summaryrefslogtreecommitdiff
path: root/drivers/iommu/amd
diff options
context:
space:
mode:
authorSuravee Suthikulpanit <suravee.suthikulpanit@amd.com>2020-12-15 01:36:58 -0600
committerJoerg Roedel <jroedel@suse.de>2021-01-28 16:51:17 +0100
commit18954252a1d0b12e1b77087b55c37fb43b09e12a (patch)
tree93718f36eb23c206f852dc04d9885be794a37b92 /drivers/iommu/amd
parentf9b4df790aa4372bfa11b7d212e537b763295429 (diff)
iommu/amd: Move IO page table related functions
Preparing to migrate to use IO page table framework. There is no functional change. Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com> Link: https://lore.kernel.org/r/20201215073705.123786-7-suravee.suthikulpanit@amd.com Signed-off-by: Joerg Roedel <jroedel@suse.de>
Diffstat (limited to 'drivers/iommu/amd')
-rw-r--r--drivers/iommu/amd/amd_iommu.h18
-rw-r--r--drivers/iommu/amd/io_pgtable.c473
-rw-r--r--drivers/iommu/amd/iommu.c476
3 files changed, 493 insertions, 474 deletions
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index bf29ab8c99f0..1bad42a3c73c 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -131,4 +131,22 @@ void amd_iommu_apply_ivrs_quirks(void);
static inline void amd_iommu_apply_ivrs_quirks(void) { }
#endif
+/* TODO: These are temporary and will be removed once fully transition */
+extern void free_pagetable(struct domain_pgtable *pgtable);
+extern int iommu_map_page(struct protection_domain *dom,
+ unsigned long bus_addr,
+ unsigned long phys_addr,
+ unsigned long page_size,
+ int prot,
+ gfp_t gfp);
+extern unsigned long iommu_unmap_page(struct protection_domain *dom,
+ unsigned long bus_addr,
+ unsigned long page_size);
+extern u64 *fetch_pte(struct protection_domain *domain,
+ unsigned long address,
+ unsigned long *page_size);
+extern void amd_iommu_domain_get_pgtable(struct protection_domain *domain,
+ struct domain_pgtable *pgtable);
+extern void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
+ u64 *root, int mode);
#endif
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index cf2cd2d2e43e..dbc0ad775d5e 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -45,6 +45,479 @@ static const struct iommu_flush_ops v1_flush_ops = {
};
/*
+ * Helper function to get the first pte of a large mapping
+ */
+static u64 *first_pte_l7(u64 *pte, unsigned long *page_size,
+ unsigned long *count)
+{
+ unsigned long pte_mask, pg_size, cnt;
+ u64 *fpte;
+
+ pg_size = PTE_PAGE_SIZE(*pte);
+ cnt = PAGE_SIZE_PTE_COUNT(pg_size);
+ pte_mask = ~((cnt << 3) - 1);
+ fpte = (u64 *)(((unsigned long)pte) & pte_mask);
+
+ if (page_size)
+ *page_size = pg_size;
+
+ if (count)
+ *count = cnt;
+
+ return fpte;
+}
+
+/****************************************************************************
+ *
+ * The functions below are used the create the page table mappings for
+ * unity mapped regions.
