200, j...@8bytes.org wrote: > On Thu, Apr 26, 2018 at 10:30:14PM +0000, Kani, Toshi wrote: > > Thanks for the clarification. After reading through SDM one more time, I > > agree that we need a TLB purge here. Here is my current understanding. >

Re: [PATCH] Revert "x86/mm: implement free pmd/pte page interfaces"

On Fri, 2018-04-27 at 08:28 +0200, Ingo Molnar wrote: > * Kani, Toshi wrote: > > > On Thu, 2018-04-26 at 17:14 +0200, Joerg Roedel wrote: > > > From: Joerg Roedel > > > > > > This reverts commit 28ee90fe6048fa7b7ceaeb8831c0e4e454a4cf89. > > > &

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Sat, 2018-04-28 at 11:02 +0200, j...@8bytes.org wrote: > On Fri, Apr 27, 2018 at 02:31:51PM +0000, Kani, Toshi wrote: > > So, we can add the step 2 on top of this patch. > > 1. Clear pud/pmd entry. > > 2. System wide TLB flush <-- TO BE ADDED BY NEW PATCH > > 3

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Mon, 2018-04-30 at 13:00 +0530, Chintan Pandya wrote: > > On 4/29/2018 2:24 AM, Kani, Toshi wrote: > > On Sat, 2018-04-28 at 11:02 +0200, j...@8bytes.org wrote: > > > On Fri, Apr 27, 2018 at 02:31:51PM +, Kani, Toshi wrote: > > > > So, we can ad

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Thu, 2018-04-26 at 16:19 +0200, Joerg Roedel wrote: > Hi Toshi, Andrew, > > this patch(-set) is broken in several ways, please see below. > > On Wed, Mar 14, 2018 at 12:01:55PM -0600, Toshi Kani wrote: > > Implement pud_free_pmd_page() and pmd_free_pte_page() on x86, which > > clear a given

Re: [PATCH] Revert "x86/mm: implement free pmd/pte page interfaces"

On Thu, 2018-04-26 at 17:14 +0200, Joerg Roedel wrote: > From: Joerg Roedel > > This reverts commit 28ee90fe6048fa7b7ceaeb8831c0e4e454a4cf89. > > This commit is broken for x86, as it unmaps the PTE and PMD > pages and immediatly frees them without doing a TLB flush. > > Further this lacks

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Thu, 2018-04-26 at 19:23 +0200, j...@8bytes.org wrote: > On Thu, Apr 26, 2018 at 04:21:19PM +0000, Kani, Toshi wrote: > > All pages under the pmd had been unmapped and then lazy TLB purged with > > INVLPG before coming to this code path. Speculation is not allowed to > >

Re: [PATCH v2 2/2] x86/mm: implement free pmd/pte page interfaces

On Thu, 2018-04-26 at 22:07 +0200, j...@8bytes.org wrote: > On Thu, Apr 26, 2018 at 05:49:58PM +0000, Kani, Toshi wrote: > > On Thu, 2018-04-26 at 19:23 +0200, j...@8bytes.org wrote: > > > So the PMD entry you clear can still be in a page-walk cache and this > > > nee

Re: [PATCH v2 1/3] x86/mm: disable ioremap free page handling on x86-PAE

On Wed, 2018-05-16 at 19:00 +0800, kbuild test robot wrote: > Hi Toshi, > > Thank you for the patch! Yet something to improve: > > [auto build test ERROR on arm64/for-next/core] > [also build test ERROR on v4.17-rc5 next-20180515] > [cannot apply to tip/x86/core] > [if your patch is applied to

Re: [PATCH v3 2/3] ioremap: Update pgtable free interfaces with addr

On Thu, 2018-05-17 at 08:47 +0200, Michal Hocko wrote: > On Wed 16-05-18 17:32:06, Kani Toshimitsu wrote: > > From: Chintan Pandya > > > > This patch ("mm/vmalloc: Add interfaces to free unmapped > > page table") adds following 2 interfaces to free the page > > table in case we implement huge

