From d239865ac804c91a621294ca7bece4241b006fae Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 28 Dec 2018 00:37:38 -0800 Subject: ioremap: rework pXd_free_pYd_page() API 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()) being called even on entries that aren't present. This resulted in a minor bug in the arm64 implementation, giving rise to spurious VM_WARN messages. This patch moves the pXd_present() checks out into the core code, refactoring the callsites at the same time so that we avoid the complex conjunctions when determining whether or not we can put down a huge mapping. Link: http://lkml.kernel.org/r/1544120495-17438-2-git-send-email-will.deacon@arm.com Signed-off-by: Will Deacon Reviewed-by: Toshi Kani Suggested-by: Linus Torvalds Cc: Chintan Pandya Cc: Toshi Kani Cc: Thomas Gleixner Cc: Michal Hocko Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Sean Christopherson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/ioremap.c | 56 ++++++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 42 insertions(+), 14 deletions(-) (limited to 'lib/ioremap.c') diff --git a/lib/ioremap.c b/lib/ioremap.c index 517f5853ffed..6c72764af19c 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -76,6 +76,25 @@ static int ioremap_pte_range(pmd_t *pmd, unsigned long addr, return 0; } +static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, + pgprot_t prot) +{ + if (!ioremap_pmd_enabled()) + return 0; + + if ((end - addr) != PMD_SIZE) + return 0; + + if (!IS_ALIGNED(phys_addr, PMD_SIZE)) + return 0; + + if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr)) + return 0; + + return pmd_set_huge(pmd, phys_addr, prot); +} + static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { @@ -89,13 +108,8 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, do { next = pmd_addr_end(addr, end); - if (ioremap_pmd_enabled() && - ((next - addr) == PMD_SIZE) && - IS_ALIGNED(phys_addr + addr, PMD_SIZE) && - pmd_free_pte_page(pmd, addr)) { - if (pmd_set_huge(pmd, phys_addr + addr, prot)) - continue; - } + if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr + addr, prot)) + continue; if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, prot)) return -ENOMEM; @@ -103,6 +117,25 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, return 0; } +static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, + pgprot_t prot) +{ + if (!ioremap_pud_enabled()) + return 0; + + if ((end - addr) != PUD_SIZE) + return 0; + + if (!IS_ALIGNED(phys_addr, PUD_SIZE)) + return 0; + + if (pud_present(*pud) && !pud_free_pmd_page(pud, addr)) + return 0; + + return pud_set_huge(pud, phys_addr, prot); +} + static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { @@ -116,13 +149,8 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, do { next = pud_addr_end(addr, end); - if (ioremap_pud_enabled() && - ((next - addr) == PUD_SIZE) && - IS_ALIGNED(phys_addr + addr, PUD_SIZE) && - pud_free_pmd_page(pud, addr)) { - if (pud_set_huge(pud, phys_addr + addr, prot)) - continue; - } + if (ioremap_try_huge_pud(pud, addr, next, phys_addr + addr, prot)) + continue; if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot)) return -ENOMEM; -- cgit v1.2.1 From 36ddc5a78c878e9b10c323d2fe88b0dae2f487eb Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 28 Dec 2018 00:37:49 -0800 Subject: lib/ioremap: ensure phys_addr actually corresponds to a physical address The current ioremap() code uses a phys_addr variable at each level of page table, which is confusingly offset by subtracting the base virtual address being mapped so that adding the current virtual address back on when iterating through the page table entries gives back the corresponding physical address. This is fairly confusing and results in all users of phys_addr having to add the current virtual address back on. Instead, this patch just updates phys_addr when iterating over the page table entries, ensuring that it's always up-to-date and doesn't require explicit offsetting. Link: http://lkml.kernel.org/r/1544120495-17438-5-git-send-email-will.deacon@arm.com Signed-off-by: Will Deacon Tested-by: Sean Christopherson Reviewed-by: Sean Christopherson Cc: Chintan Pandya Cc: Toshi Kani Cc: Thomas Gleixner Cc: Michal Hocko Cc: Sean Christopherson Cc: "H. Peter Anvin" Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/ioremap.