+ *
+ ****************************************************************************/
+
+static void free_page_list(struct page *freelist)
+{
+ while (freelist != NULL) {
+ unsigned long p = (unsigned long)page_address(freelist);
+
+ freelist = freelist->freelist;
+ free_page(p);
+ }
+}
+
+static struct page *free_pt_page(unsigned long pt, struct page *freelist)
+{
+ struct page *p = virt_to_page((void *)pt);
+
+ p->freelist = freelist;
+
+ return p;
+}
+
+#define DEFINE_FREE_PT_FN(LVL, FN) \
+static struct page *free_pt_##LVL (unsigned long __pt, struct page *freelist) \
+{ \
+ unsigned long p; \
+ u64 *pt; \
+ int i; \
+ \
+ pt = (u64 *)__pt; \
+ \
+ for (i = 0; i < 512; ++i) { \
+ /* PTE present? */ \
+ if (!IOMMU_PTE_PRESENT(pt[i])) \
+ continue; \
+ \
+ /* Large PTE? */ \
+ if (PM_PTE_LEVEL(pt[i]) == 0 || \
+ PM_PTE_LEVEL(pt[i]) == 7) \
+ continue; \
+ \
+ p = (unsigned long)IOMMU_PTE_PAGE(pt[i]); \
+ freelist = FN(p, freelist); \
+ } \
+ \
+ return free_pt_page((unsigned long)pt, freelist); \
+}
+
+DEFINE_FREE_PT_FN(l2, free_pt_page)
+DEFINE_FREE_PT_FN(l3, free_pt_l2)
+DEFINE_FREE_PT_FN(l4, free_pt_l3)
+DEFINE_FREE_PT_FN(l5, free_pt_l4)
+DEFINE_FREE_PT_FN(l6, free_pt_l5)
+
+static struct page *free_sub_pt(unsigned long root, int mode,
+ struct page *freelist)
+{
+ switch (mode) {
+ case PAGE_MODE_NONE:
+ case PAGE_MODE_7_LEVEL:
+ break;
+ case PAGE_MODE_1_LEVEL:
+ freelist = free_pt_page(root, freelist);
+ break;
+ case PAGE_MODE_2_LEVEL:
+ freelist = free_pt_l2(root, freelist);
+ break;
+ case PAGE_MODE_3_LEVEL:
+ freelist = free_pt_l3(root, freelist);
+ break;
+ case PAGE_MODE_4_LEVEL:
+ freelist = free_pt_l4(root, freelist);
+ break;
+ case PAGE_MODE_5_LEVEL:
+ freelist = free_pt_l5(root, freelist);
+ break;
+ case PAGE_MODE_6_LEVEL:
+ freelist = free_pt_l6(root, freelist);
+ break;
+ default:
+ BUG();
+ }
+
+ return freelist;
+}
+
+void free_pagetable(struct domain_pgtable *pgtable)
+{
+ struct page *freelist = NULL;
+ unsigned long root;
+
+ if (pgtable->mode == PAGE_MODE_NONE)
+ return;
+
+ BUG_ON(pgtable->mode < PAGE_MODE_NONE ||
+ pgtable->mode > PAGE_MODE_6_LEVEL);
+
+ root = (unsigned long)pgtable->root;
+ freelist = free_sub_pt(root, pgtable->mode, freelist);
+
+ free_page_list(freelist);
+}
+
+void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
+ u64 *root, int mode)
+{
+ u64 pt_root;
+
+ /* lowest 3 bits encode pgtable mode */
+ pt_root = mode & 7;
+ pt_root |= (u64)root;
+
+ amd_iommu_domain_set_pt_root(domain, pt_root);
+}
+
+/*
+ * This function is used to add another level to an IO page table. Adding
+ * another level increases the size of the address space by 9 bits to a size up
+ * to 64 bits.
+ */
+static bool increase_address_space(struct protection_domain *domain,
+ unsigned long address,
+ gfp_t gfp)
+{
+ struct domain_pgtable pgtable;
+ unsigned long flags;
+ bool ret = true;
+ u64 *pte;
+
+ spin_lock_irqsave(&domain->lock, flags);
+
+ amd_iommu_domain_get_pgtable(domain, &pgtable);
+
+ if (address <= PM_LEVEL_SIZE(pgtable.mode))
+ goto out;
+
+ ret = false;
+ if (WARN_ON_ONCE(pgtable.mode == PAGE_MODE_6_LEVEL))
+ goto out;
+
+ pte = (void *)get_zeroed_page(gfp);
+ if (!pte)
+ goto out;
+
+ *pte = PM_LEVEL_PDE(pgtable.mode, iommu_virt_to_phys(pgtable.root));
+
+ pgtable.root = pte;
+ pgtable.mode += 1;
+ amd_iommu_update_and_flush_device_table(domain);
+ amd_iommu_domain_flush_complete(domain);
+
+ /*
+ * Device Table needs to be updated and flushed before the new root can
+ * be published.
