Re: [PATCH 06/18] iommu/fsl_pamu: remove ->domain_window_enable
From: Will Deacon <will@kernel.org>
Date: 2021-03-30 12:41:04
Also in:
dri-devel, kvm, linux-arm-kernel, linux-arm-msm, linux-iommu, netdev, virtualization
On Tue, Mar 16, 2021 at 04:38:12PM +0100, Christoph Hellwig wrote:
quoted hunk ↗ jump to hunk
The only thing that fsl_pamu_window_enable does for the current caller is to fill in the prot value in the only dma_window structure, and to propagate a few values from the iommu_domain_geometry struture into the dma_window. Remove the dma_window entirely, hardcode the prot value and otherwise use the iommu_domain_geometry structure instead. Remove the now unused ->domain_window_enable iommu method. Signed-off-by: Christoph Hellwig <hch@lst.de> Acked-by: Li Yang <redacted> --- drivers/iommu/fsl_pamu_domain.c | 182 +++------------------------- drivers/iommu/fsl_pamu_domain.h | 17 --- drivers/iommu/iommu.c | 11 -- drivers/soc/fsl/qbman/qman_portal.c | 7 -- include/linux/iommu.h | 17 --- 5 files changed, 14 insertions(+), 220 deletions(-)diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c index e6bdd38fc18409..fd2bc88b690465 100644 --- a/drivers/iommu/fsl_pamu_domain.c +++ b/drivers/iommu/fsl_pamu_domain.c@@ -54,34 +54,18 @@ static int __init iommu_init_mempool(void) return 0; } -static phys_addr_t get_phys_addr(struct fsl_dma_domain *dma_domain, dma_addr_t iova) -{ - struct dma_window *win_ptr = &dma_domain->win_arr[0]; - struct iommu_domain_geometry *geom; - - geom = &dma_domain->iommu_domain.geometry; - - if (win_ptr->valid) - return win_ptr->paddr + (iova & (win_ptr->size - 1)); - - return 0; -} - /* Map the DMA window corresponding to the LIODN */ static int map_liodn(int liodn, struct fsl_dma_domain *dma_domain) { int ret; - struct dma_window *wnd = &dma_domain->win_arr[0]; - phys_addr_t wnd_addr = dma_domain->iommu_domain.geometry.aperture_start; + struct iommu_domain_geometry *geom = &dma_domain->iommu_domain.geometry; unsigned long flags; spin_lock_irqsave(&iommu_lock, flags); - ret = pamu_config_ppaace(liodn, wnd_addr, - wnd->size, - ~(u32)0, - wnd->paddr >> PAMU_PAGE_SHIFT, - dma_domain->snoop_id, dma_domain->stash_id, - wnd->prot); + ret = pamu_config_ppaace(liodn, geom->aperture_start, + geom->aperture_end - 1, ~(u32)0,
You're passing 'geom->aperture_end - 1' as the size here, but the old code seemed to _add_ 1:
-static int fsl_pamu_window_enable(struct iommu_domain *domain, u32 wnd_nr,
- phys_addr_t paddr, u64 size, int prot)
-{
- struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
- struct dma_window *wnd;
- int pamu_prot = 0;
- int ret;
- unsigned long flags;
- u64 win_size;
-
- if (prot & IOMMU_READ)
- pamu_prot |= PAACE_AP_PERMS_QUERY;
- if (prot & IOMMU_WRITE)
- pamu_prot |= PAACE_AP_PERMS_UPDATE;
-
- spin_lock_irqsave(&dma_domain->domain_lock, flags);
- if (wnd_nr > 0) {
- pr_debug("Invalid window index\n");
- spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
- return -EINVAL;
- }
-
- win_size = (domain->geometry.aperture_end + 1) >> ilog2(1);here ^^ when calculating the exclusive upper bound. In other words, I think '1ULL << 36' used to get passed to pamu_config_ppaace(). Is that an intentional change? Will