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) (limited to 'lib/ioremap.c') diff --git a/lib/ioremap.c b/lib/ioremap.c index 6c72764af19c..10d7c5485c39 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -101,19 +101,18 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr, pmd_t *pmd; unsigned long next; - phys_addr -= addr; pmd = pmd_alloc(&init_mm, pud, addr); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); - if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr + addr, prot)) + if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr, prot)) continue; - if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, prot)) + if (ioremap_pte_range(pmd, addr, next, phys_addr, prot)) return -ENOMEM; - } while (pmd++, addr = next, addr != end); + } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); return 0; } @@ -142,19 +141,18 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, pud_t *pud; unsigned long next; - phys_addr -= addr; pud = pud_alloc(&init_mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); - if (ioremap_try_huge_pud(pud, addr, next, phys_addr + addr, prot)) + if (ioremap_try_huge_pud(pud, addr, next, phys_addr, prot)) continue; - if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot)) + if (ioremap_pmd_range(pud, addr, next, phys_addr, prot)) return -ENOMEM; - } while (pud++, addr = next, addr != end); + } while (pud++, phys_addr += (next - addr), addr = next, addr != end); return 0; } @@ -164,7 +162,6 @@ static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr, p4d_t *p4d; unsigned long next; - phys_addr -= addr; p4d = p4d_alloc(&init_mm, pgd, addr); if (!p4d) return -ENOMEM; @@ -173,14 +170,14 @@ static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr, if (ioremap_p4d_enabled() && ((next - addr) == P4D_SIZE) && - IS_ALIGNED(phys_addr + addr, P4D_SIZE)) { - if (p4d_set_huge(p4d, phys_addr + addr, prot)) + IS_ALIGNED(phys_addr, P4D_SIZE)) { + if (p4d_set_huge(p4d, phys_addr, prot)) continue; } - if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot)) + if (ioremap_pud_range(p4d, addr, next, phys_addr, prot)) return -ENOMEM; - } while (p4d++, addr = next, addr != end); + } while (p4d++, phys_addr += (next - addr), addr = next, addr != end); return 0; } @@ -196,14 +193,13 @@ int ioremap_page_range(unsigned long addr, BUG_ON(addr >= end); start = addr; - phys_addr -= addr; pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot); + err = ioremap_p4d_range(pgd, addr, next, phys_addr, prot); if (err) break; - } while (pgd++, addr = next, addr != end); + } while (pgd++, phys_addr += (next - addr), addr = next, addr != end); flush_cache_vmap(start, end); -- cgit v1.2.1 From 8e2d43405b22e98cf5f3730c1829ec1fdbe17ae7 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 28 Dec 2018 00:37:53 -0800 Subject: lib/ioremap: ensure break-before-make is used for huge p4d mappings Whilst no architectures actually enable support for huge p4d mappings in the vmap area, the code that is implemented should be using break-before-make, as we do for pud and pmd huge entries. Link: http://lkml.kernel.org/r/1544120495-17438-6-git-send-email-will.deacon@arm.com Signed-off-by: Will Deacon Reviewed-by: Toshi Kani Cc: Chintan Pandya Cc: Toshi Kani Cc: Thomas Gleixner Cc: Michal Hocko Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Sean Christopherson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/ioremap.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-) (limited to 'lib/ioremap.c') diff --git a/lib/ioremap.c b/lib/ioremap.c index 10d7c5485c39..063213685563 100644 --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -156,6 +156,25 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr, return 0; } +static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr, + unsigned long end, phys_addr_t phys_addr, + pgprot_t prot) +{ + if (!ioremap_p4d_enabled()) + return 0; + + if ((end - addr) != P4D_SIZE) + return 0; + + if (!IS_ALIGNED(phys_addr, P4D_SIZE)) + return 0; + + if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr)) + return 0; + + return p4d_set_huge(p4d, phys_addr, prot); +} + static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot) { @@ -168,12 +187,8 @@ static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr, do { next = p4d_addr_end(addr, end); - if (ioremap_p4d_enabled() && - ((next - addr) == P4D_SIZE) && - IS_ALIGNED(phys_addr, P4D_SIZE)) { - if (p4d_set_huge(p4d, phys_addr, prot)) - continue; - } + if (ioremap_try_huge_p4d(p4d, addr, next, phys_addr, prot)) + continue; if (ioremap_pud_range(p4d, addr, next, phys_addr, prot)) return -ENOMEM; -- cgit v1.2.1