+ */
+ amd_iommu_domain_set_pgtable(domain, pte, pgtable.mode);
+
+ ret = true;
+
+out:
+ spin_unlock_irqrestore(&domain->lock, flags);
+
+ return ret;
+}
+
+static u64 *alloc_pte(struct protection_domain *domain,
+ unsigned long address,
+ unsigned long page_size,
+ u64 **pte_page,
+ gfp_t gfp,
+ bool *updated)
+{
+ struct domain_pgtable pgtable;
+ int level, end_lvl;
+ u64 *pte, *page;
+
+ BUG_ON(!is_power_of_2(page_size));
+
+ amd_iommu_domain_get_pgtable(domain, &pgtable);
+
+ while (address > PM_LEVEL_SIZE(pgtable.mode)) {
+ /*
+ * Return an error if there is no memory to update the
+ * page-table.
+ */
+ if (!increase_address_space(domain, address, gfp))
+ return NULL;
+
+ /* Read new values to check if update was successful */
+ amd_iommu_domain_get_pgtable(domain, &pgtable);
+ }
+
+
+ level = pgtable.mode - 1;
+ pte = &pgtable.root[PM_LEVEL_INDEX(level, address)];
+ address = PAGE_SIZE_ALIGN(address, page_size);
+ end_lvl = PAGE_SIZE_LEVEL(page_size);
+
+ while (level > end_lvl) {
+ u64 __pte, __npte;
+ int pte_level;
+
+ __pte = *pte;
+ pte_level = PM_PTE_LEVEL(__pte);
+
+ /*
+ * If we replace a series of large PTEs, we need
+ * to tear down all of them.
+ */
+ if (IOMMU_PTE_PRESENT(__pte) &&
+ pte_level == PAGE_MODE_7_LEVEL) {
+ unsigned long count, i;
+ u64 *lpte;
+
+ lpte = first_pte_l7(pte, NULL, &count);
+
+ /*
+ * Unmap the replicated PTEs that still match the
+ * original large mapping
+ */
+ for (i = 0; i < count; ++i)
+ cmpxchg64(&lpte[i], __pte, 0ULL);
+
+ *updated = true;
+ continue;
+ }
+
+ if (!IOMMU_PTE_PRESENT(__pte) ||
+ pte_level == PAGE_MODE_NONE) {
+ page = (u64 *)get_zeroed_page(gfp);
+
+ if (!page)
+ return NULL;
+
+ __npte = PM_LEVEL_PDE(level, iommu_virt_to_phys(page));
+
+ /* pte could have been changed somewhere. */
+ if (cmpxchg64(pte, __pte, __npte) != __pte)
+ free_page((unsigned long)page);
+ else if (IOMMU_PTE_PRESENT(__pte))
+ *updated = true;
+
+ continue;
+ }
+
+ /* No level skipping support yet */
+ if (pte_level != level)
+ return NULL;
+
+ level -= 1;
+
+ pte = IOMMU_PTE_PAGE(__pte);
+
+ if (pte_page && level == end_lvl)
+ *pte_page = pte;
+
+ pte = &pte[PM_LEVEL_INDEX(level, address)];
+ }
+
+ return pte;
+}
+
+/*
+ * This function checks if there is a PTE for a given dma address. If
+ * there is one, it returns the pointer to it.
+ */
+u64 *fetch_pte(struct protection_domain *domain,
+ unsigned long address,
+ unsigned long *page_size)
+{
+ struct domain_pgtable pgtable;
+ int level;
+ u64 *pte;
+
+ *page_size = 0;
+
+ amd_iommu_domain_get_pgtable(domain, &pgtable);
+
+ if (address > PM_LEVEL_SIZE(pgtable.mode))
+ return NULL;
+
+ level = pgtable.mode - 1;
+ pte = &pgtable.root[PM_LEVEL_INDEX(level, address)];
+ *page_size = PTE_LEVEL_PAGE_SIZE(level);
+
+ while (level > 0) {
+
+ /* Not Present */
+ if (!IOMMU_PTE_PRESENT(*pte))
+ return NULL;
+
+ /* Large PTE */
+ if (PM_PTE_LEVEL(*pte) == 7 ||
+ PM_PTE_LEVEL(*pte) == 0)
+ break;
+
+ /* No level skipping support yet */
+ if (PM_PTE_LEVEL(*pte) != level)
+ return NULL;
+
+ level -= 1;
+
+ /* Walk to the next level */
+ pte = IOMMU_PTE_PAGE(*pte);
+ pte = &pte[PM_LEVEL_INDEX(level, address)];
+ *page_size = PTE_LEVEL_PAGE_SIZE(level);
+ }
+
+ /*
+ * If we have a series of large PTEs, make
+ * sure to return a pointer to the first one.