Re: [PATCH 3/3] x86/mm: disable ioremap free page handling on x86-PAE

On Mon, 2018-04-30 at 11:59 -0600, Toshi Kani wrote: > ioremap() supports pmd mappings on x86-PAE. However, kernel's pmd > tables are not shared among processes on x86-PAE. Therefore, any > update to sync'd pmd entries need re-syncing. Freeing a pte page > also leads to a vmalloc fault and hits

Re: [RFC patch] ioremap: don't set up huge I/O mappings when p4d/pud/pmd is zero

On Sat, 2018-01-06 at 17:46 +0800, Hanjun Guo wrote: > On 2018/1/6 6:15, Kani, Toshi wrote: > > On Thu, 2017-12-28 at 19:24 +0800, Hanjun Guo wrote: > > > From: Hanjun Guo > > > > > > When we using iounmap() to free the 4K mapping, it just clear the PTEs &

Re: [RFC patch] ioremap: don't set up huge I/O mappings when p4d/pud/pmd is zero

On Thu, 2017-12-28 at 19:24 +0800, Hanjun Guo wrote: > From: Hanjun Guo > > When we using iounmap() to free the 4K mapping, it just clear the PTEs > but leave P4D/PUD/PMD unchanged, also will not free the memory of page > tables. > > This will cause issues on ARM64 platform (not sure if other

Re: [RFC PATCH] lib/ioremap: Avoid triggering BUG_ON when end is not PAGE_ALIGN

On Fri, 2018-03-30 at 12:49 +0800, Yisheng Xie wrote: > Zhou reported a bug on Hisilicon arm64 D06 platform with 64KB page size: : > The cause is the size of PCI IO resource is 32KB, which is 4K aligned but > not 64KB aligned, so when do ioremap_pte_range(), its incoming end is not > PAGE_ALIGN

Re: [PATCH] acpi, numa: fix pxm to online numa node associations

node = n; < from this point we're using the > wrong node for node_distance() ouch... > > > Fixes: 99759869faf1 ("acpi: Add acpi_map_pxm_to_online_node()") > Cc: > Cc: Toshi Kani > Cc: Rafael J. Wysocki &g

Re: [PATCH v3 1/3] ioremap: Update pgtable free interfaces with addr

On Mon, 2018-03-19 at 18:10 +0530, Chintan Pandya wrote: > This patch ("mm/vmalloc: Add interfaces to free unmapped > page table") adds following 2 interfaces to free the page > table in case we implement huge mapping. > > pud_free_pmd_page() and pmd_free_pte_page() > > Some architectures (like

Re: [PATCH v3 2/3] arm64: Implement page table free interfaces

On Mon, 2018-03-19 at 18:10 +0530, Chintan Pandya wrote: > Implement pud_free_pmd_page() and pmd_free_pte_page(). > > Implementation requires, > 1) Freeing of the un-used next level page tables > 2) Clearing off the current pud/pmd entry > 3) Invalidate TLB which could have previously >

Re: [PATCH 1/2] mm/vmalloc: Add interfaces to free unused page table

On Wed, 2018-03-07 at 14:54 -0800, Andrew Morton wrote: > On Wed, 7 Mar 2018 11:32:26 -0700 Toshi Kani wrote: > > > On architectures with CONFIG_HAVE_ARCH_HUGE_VMAP set, ioremap() > > may create pud/pmd mappings. Kernel panic was observed on arm64 > > systems with Cortex-A75 in the following

Re: [PATCH 2/2] x86/mm: implement free pmd/pte page interfaces

On Wed, 2018-03-07 at 15:01 -0800, Andrew Morton wrote: > On Wed, 7 Mar 2018 11:32:27 -0700 Toshi Kani wrote: > > > Implement pud_free_pmd_page() and pmd_free_pte_page() on x86, which > > clear a given pud/pmd entry and free up lower level page table(s). > > Address range associated with the

  1   2   >