+ */
+ if (PM_PTE_LEVEL(*pte) == PAGE_MODE_7_LEVEL)
+ pte = first_pte_l7(pte, page_size, NULL);
+
+ return pte;
+}
+
+static struct page *free_clear_pte(u64 *pte, u64 pteval, struct page *freelist)
+{
+ unsigned long pt;
+ int mode;
+
+ while (cmpxchg64(pte, pteval, 0) != pteval) {
+ pr_warn("AMD-Vi: IOMMU pte changed since we read it\n");
+ pteval = *pte;
+ }
+
+ if (!IOMMU_PTE_PRESENT(pteval))
+ return freelist;
+
+ pt = (unsigned long)IOMMU_PTE_PAGE(pteval);
+ mode = IOMMU_PTE_MODE(pteval);
+
+ return free_sub_pt(pt, mode, freelist);
+}
+
+/*
+ * Generic mapping functions. It maps a physical address into a DMA
+ * address space. It allocates the page table pages if necessary.
+ * In the future it can be extended to a generic mapping function
+ * supporting all features of AMD IOMMU page tables like level skipping
+ * and full 64 bit address spaces.
+ */
+int iommu_map_page(struct protection_domain *dom,
+ unsigned long bus_addr,
+ unsigned long phys_addr,
+ unsigned long page_size,
+ int prot,
+ gfp_t gfp)
+{
+ struct page *freelist = NULL;
+ bool updated = false;
+ u64 __pte, *pte;
+ int ret, i, count;
+
+ BUG_ON(!IS_ALIGNED(bus_addr, page_size));
+ BUG_ON(!IS_ALIGNED(phys_addr, page_size));
+
+ ret = -EINVAL;
+ if (!(prot & IOMMU_PROT_MASK))
+ goto out;
+
+ count = PAGE_SIZE_PTE_COUNT(page_size);
+ pte = alloc_pte(dom, bus_addr, page_size, NULL, gfp, &updated);
+
+ ret = -ENOMEM;
+ if (!pte)
+ goto out;
+
+ for (i = 0; i < count; ++i)
+ freelist = free_clear_pte(&pte[i], pte[i], freelist);
+
+ if (freelist != NULL)
+ updated = true;
+
+ if (count > 1) {
+ __pte = PAGE_SIZE_PTE(__sme_set(phys_addr), page_size);
+ __pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_PR | IOMMU_PTE_FC;
+ } else
+ __pte = __sme_set(phys_addr) | IOMMU_PTE_PR | IOMMU_PTE_FC;
+
+ if (prot & IOMMU_PROT_IR)
+ __pte |= IOMMU_PTE_IR;
+ if (prot & IOMMU_PROT_IW)
+ __pte |= IOMMU_PTE_IW;
+
+ for (i = 0; i < count; ++i)
+ pte[i] = __pte;
+
+ ret = 0;
+
+out:
+ if (updated) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&dom->lock, flags);
+ /*
+ * Flush domain TLB(s) and wait for completion. Any Device-Table
+ * Updates and flushing already happened in
+ * increase_address_space().
+ */
+ amd_iommu_domain_flush_tlb_pde(dom);
+ amd_iommu_domain_flush_complete(dom);
+ spin_unlock_irqrestore(&dom->lock, flags);
+ }
+
+ /* Everything flushed out, free pages now */
+ free_page_list(freelist);
+
+ return ret;
+}
+
+unsigned long iommu_unmap_page(struct protection_domain *dom,
+ unsigned long bus_addr,
+ unsigned long page_size)
+{
+ unsigned long long unmapped;
+ unsigned long unmap_size;
+ u64 *pte;
+
+ BUG_ON(!is_power_of_2(page_size));
+
+ unmapped = 0;
+
+ while (unmapped < page_size) {
+
+ pte = fetch_pte(dom, bus_addr, &unmap_size);
+
+ if (pte) {
+ int i, count;
+
+ count = PAGE_SIZE_PTE_COUNT(unmap_size);
+ for (i = 0; i < count; i++)
+ pte[i] = 0ULL;
+ }
+
+ bus_addr = (bus_addr & ~(unmap_size - 1)) + unmap_size;
+ unmapped += unmap_size;
+ }
+
+ BUG_ON(unmapped && !is_power_of_2(unmapped));
+
+ return unmapped;
+}
+
+/*
* ----------------------------------------------------
*/
static void v1_free_pgtable(struct io_pgtable *iop)
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 76e69c510db8..eda8e196fb14 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -138,8 +138,8 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom)
return container_of(dom, struct protection_domain, domain);
}
-static void amd_iommu_domain_get_pgtable(struct protection_domain *domain,
- struct domain_pgtable *pgtable)
+void amd_iommu_domain_get_pgtable(struct protection_domain *domain,
+ struct domain_pgtable *pgtable)
{
u64 pt_root = atomic64_read(&domain->iop.pt_root);
@@ -147,18 +147,6 @@ static void amd_iommu_domain_get_pgtable(struct protection_domain *domain,
pgtable->mode = pt_root & 7; /* lowest 3 bits encode pgtable mode */
}
-static void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
- u64 *root, int mode)
-{
- u64 pt_root;
-
- /* lowest 3 bits encode pgtable mode */
- pt_root = mode & 7;
- pt_root |= (u64)root;
-
- amd_iommu_domain_set_pt_root(domain, pt_root);
-}
-
static struct iommu_dev_data *alloc_dev_data(u16 devid)
{
struct iommu_dev_data *dev_data;
@@ -414,29 +402,6 @@ static void amd_iommu_uninit_device(struct device *dev)
*/
}
-/*
- * Helper function to get the first pte of a large mapping
- */
-static u64 *first_pte_l7(u64 *pte, unsigned long *page_size,
- unsigned long *count)
-{
- unsigned long pte_mask, pg_size, cnt;
- u64 *fpte;
-
- pg_size = PTE_PAGE_SIZE(*pte);
- cnt = PAGE_SIZE_PTE_COUNT(pg_size);
- pte_mask = ~((cnt << 3) - 1);
- fpte = (u64 *)(((unsigned long)pte) & pte_mask);
-
- if (page_size)
- *page_size = pg_size;
-
- if (count)
- *count = cnt;
-
- return fpte;
-}
-
/****************************************************************************
*
* Interrupt handling functions
@@ -1361,443 +1326,6 @@ static void domain_flush_devices(struct protection_domain *domain)
/****************************************************************************
*
- * The functions below are used the create the page table mappings for
- * unity mapped regions.
- *
- ****************************************************************************/
-
-static void free_page_list(struct page *freelist)
-{
- while (freelist != NULL) {
- unsigned long p = (unsigned long)page_address(freelist);
- freelist = freelist->freelist;
- free_page(p);
- }
-}
-
-static struct page *free_pt_page(unsigned long pt, struct page *freelist)
-{
- struct page *p = virt_to_page((void *)pt);
-
- p->freelist = freelist;
-
- return p;
-}
-
-#define DEFINE_FREE_PT_FN(LVL, FN) \
-static struct page *free_pt_##LVL (unsigned long __pt, struct page *freelist) \
-{ \
- unsigned long p; \
- u64 *pt; \
- int i; \
- \
- pt = (u64 *)__pt; \
- \
- for (i = 0; i < 512; ++i) { \
- /* PTE present? */ \
- if (!IOMMU_PTE_PRESENT(pt[i])) \
- continue; \
- \
- /* Large PTE? */ \
- if (PM_PTE_LEVEL(pt[i]) == 0 || \
- PM_PTE_LEVEL(pt[i]) == 7) \
- continue; \
- \
- p = (unsigned long)IOMMU_PTE_PAGE(pt[i]); \
- freelist = FN(p, freelist); \
- } \
- \
- return free_pt_page((unsigned long)pt, freelist); \
-}
-
-DEFINE_FREE_PT_FN(l2, free_pt_page)
-DEFINE_FREE_PT_FN(l3, free_pt_l2)
-DEFINE_FREE_PT_FN(l4, free_pt_l3)
-DEFINE_FREE_PT_FN(l5, free_pt_l4)
-DEFINE_FREE_PT_FN(l6, free_pt_l5)
-
-static struct page *free_sub_pt(unsigned long root, int mode,
- struct page *freelist)
-{
- switch (mode) {
- case PAGE_MODE_NONE:
- case PAGE_MODE_7_LEVEL:
- break;
- case PAGE_MODE_1_LEVEL:
- freelist = free_pt_page(root, freelist);
- break;
- case PAGE_MODE_2_LEVEL:
- freelist = free_pt_l2(root, freelist);
- break;
- case PAGE_MODE_3_LEVEL:
- freelist = free_pt_l3(root, freelist);
- break;
- case PAGE_MODE_4_LEVEL:
- freelist = free_pt_l4(root, freelist);
- break;
- case PAGE_MODE_5_LEVEL:
- freelist = free_pt_l5(root, freelist);
- break;
- case PAGE_MODE_6_LEVEL:
- freelist = free_pt_l6(root, freelist);
- break;
- default:
- BUG();
- }
-
- return freelist;
-}
-
-static void free_pagetable(struct domain_pgtable *pgtable)
-{
- struct page *freelist = NULL;
- unsigned long root;
-
- if (pgtable->mode == PAGE_MODE_NONE)
- return;
-
- BUG_ON(pgtable->mode < PAGE_MODE_NONE ||
- pgtable->mode > PAGE_MODE_6_LEVEL);
-
- root = (unsigned long)pgtable->root;
- freelist = free_sub_pt(root, pgtable->mode, freelist);
-
- free_page_list(freelist);
-}
-
-/*
- * This function is used to add another level to an IO page table. Adding
- * another level increases the size of the address space by 9 bits to a size up
- * to 64 bits.
- */
-static bool increase_address_space(struct protection_domain *domain,
- unsigned long address,
- gfp_t gfp)
-{
- struct domain_pgtable pgtable;
- unsigned long flags;
- bool ret = true;
- u64 *pte;
-
- spin_lock_irqsave(&domain->lock, flags);
-
- amd_iommu_domain_get_pgtable(domain, &pgtable);
-
- if (address <= PM_LEVEL_SIZE(pgtable.mode))
- goto out;
-
- ret = false;
- if (WARN_ON_ONCE(pgtable.mode == PAGE_MODE_6_LEVEL))
- goto out;
-
- pte = (void *)get_zeroed_page(gfp);
- if (!pte)
- goto out;
-
- *pte = PM_LEVEL_PDE(pgtable.mode, iommu_virt_to_phys(pgtable.root));
-
- pgtable.root = pte;
- pgtable.mode += 1;
- amd_iommu_update_and_flush_device_table(domain);
- amd_iommu_domain_flush_complete(domain);
-
- /*
- * Device Table needs to be updated and flushed before the new root can
- * be published.
- */
- amd_iommu_domain_set_pgtable(domain, pte, pgtable.mode);
-
- ret = true;
-
-out:
- spin_unlock_irqrestore(&domain->lock, flags);
-
- return ret;
-}
-
-static u64 *alloc_pte(struct protection_domain *domain,
- unsigned long address,
- unsigned long page_size,
- u64 **pte_page,
- gfp_t gfp,
- bool *updated)
-{
- struct domain_pgtable pgtable;
- int level, end_lvl;
- u64 *pte, *page;
-
- BUG_ON(!is_power_of_2(page_size));
-
- amd_iommu_domain_get_pgtable(domain, &pgtable);
-
- while (address > PM_LEVEL_SIZE(pgtable.mode)) {
- /*
- * Return an error if there is no memory to update the
- * page-table.
- */
- if (!increase_address_space(domain, address, gfp))
- return NULL;
-
- /* Read new values to check if update was successful */
- amd_iommu_domain_get_pgtable(domain, &pgtable);
- }
-
-
- level = pgtable.mode - 1;
- pte = &pgtable.root[PM_LEVEL_INDEX(level, address)];
- address = PAGE_SIZE_ALIGN(address, page_size);
- end_lvl = PAGE_SIZE_LEVEL(page_size);
-
- while (level > end_lvl) {
- u64 __pte, __npte;
- int pte_level;
-
- __pte = *pte;
- pte_level = PM_PTE_LEVEL(__pte);
-
- /*
- * If we replace a series of large PTEs, we need
- * to tear down all of them.
- */
- if (IOMMU_PTE_PRESENT(__pte) &&
- pte_level == PAGE_MODE_7_LEVEL) {
- unsigned long count, i;
- u64 *lpte;
-
- lpte = first_pte_l7(pte, NULL, &count);
-
- /*
- * Unmap the replicated PTEs that still match the
- * original large mapping
- */
- for (i = 0; i < count; ++i)
- cmpxchg64(&lpte[i], __pte, 0ULL);
-
- *updated = true;
- continue;
- }
-
- if (!IOMMU_PTE_PRESENT(__pte) ||
- pte_level == PAGE_MODE_NONE) {
- page = (u64 *)get_zeroed_page(gfp);
-
- if (!page)
- return NULL;
-
- __npte = PM_LEVEL_PDE(level, iommu_virt_to_phys(page));
-
- /* pte could have been changed somewhere. */
- if (cmpxchg64(pte, __pte, __npte) != __pte)
- free_page((unsigned long)page);
- else if (IOMMU_PTE_PRESENT(__pte))
- *updated = true;
-
- continue;
- }
-
- /* No level skipping support yet */
- if (pte_level != level)
- return NULL;
-
- level -= 1;
-
- pte = IOMMU_PTE_PAGE(__pte);
-
- if (pte_page && level == end_lvl)
- *pte_page = pte;
-
- pte = &pte[PM_LEVEL_INDEX(level, address)];
- }
-
- return pte;
-}
-
-/*
- * This function checks if there is a PTE for a given dma address. If
- * there is one, it returns the pointer to it.
- */
-static u64 *fetch_pte(struct protection_domain *domain,
- unsigned long address,
- unsigned long *page_size)
-{
- struct domain_pgtable pgtable;
- int level;
- u64 *pte;
-
- *page_size = 0;
-
- amd_iommu_domain_get_pgtable(domain, &pgtable);
-
- if (address > PM_LEVEL_SIZE(pgtable.mode))
- return NULL;
-
- level = pgtable.mode - 1;
- pte = &pgtable.root[PM_LEVEL_INDEX(level, address)];
- *page_size = PTE_LEVEL_PAGE_SIZE(level);
-
- while (level > 0) {
-
- /* Not Present */
- if (!IOMMU_PTE_PRESENT(*pte))
- return NULL;
-
- /* Large PTE */
- if (PM_PTE_LEVEL(*pte) == 7 ||
- PM_PTE_LEVEL(*pte) == 0)
- break;
-
- /* No level skipping support yet */
- if (PM_PTE_LEVEL(*pte) != level)
- return NULL;
-
- level -= 1;
-
- /* Walk to the next level */
- pte = IOMMU_PTE_PAGE(*pte);
- pte = &pte[PM_LEVEL_INDEX(level, address)];
- *page_size = PTE_LEVEL_PAGE_SIZE(level);
- }
-
- /*
- * If we have a series of large PTEs, make
- * sure to return a pointer to the first one.
- */
- if (PM_PTE_LEVEL(*pte) == PAGE_MODE_7_LEVEL)
- pte = first_pte_l7(pte, page_size, NULL);
-
- return pte;
-}
-
-static struct page *free_clear_pte(u64 *pte, u64 pteval, struct page *freelist)
-{
- unsigned long pt;
- int mode;
-
- while (cmpxchg64(pte, pteval, 0) != pteval) {
- pr_warn("AMD-Vi: IOMMU pte changed since we read it\n");
- pteval = *pte;
- }
-
- if (!IOMMU_PTE_PRESENT(pteval))
- return freelist;
-
- pt = (unsigned long)IOMMU_PTE_PAGE(pteval);
- mode = IOMMU_PTE_MODE(pteval);
-
- return free_sub_pt(pt, mode, freelist);
-}
-
-/*
- * Generic mapping functions. It maps a physical address into a DMA
- * address space. It allocates the page table pages if necessary.
- * In the future it can be extended to a generic mapping function
- * supporting all features of AMD IOMMU page tables like level skipping
- * and full 64 bit address spaces.
- */
-static int iommu_map_page(struct protection_domain *dom,
- unsigned long bus_addr,
- unsigned long phys_addr,
- unsigned long page_size,
- int prot,
- gfp_t gfp)
-{
- struct page *freelist = NULL;
- bool updated = false;
- u64 __pte, *pte;
- int ret, i, count;
-
- BUG_ON(!IS_ALIGNED(bus_addr, page_size));
- BUG_ON(!IS_ALIGNED(phys_addr, page_size));
-
- ret = -EINVAL;
- if (!(prot & IOMMU_PROT_MASK))
- goto out;
-
- count = PAGE_SIZE_PTE_COUNT(page_size);
- pte = alloc_pte(dom, bus_addr, page_size, NULL, gfp, &updated);
-
- ret = -ENOMEM;
- if (!pte)
- goto out;
-
- for (i = 0; i < count; ++i)
- freelist = free_clear_pte(&pte[i], pte[i], freelist);
-
- if (freelist != NULL)
- updated = true;
-
- if (count > 1) {
- __pte = PAGE_SIZE_PTE(__sme_set(phys_addr), page_size);
- __pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_PR | IOMMU_PTE_FC;
- } else
- __pte = __sme_set(phys_addr) | IOMMU_PTE_PR | IOMMU_PTE_FC;
-
- if (prot & IOMMU_PROT_IR)
- __pte |= IOMMU_PTE_IR;
- if (prot & IOMMU_PROT_IW)
- __pte |= IOMMU_PTE_IW;
-
- for (i = 0; i < count; ++i)
- pte[i] = __pte;
-
- ret = 0;
-
-out:
- if (updated) {
- unsigned long flags;
-
- spin_lock_irqsave(&dom->lock, flags);
- /*
- * Flush domain TLB(s) and wait for completion. Any Device-Table
- * Updates and flushing already happened in
- * increase_address_space().
- */
- amd_iommu_domain_flush_tlb_pde(dom);
- amd_iommu_domain_flush_complete(dom);
- spin_unlock_irqrestore(&dom->lock, flags);
- }
-
- /* Everything flushed out, free pages now */
- free_page_list(freelist);
-
- return ret;
-}
-
-static unsigned long iommu_unmap_page(struct protection_domain *dom,
- unsigned long bus_addr,
- unsigned long page_size)
-{
- unsigned long long unmapped;
- unsigned long unmap_size;
- u64 *pte;
-
- BUG_ON(!is_power_of_2(page_size));
-
- unmapped = 0;
-
- while (unmapped < page_size) {
-
- pte = fetch_pte(dom, bus_addr, &unmap_size);
-
- if (pte) {
- int i, count;
-
- count = PAGE_SIZE_PTE_COUNT(unmap_size);
- for (i = 0; i < count; i++)
- pte[i] = 0ULL;
- }
-
- bus_addr = (bus_addr & ~(unmap_size - 1)) + unmap_size;
- unmapped += unmap_size;
- }
-
- BUG_ON(unmapped && !is_power_of_2(unmapped));
-
- return unmapped;
-}
-
-/****************************************************************************
- *
* The next functions belong to the domain allocation. A domain is
* allocated for every IOMMU as the default domain. If device isolation
* is enabled, every device get its own domain. The most important thing